Prediction of massive bleeding in pancreatic surgery based on preoperative patient characteristics using a decision tree

Taiichi Wakiya; Keinosuke Ishido; Norihisa Kimura; Hayato Nagase; Shunsuke Kubota; Hiroaki Fujita; Yusuke Hagiwara; Taishu Kanda; Masashi Matsuzaka; Yoshihiro Sasaki; Kenichi Hakamada

doi:10.1371/journal.pone.0259682

. 2021 Nov 9;16(11):e0259682. doi: 10.1371/journal.pone.0259682

Prediction of massive bleeding in pancreatic surgery based on preoperative patient characteristics using a decision tree

Taiichi Wakiya ^1,^*, Keinosuke Ishido ¹, Norihisa Kimura ¹, Hayato Nagase ¹, Shunsuke Kubota ¹, Hiroaki Fujita ¹, Yusuke Hagiwara ¹, Taishu Kanda ¹, Masashi Matsuzaka ², Yoshihiro Sasaki ², Kenichi Hakamada ¹

Editor: Ulrich Wellner³

PMCID: PMC8577735 PMID: 34752505

Abstract

Massive intraoperative blood loss (IBL) negatively influence outcomes after surgery for pancreatic ductal adenocarcinoma (PDAC). However, few data or predictive models are available for the identification of patients with a high risk for massive IBL. This study aimed to build a model for massive IBL prediction using a decision tree algorithm, which is one machine learning method. One hundred and seventy-five patients undergoing curative surgery for resectable PDAC at our facility between January 2007 and October 2020 were allocated to training (n = 128) and testing (n = 47) sets. Using the preoperatively available data of the patients (34 variables), we built a decision tree classification algorithm. Of the 175 patients, massive IBL occurred in 88 patients (50.3%). Binary logistic regression analysis indicated that alanine aminotransferase and distal pancreatectomy were significant predictors of massive IBL occurrence with an overall correct prediction rate of 70.3%. Decision tree analysis automatically selected 14 predictive variables. The best predictor was the surgical procedure. Though massive IBL was not common, the outcome of patients with distal pancreatectomy was secondarily split by glutamyl transpeptidase. Among patients who underwent PD (n = 83), diabetes mellitus (DM) was selected as the variable in the second split. Of the 21 patients with DM, massive IBL occurred in 85.7%. Decision tree sensitivity was 98.5% in the training data set and 100% in the testing data set. Our findings suggested that a decision tree can provide a new potential approach to predict massive IBL in surgery for resectable PDAC.

Introduction

Pancreatic ductal adenocarcinoma (PDAC) has the poorest prognosis of any cancer, worldwide [1]. In tackling this lethal disease, surgery has been one of the most fundamental treatment options [2–4]. Today, pancreatic cancer surgery outcomes have improved thanks to increasing experience and refinement in surgical technique, as well as centralization of patient care to high-volume centers [5–10]. However, due to the technical complexity of the procedure, pancreatic cancer surgery with lymph node dissection sometimes causes massive intraoperative blood loss (IBL), even when performed by experienced surgeons in high-volume centers [11]. As a result, allogeneic blood transfusion (ABT) has become commonplace for patients undergoing surgery for PDAC [11–13].

Although ABT can be a lifesaving treatment during pancreatic cancer surgery, it can cause an immunomodulatory effect called transfusion related immunomodulation [14–16]. In 1973, Opelz et al. provided initial evidence for ABT-related immunomodulation [14, 15]. Since then, though there are various potentially confounding factors to consider [17–19], many studies have reported the harmful effects of ABT on the prognosis after cancer surgery [13, 16, 20, 21]. Likewise, past reports have shown the negative effects of ABT on the long-term postoperative outcomes of PDAC patients [13, 20–24]. We also previously revealed that intraoperative ABT was strongly associated with poor prognosis in patients who underwent resection with curative intent for resectable PDAC [25]. Thus, we need to establish alternate strategies to ABT to improve the prognosis of PDAC patients further.

If we can predict massive IBL before surgery, it is possible to avoid ABT using various creative alternatives such as preoperative autologous blood storage and intraoperative acute normovolemic hemodilution. However, to date, it has not been possible to predict the occurrence of massive IBL beforehand. An accurate and robust prediction model would ultimately contribute to a better prognosis in PDAC patients. Therefore, in this study, we designed a prediction model for massive IBL in pancreatic cancer surgery. Here, we have successfully developed a user-friendly decision tree that predicts massive IBL in surgery for patients with resectable PDAC.

Materials and methods

Patients and study design

This single-center, retrospective, observational study was approved by the institutional ethics committee (reference no. 2020–202). This study was registered at the Japan Registry of Clinical Trials (https://jrct.niph.go.jp/, jRCT1020210001). Informed consent was obtained in the form of opt-out on our website (https://www.med.hirosaki-u.ac.jp/hospital/outline/resarch/resarch.html). This study was designed and carried out in accordance with the Declaration of Helsinki. Data has been reported in line with STROCSS 2019 criteria [26].

A total of 175 consecutive patients undergoing pancreatic surgery, with curative intent, for resectable PDAC at our facility between January 2007 and October 2020 were screened for study inclusion. Resectability status was made based on National Comprehensive Cancer Network guidelines. All patients had a confirmed pathologic diagnosis. In this study, we excluded the following cases: patients who had received neoadjuvant chemotherapy, anyone with remnant pancreatic cancer, or those with other synchronous malignancies.

Perioperative variable selection

Patient data were extracted from the medical records at our facilities. A total of 34 perioperative variables were selected from patient records, categorized into five groups: 1) patient demographics (n = 4), 2) comorbidities (n = 8), 3) laboratory values (n = 14), 4) tumor factors (n = 5), and 5) operative factors (n = 2).

Surgical procedures and operative management

We selected the type of pancreatic resection based on tumor location. Open pancreatoduodenectomy (PD) with lymph node dissections was usually performed on cases of pancreatic head cancer. In cases of pancreatic body and tail cancer, open or minimally invasive distal pancreatectomy (DP) was performed with lymph node dissections. If we detected a swelling paraaortic lymph node, we generally performed paraaortic lymph node sampling during PD; whereas sampling was not routinely performed during DP. We performed a fresh frozen section analysis to confirm if the pancreatic cut-end margin was clear of residual cancer. If residual cancer was present at the pancreatic cut end margin, we cut the pancreas further to reach negative margin status. If necessary, to achieve curative resection, we performed a total pancreatectomy (TP) with lymph node dissections.

Definition of massive IBL

In this study, we defined massive IBL as more than 20% of the estimated circulating blood volume (CBV), based on the model of Lundsgaard-Hansen [27]. We estimated the CBV using the following formula; CBV (mL) = 70 x body weight (kg). The IBL was calculated based on the in/out balance of the operative field. At our institution, any fluid loss from the abdominal cavity including ascites, bile, and lymphatics is considered to be intraoperative bleeding.

Statistical analyses

Continuous variables were expressed as medians (ranges) and analyzed using nonparametric methods for non-normally distributed data (Mann–Whitney U-test). Categorical variables were reported as numbers (percentages) and analyzed using the chi-squared test or Fisher’s exact test, as appropriate. Variables with a significant relationship to massive IBL in univariate analysis were used in a binary logistic regression model. Before inputting variables, we performed the Spearman correlation analysis and confirmed that there was no strong correlation (r >0.80) between the independent variables. Recurrence free survival (RFS) and Disease specific survival (DSS) were calculated using the Kaplan–Meier method, and differences in the survival rates between the massive IBL and non-massive IBL groups were compared using the log-rank test. RFS was defined as the time from the operation to the date of disease recurrence. DSS was defined as the time from the operation to the time of death due to PDAC, or the last follow-up time. This study was planned with a maximum follow-up period of five years. A difference was considered to be significant for values of P < 0.05. The statistical analyses were performed using IBM SPSS Statistics for Windows, Version 26.0 (IBM Corp, Armonk, NY, USA).

Decision tree analysis

We built a tree to predict occurrence of massive IBL using classification and regression trees (CART) analysis. Enrolled patients were divided into training and testing data sets, with a ratio of about 3:1. The training data included the patients who underwent pancreatic surgery between January 2007 and June 2018. The testing data included patients who had surgery between July 2018 and October 2020. The training set was used for generating the model. Each parameter was determined by performing a grid search for those with maximum accuracy. The development environment used for decision tree analysis was Python 3.6, implemented with scikit–learn 0.20 [28]. The developed software searched the training database for the factor that most effectively predicted massive IBL occurrence and its cut-off value. In brief, the decision tree was built using the following process: 1) identification of the single variable that, when used to split the dataset into two groups (“left and right children nodes”), best-minimized impurity of massive IBL occurrence in each node, according to the Gini impurity index; 2) repetition of the splitting process within each child node leading to leaf nodes where no additional splitting achieved further reductions in node impurity. In addition, a restriction was imposed on the tree construction such that nodes resulting from any given split needed to have at least five patients. We set a maximum tree depth of six to avoid overfitting. Nodes in binary recursive partitioning trees predict massive IBL occurrence categorically but, by evaluating node impurity, also offer associated probabilities. Finally, a massive IBL risk prediction model was created based on this analysis. Furthermore, the suitability and reproducibility of the model were validated using the testing data sets.

Results

Patient characteristics from the training and testing data sets

The clinical characteristics of the 175 enrolled patients are shown in Table 1.

Table 1. Patient characteristics in data sets.

	All cases (n = 175)	Training data (n = 128)	Testing data (n = 47)
Gender, male, n	91 (52.0)	65 (50.8)	26 (55.3)
Age, year	70 (43–87)	70 (50–85)	72 (43–87)
Body weight, kg	55.9 (34.0–85.0)	56.0 (34.0–85.0)	55.8 (37.0–77.4)
Body mass index, kg/m²	22.0 (14.1–36.3)	22.3 (14.1–36.3)	21.8 (17.4–32.3)
Comorbidities
Diabetes mellitus, n	68 (38.9)	43 (33.6)	25 (53.2)
Cancer history, n	35 (20.0)	21 (16.4)	14 (29.8)
Hypertension, n	70 (40.0)	45 (35.2)	25 (53.2)
Heart disease, n	20 (11.4)	14 (10.9)	6 (12.8)
Cerebrovascular disease, n	9 (5.1)	5 (3.9)	4 (8.5)
Hepatitis, n	20 (11.4)	15 (11.7)	5 (10.6)
Obstructive jaundice, n	78 (44.6)	60 (46.9)	18 (38.3)
Biliary drainage, n	63 (36.0)	44 (34.4)	19 (40.4)
Laboratory values
WBC, /μL	5520 (2230–11020)	5165 (2230–11020)	5640 (3390–10430)
Hemoglobin, g/dL	12.7 (7.2–16.5)	12.7 (7.2–16.3)	12.7 (8.8–16.5)
Hematocrit, %	37.3 (22.8–46.1)	37.2 (22.8–46.1)	37.6 (25.3–45.9)
Platelets, ×10³/μL	221 (64–539)	222 (64–513)	214 (118–539)
CRP, mg/dL	0.15 (0.01–9.59)	0.17 (0.01–9.59)	0.12 (0.02–5.14)
Albumin, g/dL	3.9 (2.0–5.7)	3.9 (2.0–5.7)	3.9 (2.7–4.7)
Total protein, g/dL	7.0 (4.9–8.9)	6.8 (4.9–8.9)	7.2 (5.9–8.0)
Creatinine, mg/dL	0.67 (0.40–2.02)	0.64 (0.40–1.43)	0.72 (0.46–2.02)
AST, U/L	28 (11–406)	29 (11–406)	26 (14–220)
ALT, U/L	31 (9–627)	35 (9–627)	27 (10–175)
GTP, U/L	51 (9–2579)	65 (9–1720)	38 (9–2579)
Total bilirubin, mg/dL	0.7 (0.2–32.7)	0.8 (0.2–32.7)	0.6 (0.2–4.6)
Amylase, U/L	74 (17–737)	74 (17–737)	75 (25–447)
CA19-9, U/mL	87 (1–9675)	71 (1–9675)	152 (4–2114)
CEA, ng/mL	2.7 (0.5–274)	2.7 (0.5–37.0)	3.2 (0.7–274)
Tumor factors
Tumor size
TS1	19 (10.9)	15 (11.7)	4 (8.5)
TS2	98 (56.0)	76 (59.4)	22 (46.8)
TS3	44 (14.1)	29 (22.7)	15 (31.9)
TS4	14 (8.0)	8 (6.3)	6 (12.8)
UICC 8^th edition
T category, n
T1	18 (10.3)	16 (12.5)	2 (4.3)
T2	85 (48.6)	79 (61.7)	6 (12.8)
T3	72 (41.1)	33 (25.8)	39 (83.0)
T4	0	0	0
N category, n
N0	74 (42.3)	49 (38.3)	25 (53.2)
N1	64 (36.6)	49 (38.3)	15 (31.9)
N2	37 (21.1)	30 (23.4)	7 (14.9)
M category, n
M0	162 (92.6)	117 (91.4)	45 (95.7)
M1^†	13 (6.9)	11 (8.6)	2 (4.3)
UICC Stage, n
IA	14 (8.0)	12 (9.4)	2 (4.3)
IB	29 (16.6)	24 (18.8)	5 (10.6)
IIA	30 (17.1)	12 (9.4)	18 (38.3)
IIB	60 (34.3)	45 (35.2)	15 (31.9)
III	29 (16.6)	24 (18.8)	5 (10.6)
IV	13 (7.4)	11 (8.6)	2 (4.3)
Operative factors
Surgical procedure, n
Pancreaticoduodenectomy	106 (60.6)	83 (64.8)	23 (48.9)
Distal pancreatectomy	59 (33.7)	40 (31.3)	19 (40.4)
Total pancreatectomy	10 (5.7)	5 (3.9)	5 (10.6)
Portal vein resection, n	28 (16.0)	19 (14.8)	9 (19.1)
Minimally invasive surgery, n	7 (4.0)	3 (2.3)	4 (8.5)

Open in a new tab

ALT, alanine aminotransferase; AST, aspartate aminotransferase; CA19-9, carbohydrate antigen 19–9; CEA, carcinoembryonic antigen; CRP, C-reactive protein; GTP, glutamyl transpeptidase; TS, tumor size; UICC, Union for International Cancer Control; WBC, white blood cell;

^†: All of the patients were diagnosed with M1 due to positive lymph nodes other than the regional lymph nodes.

Of the 175 patients, 128 were used for the training data, and data sets from 47 patients (26.9%) were used as the testing data. Information on IBL is presented in Table 2. Of the 175 patients, 88 patients (50.3%) were included in the massive IBL group.

Table 2. Information of IBL.

	All cases (n = 175)	Training data (n = 128)	Testing data (n = 47)
IBL, mL	750 (50–5600)	765 (90–3915)	650 (50–5600)
IBL > 20% in CBV, n	88 (50.3)	68 (53.1)	20 (42.6)
IBL > 1000mL, n	60 (34.3)	46 (35.9)	14 (29.8)
ABT, n	35 (20.0)	24 (18.8)	11 (23.4)

Open in a new tab

ABT, allogeneic red blood cell transfusion; CBV, circulating blood volume; IBL, intraoperative blood loss.

Comparison of the perioperative characteristics of the massive IBL and non-massive IBL groups

The massive IBL group demonstrated higher levels on liver function tests such as aspartate aminotransferase (AST), alanine aminotransferase (ALT), glutamyl transpeptidase (GTP), and serum total bilirubin (Table 3). This is assumed to have been caused by obstructive jaundice. There were no significant differences in the comorbidities between the groups. Although the tumor related factors were almost similar among groups, the massive IBL group had higher incidences of lymphatic metastasis (P = 0.046). Massive IBL was significantly associated with PD (78.4 vs. 42.5%, P < 0.001) and portal vein resection (25.0 vs. 6.9%, P = 0.001).

Table 3. Comparison of the perioperative characteristics of massive IBL and non-massive IBL groups.

	All cases (n = 175)	non-massive IBL (n = 87)	massive IBL (n = 88)	P value	Logistic regression
	All cases (n = 175)	non-massive IBL (n = 87)	massive IBL (n = 88)	P value	Odds Ratio	95% CI	P Value
Gender, male, n	91 (52.0)	40 (46.0)	51 (58.0)	0.113
Age, year	70 (43–87)	71 (52–85)	69 (43–87)	0.018	0.957	0.910–1.006	0.083
Body weight, kg	55.9 (34.0–85.0)	55.9 (34.0–82.5)	55.9 (34.7–85.0)	0.512
Body mass index, kg/m²	22.0 (14.1–36.3)	22.2 (17.1–33.3)	22.0 (14.1–36.3)	0.952
Comorbidities
Diabetes mellitus, n	68 (38.9)	30 (34.5)	38 (43.2)	0.238
Cancer history, n	35 (20.0)	21 (24.1)	14 (15.9)	0.174
Hypertension, n	70 (40.0)	34 (39.1)	36 (40.9)	0.805
Heart disease, n	20 (11.4)	10 (11.5)	10 (11.4)	0.978
Cerebrovascular disease, n	9 (5.1)	3 (3.4)	6 (6.8)	0.254
Hepatitis, n	20 (11.4)	9 (10.3)	11 (12.5)	0.654
Obstructive jaundice, n	78 (44.6)	26 (29.9)	52 (59.1)	< 0.001	0.603	0.090–4.041	0.602
Biliary drainage, n	63 (36.0)	21 (24.1)	42 (47.7)	0.001	1.267	0.229–7.009	0.786
Laboratory values
WBC, /μL	5520 (2230–11020)	5160 (2230–9980)	5335 (2410–11020)	0.227
Hemoglobin, g/dL	12.7 (7.2–16.5)	12.7 (7.2–15.9)	12.7 (8.8–16.5)	0.829
Hematocrit, %	37.3 (22.8–46.1)	37.4 (22.8–46.1)	37.1 (26.7–45.8)	0.793
Platelets, ×10³/μL	221 (64–539)	214 (96–539)	223 (64–513)	0.430
CRP, mg/dL	0.15 (0.01–9.59)	0.11 (0.02–9.59)	0.23 (0.01–6.50)	0.057
Albumin, g/dL	3.9 (2.0–5.7)	4.0 (2.5–5.7)	3.9 (2.0–4.9)	0.005	0.457	0.198–1.054	0.066
Total protein, g/dL	7.0 (4.9–8.9)	7.1 (5.4–8.9)	6.9 (4.9–8.1)	0.324
Creatinine, mg/dL	0.67 (0.40–2.02)	0.67 (0.43–2.02)	0.67 (0.40–1.69)	0.970
AST, U/L	28 (11–406)	24 (14–287)	34 (11–406)	0.001	^‡
ALT, U/L	31 (9–627)	23 (9–361)	45 (9–627)	< 0.001	1.007	1.001–1.014	0.028
GTP, U/L	51 (9–2579)	30 (9–1422)	113 (11–2579)	< 0.001	0.999	0.998–1.001	0.219
Total bilirubin, mg/dL	0.7 (0.2–32.7)	0.6 (0.2–32.7)	0.9 (0.3–24.1)	0.015	0.971	0.869–1.085	0.971
Amylase, U/L	74 (17–737)	71 (17–446)	81 (25–737)	0.197
CA19-9, U/mL	87 (1–9675)	62 (1–3199)	113 (1–9675)	0.248
CEA, ng/mL	2.7 (0.5–274)	2.7 (0.6–274)	3.0 (0.5–23.9)	0.272
Tumor factors
Tumor size				0.799
TS1	19 (10.9)	11 (12.6)	8 (9.1)
TS2	98 (56.0)	47 (54.0)	51 (58.0)
TS3	44 (14.1)	23 (26.4)	21 (23.9)
TS4	14 (8.0)	6 (6.9)	8 (9.1)
UICC 8^th edition
T category, n				0.602
T1	18 (10.3)	10 (11.5)	8 (9.1)
T2	85 (48.6)	39 (44.8)	46 (52.3)
T3	72 (41.1)	38 (43.7)	34 (38.6)
T4	0	0	0
N category, n				0.046
N0	74 (42.3)	44 (50.6)	30 (34.1)
N1	64 (36.6)	30 (34.5)	34 (38.6)		1.065	0.467–2.426	0.881
N2	37 (21.1)	13 (14.9)	24 (27.3)		1.508	0.570–3.986	0.408
M category, n				0.399
M0	162 (92.6)	82 (94.3)	80 (90.9)
M1^†	13 (6.9)	5 (5.7)	8 (9.1)
UICC Stage, n				0.212
IA	14 (8.0)	9 (10.3)	5 (5.7)
IB	29 (16.6)	18 (20.7)	11 (12.5)
IIA	30 (17.1)	17 (19.5)	13 (14.8)
IIB	60 (34.3)	28 (32.2)	32 (36.4)
III	29 (16.6)	10 (11.5)	19 (21.6)
IV	13 (7.4)	5 (5.7)	8 (9.1)
Operative factors
Surgical procedure, n				< 0.001
Pancreaticoduodenectomy	106 (60.6)	37 (42.5)	69 (78.4)
Distal pancreatectomy	59 (33.7)	47 (54.0)	12 (13.6)		0.244	0.089–0.672	0.006
Total pancreatectomy	10 (5.7)	3 (3.4)	7 (8.0)		1.991	0.378–10.482	0.416
Portal vein resection, n	28 (16.0)	6 (6.9)	22 (25.0)	0.001	2.366	0.816–6.864	0.113

Open in a new tab

ALT, alanine aminotransferase; AST, aspartate aminotransferase; CA19-9, carbohydrate antigen 19–9; CEA, carcinoembryonic antigen; CI, confidence interval; CRP, C-reactive protein; GTP, glutamyl transpeptidase; IBL, intraoperative blood loss; TS, tumor size; UICC, Union for International Cancer Control; WBC, white blood cell;

^†: All of the patients were diagnosed with M1 due to positive lymph nodes other than the regional lymph nodes.

^‡: Excluded due to multicollinearity with ALT.

Comparison of the postoperative outcomes of the massive IBL and non-massive IBL groups

Of the 88 patients with massive IBL, 33 (37.5%) received ABT (Table 4). The massive IBL group was associated with a higher frequency of postoperative complications (Clavien-Dindo grade ≥ 3, P = 0.001), especially in terms of the rate of pancreatic fistulas (with an International Study Group for Pancreatic Surgery (ISGPF) grade ≥ B) (20.5% vs. 6.9%, P = 0.009). Moreover, the IBL groups exhibited longer periods with regard to postoperative hospital stays (P < 0.001).

Table 4. Comparison of the operative outcomes of the massive IBL and non-massive IBL groups.

	All cases (n = 175)	non-massive IBL (n = 87)	massive IBL (n = 88)	P value
ABT, n	35 (20.0)	2 (2.3)	33 (37.5)	< 0.001
Postoperative complications (Clavien-dindo classification grade ≥ 3), n	28 (16.0)	6 (6.9)	22 (25.0)	0.001
Pancreatic fistula (ISGPF grade ≥ B), n	24 (13.7)	6 (6.9)	18 (20.5)	0.009
Delayed gastric emptying (ISGPS grade ≥ B), n	18 (10.3)	7 (8.0)	11 (12.5)	0.332
Postoperative hospital stay, days	18 (6–73)	16 (6–73)	23 (9–64)	< 0.001

Open in a new tab

ABT, allogeneic red blood cell transfusion; IBL, intraoperative blood loss; ISGPF, the International Study Group of Pancreatic Fistula; ISGPS, the International Study Group of Pancreatic Surgery.

The RFS time was significantly shorter in the massive IBL group than in the non-massive IBL group (median survival time (MST), 12.4 vs. 14.5 months, P = 0.013). Likewise, the DSS was shorter in the massive IBL group (MST, 28.6 vs. 40.0 months, P = 0.1124) (Fig 1).

Binary logistic regression analysis

To predict the occurrence of massive IBL, we performed a binary logistic regression analysis. We set the occurrence of massive IBL as the dependent variable. Significant predictor variables linked with massive IBL, which were found through a univariate analysis (P<0.05), as listed in Table 3, were entered into a binary logistic regression analysis. Before inputting predictor variables, we performed the Spearman correlation analysis and confirmed that there was no strong correlation (r >0.80) between the independent variables. As a result, we found a strong correlation between AST and ALT (r >0.90, p <0.001). Thus, we selected ALT based on the p value in a univariate analysis. There were no outliers whose predicted values exceeded ± 2SD in the measured values.

Binary logistic regression indicated that ALT and surgical procedure (DP) were significant predictors of massive IBL occurrence (Chi-Square = 48.977, df = 12, and p<0.001). All twelve predictors explained 32.5% of the variability of massive IBL occurrence. The results of Hosmer and Lemeshow was p = 0.347. ALT and surgical procedure (DP) were significant at the 5% level (ALT Wald = 4.829, p = 0.028; DP Wald = 7.454, p = 0.006). The odds ratio for ALT was 1.007 (95% confidence interval (CI): 1.001–1.014) and for DP was 0.244 (95% CI: 0.089–0.672). The model correctly predicted 65.5% of cases without massive IBL and 75.0% of cases with massive IBL, giving an overall correct prediction rate of 70.3%.

Decision tree analysis

Decision tree analysis was carried out on the training data set using 34 variables (Fig 2). The analysis automatically selected 14 predictive variables. The best predictor in the root node was the surgical procedure. Surgical procedure (including PD or not) was selected as the variable for the initial split. Among non-PD patients, the surgical procedure DP or TP was further identified as the variable of the second split. Among the patients with TP, creatinine was identified as the variable of the third split, with an optimal cut-off value of ≤ 0.705 mg/dL. In this node, all patients under 0.705 mg/dL experienced massive IBL.

The outcome of patients with DP was split by GTP levels, with an optimal cut-off value of ≤ 98.952 U/L. In this node, all patients over 98.952 U/L experienced massive IBL. The outcome of other patients with DP was determined by an additional predictor such as creatinine, carbohydrate antigen 19–9 (CA19-9), total bilirubin, ALT or hematocrit.

Among the patients who underwent PD, diabetes mellitus (DM) was selected as the variable of the second split. Of the 21 patients with DM, the rate of massive IBL occurrence was 85.7%. The outcome for non-DM patients undergoing PD was determined by an additional predictor such as ALT, total protein, carcinoembryonic antigen (CEA), or age.

With all the variables in the model, the decision tree achieved an accuracy of 80.5% (sensitivity of 98.5% and specificity of 60.0%) for the training data set. In the testing data set, the decision tree achieved an accuracy of 80.9%, sensitivity of 100.0%, and specificity of 66.7%.

Discussion

We defined the variables that could identify individuals at a risk for massive IBL in surgery for patients with resectable PDAC. Furthermore, we developed a decision tree to predict massive IBL.

The negative impact of IBL on outcomes after pancreatic surgery has long been suspected [29–34]; however, there have been few reports demonstrating risk factors for IBL [32, 33]. Rystedt et al. retrospectively analyzed 1864 patients who had undergone a PD in the Swedish National Pancreatic and Periampullary Cancer Registry. The national study on resectable periampullary tumors shows that the preoperative independent risk factors associated with major IBL (≥1000 mL) were male sex, body mass index ≥25 kg/m², preoperative biliary drainage, C-reactive protein ≥12 mg/L, and neo-adjuvant chemotherapy treatment [32]. Seykora et al. conducted a multi-institutional retrospective study and precisely evaluated 5323 PD patients who had been treated for either benign or malignant disease by 62 surgeons from 17 institutions [33]. They demonstrated that factors significantly associated with increased IBL (>1300 mL) were trans-anastomotic stent placement, neoadjuvant chemotherapy, pancreaticogastrostomy reconstruction, multiorgan or vascular resection, and elevated operative time (>435 min). Furthermore, they showed that female sex, small duct (≤2 mm), soft gland, minimally invasive approach, pylorus preservation, biological sealant use, and institutional volume (≥67/year) were associated with decreased IBL (<300 mL). Those large cohort studies, which provided novel and significant insight to us, were analyzed using multivariable logistic regression modeling to identify the independent risk factors for massive IBL. This method has been traditionally performed in clinical studies, but there have been certain limitations, such as selecting the variables, confounding factors, and multicollinearity, as shown in this study. To resolve these problems, we attempted to make a prediction model using a decision tree analysis. This study is the first report describing a decision tree used to predict massive IBL in pancreatic surgery for resectable PDAC. The innovative value of this study is less about the excellent accuracy of the decision tree model, but more about demonstrating the potential of a novel approach for this type of prediction.

The decision tree is a machine-learning model. It comprises decision rules based on optimal feature cutoff values that recursively split independent variables into different groups and predict an outcome hierarchically [35]. The advantages of decision tree algorithms are that they are logic-based, easily interpretable, and straightforward [36]. Moreover, this machine learning method can handle both continuous and categorical variables, which suit a clinical study that includes mixed variables.

In establishing this decision tree model, surgical procedure was the first node in predicting massive IBL. Then, factors related to liver function tests, such as GTP and ALT, were usually identified as the split variable. Tumor markers, such as CA19-9 and CEA, were also identified as the split variable. These would be easily acceptable to surgeons based on their long experience.

Our model identified that hepatobiliary enzymes were risk factors for massive IBL. One of the possible explanations is that the elevation of hepatobiliary enzymes is caused by cholangitis due to bile duct obstruction. Generally, inflammation can induce neovascularization during the healing process. In the animal cholangitis model, microvessels were richly developed around the dilated bile duct [37]. It was speculated that vascular endothelial growth factor (VEGF) plays a central role in this neovascularization. Ren et al. demonstrated that overexpression of VEGF was more prominent not only in the surrounding microvessels but also in bile duct epithelium with inflammation [37]. Unfortunately, before surgery, predicting the degree of VEGF and neovascularization around the bile duct is extremely hard. Thus, it is better for us to consider patients with elevated hepatobiliary enzyme, even after biliary drainage, as at risk for massive IBL.

In this study, 88 of the 175 patients (50.3%) were included in the massive IBL group. The factors which may have led to a relatively high proportion of massive IBL are as follows. First, we defined massive IBL as more than 20% of the estimated circulating blood volume, based on the model of Lundsgaard-Hansen [27]. This definition of massive IBL is stricter than that of previous studies [32, 33]. If we define massive IBL as bleeding of over 1000 ml, 60 patients (34.3%) would be included in the massive IBL group. Second, at our institution, any fluid loss from the abdominal cavity including ascites, bile, and lymphatics is considered to be intraoperative bleeding. Thus, only 20% of the patients required intraoperative allogeneic RBC transfusion, which is a similar rate to that of previous reports. Third, this study included only a small number of minimally invasive surgery cases. Finally, at our institution, approximately 20 different surgeons operated during the study period. Previous studies reported that surgeon volume was an important determinant of IBL [38, 39]. In short, surgeons with more experience are more likely to reduce IBL compared with their less-experienced peers. Ideally, all surgery should be performed by the most experienced surgeons. However, it is sometimes difficult to achieve this in real clinical situations. We believe that our study should be useful, especially to less-experienced surgeons and their patients.

The present study, using a decision tree, has several limitations. First, this is a retrospective single-institution cohort study. In addition, the patient population was small. If we had access to additional training data, we could achieve even higher prediction accuracy. Furthermore, we could use other machine learning methods such as some sort of neural network. Actually, we attempted the use of a neural net work and achieved an accuracy of 95.3% for the same training data set. However, the accuracy of the testing data set dropped to 54.1%. In contrast to the neural network, a decision tree visualizes a flowchart that allows appropriate treatment options for each patient depending on modifiable conditions based on that patient. Another important limitation is that the accuracy of the established model is not high enough. Thus, it would be more beneficial to focus the tree on partial data, not the entirety, and interpret them locally. To establish clinical applications, sufficient training and testing data sets are fundamental requirements for decision trees as well as neural networks. A new approach using machine learning methods that could take advantage of huge database such as national or regional data sets would be attractive for both clinicians treating PDAC and their patients.

Conclusions

The present study, using a decision tree, has provided a new potential approach to predict massive IBL in surgery for resectable PDAC patients. To establish a more accurate prediction model for clinical application, conducting a study using a huge data set is a hope for the future.

Supporting information

S1 File. Our study’s minimal data set.

(TXT)

Click here for additional data file.^{(25.1KB, txt)}

S2 File. Source code.

(PY)

Click here for additional data file.^{(6.5KB, py)}

S3 File

(DOCX)

Click here for additional data file.^{(45.4KB, docx)}

Acknowledgments

We sincerely thank Shari Joy Berman for professionally editing the English draft of this manuscript.

Data Availability

All relevant data are within the manuscript and its Supporting information files.

Funding Statement

The authors received no specific funding for this work.

References

1.Bray F, Ferlay J, Soerjomataram I, Siegel RL, Torre LA, Jemal A. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: a cancer journal for clinicians. 2018;68(6):394–424. Epub 2018/09/13. doi: 10.3322/caac.21492 . [DOI] [PubMed] [Google Scholar]
2.Kleeff J, Korc M, Apte M, La Vecchia C, Johnson CD, Biankin AV, et al. Pancreatic cancer. Nat Rev Dis Primers. 2016;2:16022. Epub 2016/05/10. doi: 10.1038/nrdp.2016.22 . [DOI] [PubMed] [Google Scholar]
3.Doi R, Imamura M, Hosotani R, Imaizumi T, Hatori T, Takasaki K, et al. Surgery versus radiochemotherapy for resectable locally invasive pancreatic cancer: final results of a randomized multi-institutional trial. Surg Today. 2008;38(11):1021–8. Epub 2008/10/30. doi: 10.1007/s00595-007-3745-8 . [DOI] [PubMed] [Google Scholar]
4.Bilimoria KY, Bentrem DJ, Ko CY, Stewart AK, Winchester DP, Talamonti MS. National failure to operate on early stage pancreatic cancer. Ann Surg. 2007;246(2):173–80. Epub 2007/08/02. doi: 10.1097/SLA.0b013e3180691579 . [DOI] [PMC free article] [PubMed] [Google Scholar]
5.Ahola R, Sand J, Laukkarinen J. Pancreatic resections are not only safest but also most cost-effective when performed in a high-volume centre: A Finnish register study. Pancreatology. 2019;19(5):769–74. Epub 2019/06/27. doi: 10.1016/j.pan.2019.06.007 . [DOI] [PubMed] [Google Scholar]
6.Amini N, Spolverato G, Gupta R, Margonis GA, Kim Y, Wagner D, et al. Impact Total Psoas Volume on Short- and Long-Term Outcomes in Patients Undergoing Curative Resection for Pancreatic Adenocarcinoma: a New Tool to Assess Sarcopenia. J Gastrointest Surg. 2015;19(9):1593–602. doi: 10.1007/s11605-015-2835-y . [DOI] [PMC free article] [PubMed] [Google Scholar]
7.de Wilde RF, Besselink MG, van der Tweel I, de Hingh IH, van Eijck CH, Dejong CH, et al. Impact of nationwide centralization of pancreaticoduodenectomy on hospital mortality. Br J Surg. 2012;99(3):404–10. Epub 2012/01/13. doi: 10.1002/bjs.8664 . [DOI] [PubMed] [Google Scholar]
8.Gooiker GA, Lemmens VE, Besselink MG, Busch OR, Bonsing BA, Molenaar IQ, et al. Impact of centralization of pancreatic cancer surgery on resection rates and survival. Br J Surg. 2014;101(8):1000–5. Epub 2014/05/23. doi: 10.1002/bjs.9468 . [DOI] [PubMed] [Google Scholar]
9.Onete VG, Besselink MG, Salsbach CM, Van Eijck CH, Busch OR, Gouma DJ, et al. Impact of centralization of pancreatoduodenectomy on reported radical resections rates in a nationwide pathology database. HPB (Oxford). 2015;17(8):736–42. Epub 2015/06/04. doi: 10.1111/hpb.12425 . [DOI] [PMC free article] [PubMed] [Google Scholar]
10.Hachey K, Morgan R, Rosen A, Rao SR, McAneny D, Tseng J, et al. Quality Comes with the (Anatomic) Territory: Evaluating the Impact of Surgeon Operative Mix on Patient Outcomes After Pancreaticoduodenectomy. Ann Surg Oncol. 2018;25(13):3795–803. Epub 2018/09/07. doi: 10.1245/s10434-018-6732-y . [DOI] [PubMed] [Google Scholar]
11.Snyder RA, Prakash LR, Nogueras-Gonzalez GM, Kim MP, Aloia TA, Vauthey JN, et al. Perioperative blood transfusions for vein resection during pancreaticoduodenectomy for pancreatic adenocarcinoma: Identification of clinical targets for optimization. HPB (Oxford). 2019;21(7):841–8. Epub 2018/12/07. doi: 10.1016/j.hpb.2018.10.018 . [DOI] [PubMed] [Google Scholar]
12.Ecker BL, Simmons KD, Zaheer S, Poe SL, Bartlett EK, Drebin JA, et al. Blood Transfusion in Major Abdominal Surgery for Malignant Tumors: A Trend Analysis Using the National Surgical Quality Improvement Program. JAMA surgery. 2016;151(6):518–25. Epub 2016/01/15. doi: 10.1001/jamasurg.2015.5094 . [DOI] [PubMed] [Google Scholar]
13.Kneuertz PJ, Patel SH, Chu CK, Maithel SK, Sarmiento JM, Delman KA, et al. Effects of perioperative red blood cell transfusion on disease recurrence and survival after pancreaticoduodenectomy for ductal adenocarcinoma. Ann Surg Oncol. 2011;18(5):1327–34. Epub 2011/03/04. doi: 10.1245/s10434-010-1476-3 . [DOI] [PubMed] [Google Scholar]
14.Opelz G, Sengar DP, Mickey MR, Terasaki PI. Effect of blood transfusions on subsequent kidney transplants. Transplant Proc. 1973;5(1):253–9. Epub 1973/03/01. . [PubMed] [Google Scholar]
15.Opelz G, Terasaki PI. Improvement of kidney-graft survival with increased numbers of blood transfusions. N Engl J Med. 1978;299(15):799–803. Epub 1978/10/12. doi: 10.1056/NEJM197810122991503 . [DOI] [PubMed] [Google Scholar]
16.Remy KE, Hall MW, Cholette J, Juffermans NP, Nicol K, Doctor A, et al. Mechanisms of red blood cell transfusion-related immunomodulation. Transfusion. 2018;58(3):804–15. Epub 2018/02/01. doi: 10.1111/trf.14488 . [DOI] [PMC free article] [PubMed] [Google Scholar]
17.Nakanishi K, Kanda M, Kodera Y. Long-lasting discussion: Adverse effects of intraoperative blood loss and allogeneic transfusion on prognosis of patients with gastric cancer. World J Gastroenterol. 2019;25(22):2743–51. Epub 2019/06/27. doi: 10.3748/wjg.v25.i22.2743 . [DOI] [PMC free article] [PubMed] [Google Scholar]
18.Peng P, Hyder O, Firoozmand A, Kneuertz P, Schulick RD, Huang D, et al. Impact of sarcopenia on outcomes following resection of pancreatic adenocarcinoma. J Gastrointest Surg. 2012;16(8):1478–86. doi: 10.1007/s11605-012-1923-5 . [DOI] [PMC free article] [PubMed] [Google Scholar]
19.Lee B, Han HS, Yoon YS, Cho JY, Lee JS. Impact of Preoperative Malnutrition, based on Albumin Level and Body Mass Index, on Operative Outcomes in Patients with Pancreatic Head Cancer. J Hepatobiliary Pancreat Sci. 2020. Epub 2020/11/01. doi: 10.1002/jhbp.858 . [DOI] [PubMed] [Google Scholar]
20.Mavros MN, Xu L, Maqsood H, Gani F, Ejaz A, Spolverato G, et al. Perioperative Blood Transfusion and the Prognosis of Pancreatic Cancer Surgery: Systematic Review and Meta-analysis. Ann Surg Oncol. 2015;22(13):4382–91. Epub 2015/08/22. doi: 10.1245/s10434-015-4823-6 . [DOI] [PubMed] [Google Scholar]
21.Sutton JM, Kooby DA, Wilson GC, Squires MH 3rd, Hanseman DJ, Maithel SK, et al. Perioperative blood transfusion is associated with decreased survival in patients undergoing pancreaticoduodenectomy for pancreatic adenocarcinoma: a multi-institutional study. J Gastrointest Surg. 2014;18(9):1575–87. Epub 2014/06/20. doi: 10.1007/s11605-014-2567-4 . [DOI] [PubMed] [Google Scholar]
22.Abe T, Amano H, Hanada K, Minami T, Yonehara S, Hattori M, et al. Perioperative Red Blood Cell Transfusion Is Associated with Poor Long-term Survival in Pancreatic Adenocarcinoma. Anticancer Res. 2017;37(10):5863–70. Epub 2017/10/07. doi: 10.21873/anticanres.12031 . [DOI] [PubMed] [Google Scholar]
23.Kim SY, Choi M, Hwang HK, Rho SY, Lee WJ, Kang CM. Intraoperative Transfusion is Independently Associated with a Worse Prognosis in Resected Pancreatic Cancer-a Retrospective Cohort Analysis. Journal of clinical medicine. 2020;9(3). Epub 2020/03/08. doi: 10.3390/jcm9030689 . [DOI] [PMC free article] [PubMed] [Google Scholar]
24.Hwang HK, Jung MJ, Lee SH, Kang CM, Lee WJ. Adverse oncologic effects of intraoperative transfusion during pancreatectomy for left-sided pancreatic cancer: the need for strict transfusion policy. J Hepatobiliary Pancreat Sci. 2016;23(8):497–507. Epub 2016/06/15. doi: 10.1002/jhbp.368 . [DOI] [PubMed] [Google Scholar]
25.Kanda T, Wakiya T, Ishido K, Kimura N, Nagase H, Kubota S, et al. Intraoperative Allogeneic Red Blood Cell Transfusion Negatively Influences Prognosis After Radical Surgery for Pancreatic Cancer: A Propensity Score Matching Analysis. Pancreas. 2021. in press. [DOI] [PubMed] [Google Scholar]
26.Agha R, Abdall-Razak A, Crossley E, Dowlut N, Iosifidis C, Mathew G. STROCSS 2019 Guideline: Strengthening the reporting of cohort studies in surgery. Int J Surg. 2019;72:156–65. Epub 2019/11/11. doi: 10.1016/j.ijsu.2019.11.002 . [DOI] [PubMed] [Google Scholar]
27.Lundsgaard-Hansen P. Component therapy of surgical hemorrhage: red cell concentrates, colloids and crystalloids. Bibliotheca haematologica. 1980;(46):147–69. Epub 1980/01/01. doi: 10.1159/000430555 . [DOI] [PubMed] [Google Scholar]
28.Pedregosa F. Scikit-learn: Machine learning in python. J Machine Learn Res. 2011;12:2825–30. [Google Scholar]
29.Braga M, Capretti G, Pecorelli N, Balzano G, Doglioni C, Ariotti R, et al. A prognostic score to predict major complications after pancreaticoduodenectomy. Ann Surg. 2011;254(5):702–7; discussion 7–8. doi: 10.1097/SLA.0b013e31823598fb . [DOI] [PubMed] [Google Scholar]
30.Callery MP, Pratt WB, Kent TS, Chaikof EL, Vollmer CM. A prospectively validated clinical risk score accurately predicts pancreatic fistula after pancreatoduodenectomy. J Am Coll Surg. 2013;216(1):1–14. doi: 10.1016/j.jamcollsurg.2012.09.002 . [DOI] [PubMed] [Google Scholar]
31.Kazanjian KK, Hines OJ, Duffy JP, Yoon DY, Cortina G, Reber HA. Improved Survival Following Pancreaticoduodenectomy to Treat Adenocarcinoma of the Pancreas: The Influence of Operative Blood Loss. Archives of Surgery. 2008;143(12):1166–71. doi: 10.1001/archsurg.143.12.1166 [DOI] [PubMed] [Google Scholar]
32.Rystedt J, Tingstedt B, Ansorge C, Nilsson J, Andersson B. Major intraoperative bleeding during pancreatoduodenectomy—preoperative biliary drainage is the only modifiable risk factor. HPB (Oxford). 2019;21(3):268–74. Epub 2018/09/02. doi: 10.1016/j.hpb.2018.07.024 . [DOI] [PubMed] [Google Scholar]
33.Seykora TF, Ecker BL, McMillan MT, Maggino L, Beane JD, Fong ZV, et al. The Beneficial Effects of Minimizing Blood Loss in Pancreatoduodenectomy. Ann Surg. 2019;270(1):147–57. Epub 2018/03/01. doi: 10.1097/SLA.0000000000002714 . [DOI] [PubMed] [Google Scholar]
34.Trudeau MT, Casciani F, Maggino L, Seykora TF, Asbun HJ, Ball CG, et al. The Influence of Intraoperative Blood Loss on Fistula Development Following Pancreatoduodenectomy. Annals of Surgery. 9000; Publish Ahead of Print. doi: 10.1097/sla.0000000000004549 00000658-900000000-94033. [DOI] [PubMed] [Google Scholar]
35.Wu X, Kumar V, Ross Quinlan J, Ghosh J, Yang Q, Motoda H, et al. Top 10 algorithms in data mining. Knowledge and Information Systems. 2008;14(1):1–37. doi: 10.1007/s10115-007-0114-2 [DOI] [Google Scholar]
36.Lakshmi BN, Indumathi TS, Ravi N. A Study on C.5 Decision Tree Classification Algorithm for Risk Predictions During Pregnancy. Procedia Technology. 2016;24:1542–9. doi: 10.1016/j.protcy.2016.05.128 [DOI] [Google Scholar]
37.Ren XS, Sato Y, Harada K, Sasaki M, Yoneda N, Lin ZH, et al. Biliary infection may exacerbate biliary cystogenesis through the induction of VEGF in cholangiocytes of the polycystic kidney (PCK) rat. Am J Pathol. 2011;179(6):2845–54. Epub 2011/10/22. doi: 10.1016/j.ajpath.2011.08.028 . [DOI] [PMC free article] [PubMed] [Google Scholar]
38.Casciani F, Trudeau MT, Asbun HJ, Ball CG, Bassi C, Behrman SW, et al. Surgeon experience contributes to improved outcomes in pancreatoduodenectomies at high risk for fistula development. Surgery. 2021;169(4):708–20. Epub 2021/01/03. doi: 10.1016/j.surg.2020.11.022 . [DOI] [PubMed] [Google Scholar]
39.Schmidt CM, Turrini O, Parikh P, House MG, Zyromski NJ, Nakeeb A, et al. Effect of Hospital Volume, Surgeon Experience, and Surgeon Volume on Patient Outcomes After Pancreaticoduodenectomy: A Single-Institution Experience. Archives of Surgery. 2010;145(7):634–40. doi: 10.1001/archsurg.2010.118 [DOI] [PubMed] [Google Scholar]

PLoS One. doi: 10.1371/journal.pone.0259682.r001

Decision Letter 0

Ulrich Wellner

31 Aug 2021

PONE-D-21-25114

Prediction of massive bleeding in pancreatic surgery based on preoperative patient characteristics using a decision tree

PLOS ONE

Dear Dr. Wakiya,

Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process.

Please submit your revised manuscript by Oct 15 2021 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.

Please include the following items when submitting your revised manuscript:

A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'.
A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'.
An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'.

If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter.

If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: http://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols. Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols.

We look forward to receiving your revised manuscript.

Kind regards,

Ulrich Wellner, Prof Dr. med.

Academic Editor

PLOS ONE

Journal Requirements:

When submitting your revision, we need you to address these additional requirements.

1. Please ensure that your manuscript meets PLOS ONE's style requirements, including those for file naming. The PLOS ONE style templates can be found at

https://journals.plos.org/plosone/s/file?id=wjVg/PLOSOne_formatting_sample_main_body.pdf and

https://journals.plos.org/plosone/s/file?id=ba62/PLOSOne_formatting_sample_title_authors_affiliations.pdf

2. We suggest you thoroughly copyedit your manuscript for language usage, spelling, and grammar. If you do not know anyone who can help you do this, you may wish to consider employing a professional scientific editing service.

Whilst you may use any professional scientific editing service of your choice, PLOS has partnered with both American Journal Experts (AJE) and Editage to provide discounted services to PLOS authors. Both organizations have experience helping authors meet PLOS guidelines and can provide language editing, translation, manuscript formatting, and figure formatting to ensure your manuscript meets our submission guidelines. To take advantage of our partnership with AJE, visit the AJE website (http://learn.aje.com/plos/) for a 15% discount off AJE services. To take advantage of our partnership with Editage, visit the Editage website (www.editage.com) and enter referral code PLOSEDIT for a 15% discount off Editage services. If the PLOS editorial team finds any language issues in text that either AJE or Editage has edited, the service provider will re-edit the text for free.

Upon resubmission, please provide the following:

The name of the colleague or the details of the professional service that edited your manuscript

A copy of your manuscript showing your changes by either highlighting them or using track changes (uploaded as a *supporting information* file)

A clean copy of the edited manuscript (uploaded as the new *manuscript* file)

3. Please note that PLOS ONE has specific guidelines on code sharing for submissions in which author-generated code underpins the findings in the manuscript. In these cases, all author-generated code must be made available without restrictions upon publication of the work. Please review our guidelines at https://journals.plos.org/plosone/s/materials-and-software-sharing#loc-sharing-code and ensure that your code is shared in a way that follows best practice and facilitates reproducibility and reuse.

In addition, please provide further details of the generation of the decision tree and the CART algorithm in particular.

4. In your Data Availability statement, you have not specified where the minimal data set underlying the results described in your manuscript can be found. PLOS defines a study's minimal data set as the underlying data used to reach the conclusions drawn in the manuscript and any additional data required to replicate the reported study findings in their entirety. All PLOS journals require that the minimal data set be made fully available. For more information about our data policy, please see http://journals.plos.org/plosone/s/data-availability.

"Upon re-submitting your revised manuscript, please upload your study’s minimal underlying data set as either Supporting Information files or to a stable, public repository and include the relevant URLs, DOIs, or accession numbers within your revised cover letter. For a list of acceptable repositories, please see http://journals.plos.org/plosone/s/data-availability#loc-recommended-repositories. Any potentially identifying patient information must be fully anonymized.

Important: If there are ethical or legal restrictions to sharing your data publicly, please explain these restrictions in detail. Please see our guidelines for more information on what we consider unacceptable restrictions to publicly sharing data: http://journals.plos.org/plosone/s/data-availability#loc-unacceptable-data-access-restrictions. Note that it is not acceptable for the authors to be the sole named individuals responsible for ensuring data access.

We will update your Data Availability statement to reflect the information you provide in your cover letter.

[Note: HTML markup is below. Please do not edit.]

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. Is the manuscript technically sound, and do the data support the conclusions?

The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented.

Reviewer #1: Yes

Reviewer #2: No

Reviewer #3: Yes

Reviewer #4: No

Reviewer #5: Partly

Reviewer #6: Partly

**********

2. Has the statistical analysis been performed appropriately and rigorously?

Reviewer #1: Yes

Reviewer #2: No

Reviewer #3: Yes

Reviewer #4: Yes

Reviewer #5: N/A

Reviewer #6: No

**********

3. Have the authors made all data underlying the findings in their manuscript fully available?

The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.

Reviewer #1: No

Reviewer #2: No

Reviewer #3: Yes

Reviewer #4: Yes

Reviewer #5: Yes

Reviewer #6: Yes

**********

4. Is the manuscript presented in an intelligible fashion and written in standard English?

PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.

Reviewer #1: Yes

Reviewer #2: No

Reviewer #3: Yes

Reviewer #4: Yes

Reviewer #5: No

Reviewer #6: Yes

**********

5. Review Comments to the Author

Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)

Reviewer #1: The authors present a retrospective study examining the predictor of massive bleeding (IBL) in pancreatic surgery based on preoperative patient characteristics using a binary logistic regression analysis and a decision tree model. The best predictor was the surgical procedure using both analysis. Using the decision tree model of the training data set, the outcome of patients with DP was secondarily split by glutamyl transpeptidase. Among patients who underwent PD, DM was selected as the variable in the second split. Accuracy between the training and testing data sets was comparable (80.5% and 80.9%).

Major

1) Authors indicated that many studies have reported the harmful effects of allogeneic blood transfusion (ABT) on the prognosis after cancer surgery. Therefore, in order to prove this hypothesis, the authors should show prognosis with or without ABT.

2) In order to clarify the relevance of ABT and IBL, it is better to show the frequency of ABT by IBL.

3) Several papers describe the relationship between intraoperative bleeding and postoperative complications. The association between IBL and postoperative complications should be clarified.

4) The authors need to discuss that hepatobiliary enzymes and liver function are risk factors for IBL.

Minor

1) Figure was unclear. Would you make the figure easier to see?

Reviewer #2: 1. recent publications such as J Clin Med. 2020 Mar 4;9(3):689, J Hepatobiliary Pancreat Sci. 2016 Aug;23(8):497-507 need to be considered for citation.

2. "Of the 175 136 patients, 88 patients (50.3%) were included in the massive IBL group". It seems to be too high proportion of massive IBL. Is it so common?

3. Regarding decision tree.

1) It seems to be too complicated to apply in real clinical practice.

2) What is the rationale of decision criteria, such as DM, Cr, HT, CEA...

3) It should be presented as a form of calculator.

Reviewer #3: If intraoperative bleeding can be well predicted before surgery, the situation of these patients will be effectively improved. This study has very important clinical implications. However, if this predictive model can effectively reduce and avoid intraoperative bleeding in these patients, it would be better.

Reviewer #4: 1.Of the 175 patients, 128 were used for the training data, and data sets from 47 patients (26.9%) were used as the testing data. Based on what criteria or methodology is the grouping?

2.Massive intraoperative bleeding is a serious complication of pancreatic surgery, which is more common in the injury of the portal vein, superior mesenteric vein and superior mesenteric artery. A skilled surgeon can significantly reduce intraoperative bleeding in pancreatic surgery, so massive intraoperative bleeding is not common in large-volume centers. In your data, 88 of 175 patients experienced massive intraoperative bleeding (Of the 175 patients, 88 patients (50.3%) were included in the massive IBL group). I'm curious if all these surgeries were performed by a single surgeon? What are the causes of massive intraoperative bleeding? What were the perioperative outcomes for these patients?

Reviewer #5: Taiichi and colleagues build a model for massive IBL prediction in pancreatic surgery for PDAC by a decision tree

algorithm.The manuscript is partly technically sound and builds on current data. I have few comments here:

1.Language should be revised (seeking professional assistance is suggested).

2. The sample size described in current cohort is too small to make a strong conclusion.

3. The authors should show how the massive IBL in pancreatic surgery influence the short-term and long-term outcomes for PDAC in current data.

4.The authors defined massive IBL as more than 20% of the estimated circulating blood volume. I have two questions: First, Is there any referrence for this definition or the author made it by themselves? Second, How the authours calculate the IBL volume? Besides, of the 175 patients, 88 patients (50.3%) were included in the massive IBL group, which is a relatively high proportion.

5.The result showed that distal pancreactomy (DP) were significant predictors of massive IBL occurrence and surgical procedure was the first node in predicting massive IBL. The authours should make further discussion. Tumors located in body or tail more easily lead to left-side portal hypertension which is casued by splenic vein obstruction. Therefore, these patients are more likely to have massive IBL occurrence.

6. Alanine aminotransferase or liver function was one of significant predictors of massive IBL,however, the authors should show the coagulation function in the data and analyze its impact on IBL.

7.The discussionare too short and the limitation section are too long.

Reviewer #6: This is an impressive paper on the development of a decision tree based prediction model for intraoperative blood loss.

While the concept of the paper is interesting, I think there are a few critical problems with it. Needless to say, the performance of surgical procedures has improved over time. I think the main reasons for this are energy devices, laparoscopic surgery, and robotics. The amount of blood loss depends on what kind of energy device is used. Also, a major advantage of minimally invasive surgery is the reduction of blood loss, and I don't know if it is arbitrary that this paper does not take this into account, but it greatly reduces the value of this study. More to the point, the fact that about half of the patients in the authors' cohort had massive bleeding is problematic for the quality of surgery today. Unfortunately, I don't think that a study done with such surgical quality can provide universal facts.

**********

6. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy.

Reviewer #1: No

Reviewer #2: No

Reviewer #3: No

Reviewer #4: No

Reviewer #5: No

Reviewer #6: No

[NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.]

While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/. PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email PLOS at figures@plos.org. Please note that Supporting Information files do not need this step.

PLoS One. 2021 Nov 9;16(11):e0259682. doi: 10.1371/journal.pone.0259682.r002

Author response to Decision Letter 0

11 Oct 2021

Ulrich Wellner

Academic Editor

PLOS ONE

Dear Professor Wellner,

On behalf of my co-authors, I would like to express my gratitude to the Editor and the Reviewers for their kind attention to our initial manuscript, PONE-D-21-25114, entitled " Prediction of massive bleeding in pancreatic surgery based on preoperative patient characteristics using a decision tree" We greatly appreciate the Editor and Reviewers’ thoughtful and constructive comments, for they provided important scientific suggestions. These suggestions helped us enormously in preparing our new manuscript.

After careful consideration of the comments for PONE-D-21-25114, we have prepared a new manuscript in which we have improved the quality of the rendering of our data with additional results that reinforce our original findings, and we have extensively revised our manuscript. Our responses to each of the Editor and Reviewers’ comments are delineated below.

------------------------------------------------------

Revision notes

Responses to the Journal Requirements

We greatly appreciate your thoughtful and constructive comments. These suggestions have helped us enormously in preparing our new manuscript. We have revised our manuscript based on your comments (specific details below).

Journal Requirement 1:

Please ensure that your manuscript meets PLOS ONE's style requirements, including those for file naming.

Our Response to Journal Requirement 1:

We have revised the manuscript based on PLOS ONE's style requirements, including those for file naming.

Journal Requirement 2:

We suggest you thoroughly copyedit your manuscript for language usage, spelling, and grammar. If you do not know anyone who can help you do this, you may wish to consider employing a professional scientific editing service.

Upon resubmission, please provide the following:

The name of the colleague or the details of the professional service that edited your manuscript

Our Response to Journal Requirement 2:

We have made revisions based on this Comment. This revised manuscript was edited by Shari Joy Berman, who is a professional English editor.

Journal Requirement 3:

Please note that PLOS ONE has specific guidelines on code sharing for submissions in which author-generated code underpins the findings in the manuscript. In these cases, all author-generated code must be made available without restrictions upon publication of the work.

In addition, please provide further details of the generation of the decision tree and the CART algorithm in particular.

Our Response to Journal Requirement 3:

As per this requirement, we have uploaded the code we generated as Supporting Information. The development environment used for decision tree analysis was Python 3.6, implemented with scikit–learn 0.20 (Diverted from Scikit-learn: Machine Learning in Python, Pedregosa et al., JMLR 12, pp. 2825-2830, 2011.)

Journal Requirement 4:

In your Data Availability statement, you have not specified where the minimal data set underlying the results described in your manuscript can be found. PLOS defines a study's minimal data set as the underlying data used to reach the conclusions drawn in the manuscript and any additional data required to replicate the reported study findings in their entirety. All PLOS journals require that the minimal data set be made fully available.

Our Response to Journal Requirement 4:

As suggested we have included the minimal data set in Supporting Information.

Responses to the comments from the Reviewer 1

We greatly appreciate your thoughtful and constructive comments. These suggestions helped us enormously in preparing our new manuscript. We have revised our manuscript based on your comments (explained below).

Reviewer 1, Comment 1:

Authors indicated that many studies have reported the harmful effects of allogeneic blood transfusion (ABT) on the prognosis after cancer surgery. Therefore, in order to prove this hypothesis, the authors should show prognosis with or without ABT.

Our Response to Reviewer 1, Comment 1:

Our latest article, which was accepted on September 14, 2021, reported that intraoperative ABT was strongly associated with poor prognosis in patients who underwent resection with curative intent for resectable PDAC. The RFS time was significantly shorter in the ABT group than in the non-ABT group (median survival time (MST), 10.6 vs. 14.2 months, P = 0.002). Likewise, the DSS was significantly shorter in the ABT group (MST, 20.5 vs. 38.3 months, P = 0.014). Results remained similar after propensity score matching analysis when confounding factors, other than ABT, were excluded. On page 4, lines 40-42, in the Introduction section, the following sentence was added to the text: “We also previously revealed that intraoperative ABT was strongly associated with poor prognosis in patients who underwent resection with curative intent for resectable PDAC (Kanda T, Wakiya T, Ishido K, Kimura N, Nagase H, Kubota S, et al. Intraoperative Allogeneic Red Blood Cell Transfusion Negatively Influences Prognosis After Radical Surgery for Pancreatic Cancer: A Propensity Score Matching Analysis. Pancreas. 2021. in press.).” We greatly appreciate the constructive comment and have added this to strengthen our introduction.

Reviewer 1, Comment 2:

In order to clarify the relevance of ABT and IBL, it is better to show the frequency of ABT by IBL.

Our Response to Reviewer 1, Comment 2:

Of the 88 patients with massive IBL, 33 (37.5%) received ABT. We have created a new table giving the information on ABT. On page 15, in the Results section, we have added Table 4. We greatly appreciate this constructive comment.

Reviewer 1, Comment 3:

Several papers describe the relationship between intraoperative bleeding and postoperative complications. The association between IBL and postoperative complications should be clarified.

Our Response to Reviewer 1, Comment 3:

On page 16, lines 176-181, in the Results, the following sentence was added to the text: “The massive IBL group was associated with a higher frequency of postoperative complications (Clavien-Dindo grade ≥ 3, P = 0.001), especially in terms of the rate of pancreatic fistulas (with an International Study Group for Pancreatic Surgery (ISGPF) grade ≥ B) (20.5% vs. 6.9%, P = 0.009). Moreover, the IBL groups exhibited longer periods with regard to postoperative hospital stays (P < 0.001).” We greatly appreciate this constructive comment.

Reviewer 1, Comment 4:

The authors need to discuss that hepatobiliary enzymes and liver function are risk factors for IBL.

Our Response to Reviewer 1, Comment 4:

On page 21, lines 285-295, in the Discussion section, the following sentence was added to the text: “Our model identified that hepatobiliary enzymes were risk factors for massive IBL. One of the possible explanations is that the elevation of hepatobiliary enzymes is caused by cholangitis due to bile duct obstruction. Generally, inflammation can induce neovascularization during the healing process. In the animal cholangitis model, microvessels were richly developed around the dilated bile duct [37]. It was speculated that vascular endothelial growth factor (VEGF) plays a central role in this neovascularization. Ren et al. demonstrated that overexpression of VEGF was more prominent not only in the surrounding microvessels but also in bile duct epithelium with inflammation [37]. Unfortunately, before surgery, predicting the degree of VEGF and neovascularization around the bile duct is extremely hard. Thus, it is better for us to consider patients with elevated hepatobiliary enzyme, even after biliary drainage, as at risk for massive IBL.”

Reviewer 1, Comment 5:

Figure was unclear. Would you make the figure easier to see?

Our Response to Reviewer 1, Comment 5:

We have made the figure easier to read.

Responses to the comments from the Reviewer 2

Reviewer 2, Comment 1:

recent publications such as J Clin Med. 2020 Mar 4;9(3):689, J Hepatobiliary Pancreat Sci. 2016 Aug;23(8):497-507 need to be considered for citation.

Our Response to Reviewer 2, Comment 1:

We have added the suggested citation based on this comment.

Reviewer 2, Comment 2:

"Of the 175 136 patients, 88 patients (50.3%) were included in the massive IBL group". It seems to be too high proportion of massive IBL. Is it so common?

Our Response to Reviewer 2, Comment 2:

In this study, we defined massive IBL as more than 20% of the estimated circulating blood volume, based on the model of Lundsgaard-Hansen (Lundsgaard-Hansen P. Component therapy of surgical hemorrhage: red cell concentrates, colloids and crystalloids. Bibliotheca haematologica. 1980(46):147-69.) This definition of massive IBL may be stricter than previous studies. If we define massive IBL as bleeding of over 1000 ml, 60 patients (34.3%) would be included the massive IBL group.

Furthermore, at our institution, any fluid loss from the abdominal cavity including ascites, bile, and lymphatics is considered intraoperative bleeding. This policy may have led to a relatively high proportion of massive IBL. Thus, only 20% of the patients required intraoperative allogeneic RBC transfusion, which is a similar rate to those in previous reports.

At our institution, though there was a difference in the number, approximately 20 different surgeons operated during the study period. These factors also may have led to a relatively high proportion of massive IBL. Previous studies reported that surgeon volume was an important determinant of IBL. In short, surgeons with more experience are more likely to reduce IBL compared with their less-experienced peers. (Ref.1: Casciani F, Trudeau MT, Asbun HJ, Ball CG, Bassi C, Behrman SW, et al. Surgeon experience contributes to improved outcomes in pancreatoduodenectomies at high risk for fistula development. Surgery. 2021;169(4):708-20. Ref-2: Schmidt CM, Turrini O, Parikh P, House MG, Zyromski NJ, Nakeeb A, et al. Effect of Hospital Volume, Surgeon Experience, and Surgeon Volume on Patient Outcomes After Pancreaticoduodenectomy: A Single-Institution Experience. Archives of Surgery. 2010;145(7):634-40.) Taken together, our study must be useful especially for less-experienced surgeons and their patients.

We have added an explanation of the high proportion of massive IBL and the implications of this study to the Discussion section.

Reviewer 2, Comment 3:

Regarding decision tree.

1) It seems to be too complicated to apply in real clinical practice.

2) What is the rationale of decision criteria, such as DM, Cr, HT, CEA...

3) It should be presented as a form of calculator.

Our Response to Reviewer 2, Comment 3:

1) We have made the figures easier to read.

2) As we described in the Materials and Methods section, each parameter was determined by performing a grid search in Scikit-learn for those with maximum accuracy. A grid search is a tuning technique that attempts to compute the optimum values of hyperparameters. It is an exhaustive search that is performed on the specific parameter values of a model. As a result, criteria such as DM, Cr, HT, CEA...were selected without being arbitrary.

3) We totally agree with you. A calculator format would be more convenient. One of the advantages of our decision tree model is that the outputs are easy to read and interpret without requiring statistical knowledge or special equipment such as computers. Ideally, in the future, we would also like to provide this in the form of app. However, at the moment, although we consider the possibility, it was too complex for us to construct the development environment of an app. Instead, we decided to share the code so that anyone could use it.

Responses to the comments from the Reviewer 3

Reviewer 3, Comment 1:

If intraoperative bleeding can be well predicted before surgery, the situation of these patients will be effectively improved. This study has very important clinical implications. However, if this predictive model can effectively reduce and avoid intraoperative bleeding in these patients, it would be better.

Our Response to Reviewer 3, Comment 1:

We totally agree with you. Our prediction model can contribute to reduce and avoid allogenic blood transfusion with various creative alternatives such as preoperative autologous blood storage. However, as you said, our ideal goal is to reduce and avoid intraoperative bleeding. Thus, based upon our decision tree, we need to conduct prospective trials attempting to intervene using modifiable factors, such as DM and cholangitis, in the future. We greatly appreciate your thoughtful and constructive comments. These comments will help us enormously in conducting our future projects.

Responses to the comments from the Reviewer 4

We greatly appreciate your thoughtful and constructive comments. These suggestions helped us enormously in preparing the new manuscript. We have revised our manuscript based on your comments (explained below).

Reviewer 4, Comment 1:

Of the 175 patients, 128 were used for the training data, and data sets from 47 patients (26.9%) were used as the testing data. Based on what criteria or methodology is the grouping?

Our Response to Reviewer 4, Comment 1:

On page 8, lines 114-116, in the Materials and Methods section, the following sentences were added to the text: “The training data included the patients who underwent pancreatic surgery between January 2007 and June 2018. The testing data included patients who had surgery between July 2018 and October 2020.” We aimed to divide the patients into training and testing data sets, with a ratio of about 3:1.

Reviewer 4, Comment 2:

Massive intraoperative bleeding is a serious complication of pancreatic surgery, which is more common in the injury of the portal vein, superior mesenteric vein and superior mesenteric artery. A skilled surgeon can significantly reduce intraoperative bleeding in pancreatic surgery, so massive intraoperative bleeding is not common in large-volume centers. In your data, 88 of 175 patients experienced massive intraoperative bleeding (Of the 175 patients, 88 patients (50.3%) were included in the massive IBL group). I'm curious if all these surgeries were performed by a single surgeon? What are the causes of massive intraoperative bleeding? What were the perioperative outcomes for these patients?

Our Response to Reviewer 4, Comment 2:

We greatly appreciate this surgically professional comment. As you have said, massive intraoperative bleeding is more common in injuries to the major vessels such as PV, SMV, and SMA. In fact, the massive IBL group had portal vein resection performed more frequently. Furthermore, half of the massive IBL group received biliary drainage preoperatively, which is considered to be an independent predictor for major intraoperative bleeding (Reference: HPB (Oxford). 2019 Mar;21(3):268-274.). At our institution, though there was a difference in the number, approximately 20 different surgeons operated during the study period. These factors may have affected the massive IBL group.

The massive IBL group was associated with a higher frequency of postoperative complications (Clavien-Dindo grade ≥ 3, P = 0.001), especially in terms of the rate of pancreatic fistulas (with an International Study Group for Pancreatic Surgery (ISGPF) grade ≥ B) (20.5% vs. 6.9%, P = 0.009). Moreover, the IBL groups exhibited longer periods with regard to postoperative hospital stays (P < 0.001). The RFS time was significantly shorter in the massive IBL group than in the non-massive IBL group (median survival time (MST), 12.4 vs. 14.5 months, P = 0.013). Likewise, the DSS was shorter in the massive IBL group (MST, 28.6 vs. 40.0 months, P = 0.1124)

Based upon your comment, we added this information to the revised manuscript. We greatly appreciate this constructive feedback.

Responses to the comments from the Reviewer 5

Reviewer 5, Comment 1:

Language should be revised (seeking professional assistance is suggested).

Our Response to Reviewer 5, Comment 1:

This revised manuscript was edited by Shari Joy Berman, who is a professional English editor.

Reviewer 5, Comment 2:

The sample size described in current cohort is too small to make a strong conclusion.

Our Response to Reviewer 5, Comment 2:

We totally agree with you. The patient population was too small to come to a clear or definite conclusion. On the other hand, our study demonstrated better prediction accuracy than traditional methods such as binary logistic regression analysis. Though the sample size was small, our study actually showed the usefulness of a decision tree and the machine learning approach. This approach has extendibility and scalability in this clinical situation of reducing massive IBL in pancreatic surgery. Your comment has helped us in revising the manuscript to state the limitations of the small cohort clearly.

Reviewer 5, Comment 3:

The authors should show how the massive IBL in pancreatic surgery influence the short-term and long-term outcomes for PDAC in current data.

Our Response to Reviewer 5, Comment 3:

Regarding short-term outcome, the massive IBL group was associated with a higher frequency of postoperative complications (Clavien-Dindo grade ≥ 3, P = 0.001), especially in terms of the rate of pancreatic fistulas (with an International Study Group for Pancreatic Surgery (ISGPF) grade ≥ B) (20.5% vs. 6.9%, P = 0.009). Moreover, the IBL groups exhibited longer periods with regard to postoperative hospital stays (P < 0.001).

Regarding long-term outcome, the RFS time was significantly shorter in the massive IBL group than in the non-massive IBL group (median survival time (MST), 12.4 vs. 14.5 months, P = 0.013). Likewise, the DSS was shorter in the massive IBL group (MST, 28.6 vs. 40.0 months, P = 0.1124). Based upon your comment, we have added this information to the revised manuscript. We greatly appreciate this constructive comment.

Reviewer 5, Comment 4:

The authors defined massive IBL as more than 20% of the estimated circulating blood volume. I have two questions: First, Is there any referrence for this definition or the author made it by themselves? Second, How the authours calculate the IBL volume? Besides, of the 175 patients, 88 patients (50.3%) were included in the massive IBL group, which is a relatively high proportion.

Our Response to Reviewer 5, Comment 4:

First, we defined massive IBL as more than 20% of the estimated circulating blood volume, based on the model established by Lundsgaard-Hansen (Lundsgaard-Hansen P. Component therapy of surgical hemorrhage: red cell concentrates, colloids and crystalloids. Bibliotheca haematologica. 1980(46):147-69.) This definition of massive IBL may be stricter than other previous studies. If we define massive IBL as bleeding of over 1000 ml, 60 patients (34.3%) would be included in the massive IBL group.

Second, the IBL was calculated based on the “in/out” balance of the operative field. At our institution, any fluid loss from the abdominal cavity including ascites, bile, and lymphatics is considered to be intraoperative bleeding. This policy may have led to a relatively high proportion of massive IBL. Thus, only 20% of the patients required intraoperative allogeneic RBC transfusion, which is a similar rate to those in previous reports.

Furthermore, at our institution, though there was a difference in the number, approximately 20 different surgeons operated during the study period. These factors also may have led to a relatively high proportion of massive IBL. Previous studies reported that surgeon volume was an important determinant of IBL. In short, more experienced surgeons are more likely to achieve reduced IBL rates compared with their peers. (Ref.1: Casciani F, Trudeau MT, Asbun HJ, Ball CG, Bassi C, Behrman SW, et al. Surgeon experience contributes to improved outcomes in pancreatoduodenectomies at high risk for fistula development. Surgery. 2021;169(4):708-20. Ref-2: Schmidt CM, Turrini O, Parikh P, House MG, Zyromski NJ, Nakeeb A, et al. Effect of Hospital Volume, Surgeon Experience, and Surgeon Volume on Patient Outcomes After Pancreaticoduodenectomy: A Single-Institution Experience. Archives of Surgery. 2010;145(7):634-40.) Ideally, all surgery should be performed by the most experienced surgeons. However, it is sometimes difficult to achieve this in real clinical situations. We believe that our study should be useful, especially for less-experienced surgeons and their patients.

We have added an explanation of the high proportion of massive IBL and the implications of this study to the Discussion section.

Reviewer 5, Comment 5:

The result showed that distal pancreactomy (DP) were significant predictors of massive IBL occurrence and surgical procedure was the first node in predicting massive IBL. The authours should make further discussion. Tumors located in body or tail more easily lead to left-side portal hypertension which is casued by splenic vein obstruction. Therefore, these patients are more likely to have massive IBL occurrence.

Our Response to Reviewer 5, Comment 5:

We totally agree with your comments from the surgical perspective. As you have said, we sometimes operated on PDAC patients with left-side portal hypertension due to splenic vein obstruction. Our results demonstrated that when the surgical procedure (PD or not) was selected that created the initial split. Moreover, among non-PD cases, the surgical procedure (DP or TP) was identified as the second split. As a matter of fact, if anything, distal pancreatectomy was identified as not being among the significant predictors of massive IBL. We deeply apologize for confusing you about the first node. We have made the figures easier to read.

Reviewer 5, Comment 6:

Alanine aminotransferase or liver function was one of significant predictors of massive IBL,however, the authors should show the coagulation function in the data and analyze its impact on IBL.

Our Response to Reviewer 5, Comment 6:

We totally agree with you. Just as you mention, we have really wanted to analyze the impact of coagulation function on IBL. However, particularly with the earlier cases of the study period, we did not measure the coagulation function test routinely in PDAC patients. Thus, in this study, it was difficult to use the coagulation function for machine learning due to too many missing values.

Our model identified that hepatobiliary enzymes were one significant predictor of massive IBL. One of the possible explanations is that the elevation of hepatobiliary enzymes was caused by cholangitis due to bile duct obstruction. Generally, inflammation can induce neovascularization during the healing process. In the animal cholangitis model, microvessels were richly developed around the dilated bile duct (33). It was speculated that vascular endothelial growth factor (VEGF) plays a central role in this neovascularization. This report demonstrated that overexpression of VEGF was more prominent not only in the surrounding microvessels but also in bile duct epithelium with inflammation (33). Unfortunately, before surgery, predicting the degree of VEGF and neovascularization around the bile duct is extremely hard. Thus, it is better for us to consider patients with elevated hepatobiliary enzymes, even after biliary drainage, as at risk for massive IBL. We added this information to the revised manuscript. We greatly appreciate your thoughtful and constructive comments.

Reviewer 5, Comment 7:

The discussion are too short and the limitation section are too long.

Our Response to Reviewer 5, Comment 7:

We agree with your assessment. We have revised the Discussion section.

Responses to the comments from the Reviewer 6

Reviewer 6, Comment 1:

This is an impressive paper on the development of a decision tree based prediction model for intraoperative blood loss.

Our Response to Reviewer 6, Comment 1:

We greatly appreciate such professional comments from surgical perspective. As you have said, intraoperative blood loss has decreased by the progress of energy devices and minimally invasive surgery. We deeply apologize for confusing you about this point due to the lack of information we provided initially.

In this study period, we mainly used scissors and monopolar electrosurgery. At the last part of the study period, we occasionally used ultrasonic systems (Harmonic® scalpel) or electrothermal bipolar-activated devices (LigaSure™). Furthermore, we performed minimally invasive surgery only in 4% (7cases) of this study cohort. At the beginning of the use of minimally invasive surgery methods in our institution, we mostly performed minimally invasive surgery on patients with benign disease. After the learning curve of the approach expanded, we extended the indication to PDAC. That is why this study, based on when the surgeries were originally performed, included only a small number of minimally invasive cases.

We defined massive IBL as more than 20% of the estimated circulating blood volume, based on the model of Lundsgaard-Hansen (Lundsgaard-Hansen P. Component therapy of surgical hemorrhage: red cell concentrates, colloids and crystalloids. Bibliotheca haematologica. 1980(46):147-69.) This definition of massive IBL may be stricter than previous studies. If we were to define massive IBL as bleeding of over 1000 ml, 60 patients (34.3%) would be included in the massive IBL group.

Additionally, at our institution, any fluid loss from the abdominal cavity including ascites, bile, and lymphatics is considered to be intraoperative bleeding. This policy may have led to a relatively high proportion of massive IBL. Thus, only 20% of the patients required intraoperative allogeneic RBC transfusion, which is a similar rate to that of previous reports.

At our institution, though there was a difference in the number, approximately 20 different surgeons operated during the study period. This factor also may have led to a relatively high proportion of massive IBL. Previous studies reported that surgeon volume was an important determinant of IBL. In short, surgeons with more experience are more likely to reduce IBL compared with their less-experienced peers. (Ref.1: Casciani F, Trudeau MT, Asbun HJ, Ball CG, Bassi C, Behrman SW, et al. Surgeon experience contributes to improved outcomes in pancreatoduodenectomies at high risk for fistula development. Surgery. 2021;169(4):708-20. Ref-2: Schmidt CM, Turrini O, Parikh P, House MG, Zyromski NJ, Nakeeb A, et al. Effect of Hospital Volume, Surgeon Experience, and Surgeon Volume on Patient Outcomes After Pancreaticoduodenectomy: A Single-Institution Experience. Archives of Surgery. 2010;145(7):634-40.) Ideally, all surgery should be performed by the most experienced surgeons. However, it is sometimes difficult to achieve this in real clinical situations. We believe that our study should be useful, especially for less-experienced surgeons and their patients.

We have added an explanation of the high proportion of massive IBL and the implications of this study to the Discussion section.

We hope that you find our revised manuscript suitable for publication in PLOS ONE.

In closing, we would like to thank you once again for your reviews and suggestions, which have helped us improve the quality of our paper. We would greatly appreciate your kind consideration for our revised manuscript.

Sincerely yours,

Taiichi Wakiya, M.D., Ph.D.

Department of Gastroenterological Surgery

Hirosaki University Graduate School of Medicine

5, Zaifu-cho, Hirosaki, Aomori, 036-8562, Japan

Telephone: +81-172-395079, Fax: +81-172-395080

E-mail: wakiya1979@hirosaki-u.ac.jp

PLoS One. doi: 10.1371/journal.pone.0259682.r003

Decision Letter 1

Ulrich Wellner

25 Oct 2021

Prediction of massive bleeding in pancreatic surgery based on preoperative patient characteristics using a decision tree

PONE-D-21-25114R1

Dear Dr. Wakiya,

We’re pleased to inform you that your manuscript has been judged scientifically suitable for publication and will be formally accepted for publication once it meets all outstanding technical requirements.

Within one week, you’ll receive an e-mail detailing the required amendments. When these have been addressed, you’ll receive a formal acceptance letter and your manuscript will be scheduled for publication.

An invoice for payment will follow shortly after the formal acceptance. To ensure an efficient process, please log into Editorial Manager at http://www.editorialmanager.com/pone/, click the 'Update My Information' link at the top of the page, and double check that your user information is up-to-date. If you have any billing related questions, please contact our Author Billing department directly at authorbilling@plos.org.

If your institution or institutions have a press office, please notify them about your upcoming paper to help maximize its impact. If they’ll be preparing press materials, please inform our press team as soon as possible -- no later than 48 hours after receiving the formal acceptance. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org.

Kind regards,

Ulrich Wellner, Prof Dr. med.

Academic Editor

PLOS ONE

Additional Editor Comments (optional):

Reviewers' comments:

PLoS One. doi: 10.1371/journal.pone.0259682.r004

Acceptance letter

Ulrich Wellner

29 Oct 2021

PONE-D-21-25114R1

Prediction of massive bleeding in pancreatic surgery based on preoperative patient characteristics using a decision tree

Dear Dr. Wakiya:

I'm pleased to inform you that your manuscript has been deemed suitable for publication in PLOS ONE. Congratulations! Your manuscript is now with our production department.

If your institution or institutions have a press office, please let them know about your upcoming paper now to help maximize its impact. If they'll be preparing press materials, please inform our press team within the next 48 hours. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information please contact onepress@plos.org.

If we can help with anything else, please email us at plosone@plos.org.

Thank you for submitting your work to PLOS ONE and supporting open access.

Kind regards,

PLOS ONE Editorial Office Staff

on behalf of

Mr. Ulrich Wellner

Academic Editor

PLOS ONE

Associated Data

This section collects any data citations, data availability statements, or supplementary materials included in this article.

Supplementary Materials

S1 File. Our study’s minimal data set.

(TXT)

Click here for additional data file.^{(25.1KB, txt)}

S2 File. Source code.

(PY)

Click here for additional data file.^{(6.5KB, py)}

S3 File

(DOCX)

Click here for additional data file.^{(45.4KB, docx)}

Data Availability Statement

All relevant data are within the manuscript and its Supporting information files.

[pone.0259682.ref001] 1.Bray F, Ferlay J, Soerjomataram I, Siegel RL, Torre LA, Jemal A. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: a cancer journal for clinicians. 2018;68(6):394–424. Epub 2018/09/13. doi: 10.3322/caac.21492 . [DOI] [PubMed] [Google Scholar]

[pone.0259682.ref002] 2.Kleeff J, Korc M, Apte M, La Vecchia C, Johnson CD, Biankin AV, et al. Pancreatic cancer. Nat Rev Dis Primers. 2016;2:16022. Epub 2016/05/10. doi: 10.1038/nrdp.2016.22 . [DOI] [PubMed] [Google Scholar]

[pone.0259682.ref003] 3.Doi R, Imamura M, Hosotani R, Imaizumi T, Hatori T, Takasaki K, et al. Surgery versus radiochemotherapy for resectable locally invasive pancreatic cancer: final results of a randomized multi-institutional trial. Surg Today. 2008;38(11):1021–8. Epub 2008/10/30. doi: 10.1007/s00595-007-3745-8 . [DOI] [PubMed] [Google Scholar]

[pone.0259682.ref004] 4.Bilimoria KY, Bentrem DJ, Ko CY, Stewart AK, Winchester DP, Talamonti MS. National failure to operate on early stage pancreatic cancer. Ann Surg. 2007;246(2):173–80. Epub 2007/08/02. doi: 10.1097/SLA.0b013e3180691579 . [DOI] [PMC free article] [PubMed] [Google Scholar]

[pone.0259682.ref005] 5.Ahola R, Sand J, Laukkarinen J. Pancreatic resections are not only safest but also most cost-effective when performed in a high-volume centre: A Finnish register study. Pancreatology. 2019;19(5):769–74. Epub 2019/06/27. doi: 10.1016/j.pan.2019.06.007 . [DOI] [PubMed] [Google Scholar]

[pone.0259682.ref006] 6.Amini N, Spolverato G, Gupta R, Margonis GA, Kim Y, Wagner D, et al. Impact Total Psoas Volume on Short- and Long-Term Outcomes in Patients Undergoing Curative Resection for Pancreatic Adenocarcinoma: a New Tool to Assess Sarcopenia. J Gastrointest Surg. 2015;19(9):1593–602. doi: 10.1007/s11605-015-2835-y . [DOI] [PMC free article] [PubMed] [Google Scholar]

[pone.0259682.ref007] 7.de Wilde RF, Besselink MG, van der Tweel I, de Hingh IH, van Eijck CH, Dejong CH, et al. Impact of nationwide centralization of pancreaticoduodenectomy on hospital mortality. Br J Surg. 2012;99(3):404–10. Epub 2012/01/13. doi: 10.1002/bjs.8664 . [DOI] [PubMed] [Google Scholar]

[pone.0259682.ref008] 8.Gooiker GA, Lemmens VE, Besselink MG, Busch OR, Bonsing BA, Molenaar IQ, et al. Impact of centralization of pancreatic cancer surgery on resection rates and survival. Br J Surg. 2014;101(8):1000–5. Epub 2014/05/23. doi: 10.1002/bjs.9468 . [DOI] [PubMed] [Google Scholar]

[pone.0259682.ref009] 9.Onete VG, Besselink MG, Salsbach CM, Van Eijck CH, Busch OR, Gouma DJ, et al. Impact of centralization of pancreatoduodenectomy on reported radical resections rates in a nationwide pathology database. HPB (Oxford). 2015;17(8):736–42. Epub 2015/06/04. doi: 10.1111/hpb.12425 . [DOI] [PMC free article] [PubMed] [Google Scholar]

[pone.0259682.ref010] 10.Hachey K, Morgan R, Rosen A, Rao SR, McAneny D, Tseng J, et al. Quality Comes with the (Anatomic) Territory: Evaluating the Impact of Surgeon Operative Mix on Patient Outcomes After Pancreaticoduodenectomy. Ann Surg Oncol. 2018;25(13):3795–803. Epub 2018/09/07. doi: 10.1245/s10434-018-6732-y . [DOI] [PubMed] [Google Scholar]

[pone.0259682.ref011] 11.Snyder RA, Prakash LR, Nogueras-Gonzalez GM, Kim MP, Aloia TA, Vauthey JN, et al. Perioperative blood transfusions for vein resection during pancreaticoduodenectomy for pancreatic adenocarcinoma: Identification of clinical targets for optimization. HPB (Oxford). 2019;21(7):841–8. Epub 2018/12/07. doi: 10.1016/j.hpb.2018.10.018 . [DOI] [PubMed] [Google Scholar]

[pone.0259682.ref012] 12.Ecker BL, Simmons KD, Zaheer S, Poe SL, Bartlett EK, Drebin JA, et al. Blood Transfusion in Major Abdominal Surgery for Malignant Tumors: A Trend Analysis Using the National Surgical Quality Improvement Program. JAMA surgery. 2016;151(6):518–25. Epub 2016/01/15. doi: 10.1001/jamasurg.2015.5094 . [DOI] [PubMed] [Google Scholar]

[pone.0259682.ref013] 13.Kneuertz PJ, Patel SH, Chu CK, Maithel SK, Sarmiento JM, Delman KA, et al. Effects of perioperative red blood cell transfusion on disease recurrence and survival after pancreaticoduodenectomy for ductal adenocarcinoma. Ann Surg Oncol. 2011;18(5):1327–34. Epub 2011/03/04. doi: 10.1245/s10434-010-1476-3 . [DOI] [PubMed] [Google Scholar]

[pone.0259682.ref014] 14.Opelz G, Sengar DP, Mickey MR, Terasaki PI. Effect of blood transfusions on subsequent kidney transplants. Transplant Proc. 1973;5(1):253–9. Epub 1973/03/01. . [PubMed] [Google Scholar]

[pone.0259682.ref015] 15.Opelz G, Terasaki PI. Improvement of kidney-graft survival with increased numbers of blood transfusions. N Engl J Med. 1978;299(15):799–803. Epub 1978/10/12. doi: 10.1056/NEJM197810122991503 . [DOI] [PubMed] [Google Scholar]

[pone.0259682.ref016] 16.Remy KE, Hall MW, Cholette J, Juffermans NP, Nicol K, Doctor A, et al. Mechanisms of red blood cell transfusion-related immunomodulation. Transfusion. 2018;58(3):804–15. Epub 2018/02/01. doi: 10.1111/trf.14488 . [DOI] [PMC free article] [PubMed] [Google Scholar]

[pone.0259682.ref017] 17.Nakanishi K, Kanda M, Kodera Y. Long-lasting discussion: Adverse effects of intraoperative blood loss and allogeneic transfusion on prognosis of patients with gastric cancer. World J Gastroenterol. 2019;25(22):2743–51. Epub 2019/06/27. doi: 10.3748/wjg.v25.i22.2743 . [DOI] [PMC free article] [PubMed] [Google Scholar]

[pone.0259682.ref018] 18.Peng P, Hyder O, Firoozmand A, Kneuertz P, Schulick RD, Huang D, et al. Impact of sarcopenia on outcomes following resection of pancreatic adenocarcinoma. J Gastrointest Surg. 2012;16(8):1478–86. doi: 10.1007/s11605-012-1923-5 . [DOI] [PMC free article] [PubMed] [Google Scholar]

[pone.0259682.ref019] 19.Lee B, Han HS, Yoon YS, Cho JY, Lee JS. Impact of Preoperative Malnutrition, based on Albumin Level and Body Mass Index, on Operative Outcomes in Patients with Pancreatic Head Cancer. J Hepatobiliary Pancreat Sci. 2020. Epub 2020/11/01. doi: 10.1002/jhbp.858 . [DOI] [PubMed] [Google Scholar]

[pone.0259682.ref020] 20.Mavros MN, Xu L, Maqsood H, Gani F, Ejaz A, Spolverato G, et al. Perioperative Blood Transfusion and the Prognosis of Pancreatic Cancer Surgery: Systematic Review and Meta-analysis. Ann Surg Oncol. 2015;22(13):4382–91. Epub 2015/08/22. doi: 10.1245/s10434-015-4823-6 . [DOI] [PubMed] [Google Scholar]

[pone.0259682.ref021] 21.Sutton JM, Kooby DA, Wilson GC, Squires MH 3rd, Hanseman DJ, Maithel SK, et al. Perioperative blood transfusion is associated with decreased survival in patients undergoing pancreaticoduodenectomy for pancreatic adenocarcinoma: a multi-institutional study. J Gastrointest Surg. 2014;18(9):1575–87. Epub 2014/06/20. doi: 10.1007/s11605-014-2567-4 . [DOI] [PubMed] [Google Scholar]

[pone.0259682.ref022] 22.Abe T, Amano H, Hanada K, Minami T, Yonehara S, Hattori M, et al. Perioperative Red Blood Cell Transfusion Is Associated with Poor Long-term Survival in Pancreatic Adenocarcinoma. Anticancer Res. 2017;37(10):5863–70. Epub 2017/10/07. doi: 10.21873/anticanres.12031 . [DOI] [PubMed] [Google Scholar]

[pone.0259682.ref023] 23.Kim SY, Choi M, Hwang HK, Rho SY, Lee WJ, Kang CM. Intraoperative Transfusion is Independently Associated with a Worse Prognosis in Resected Pancreatic Cancer-a Retrospective Cohort Analysis. Journal of clinical medicine. 2020;9(3). Epub 2020/03/08. doi: 10.3390/jcm9030689 . [DOI] [PMC free article] [PubMed] [Google Scholar]

[pone.0259682.ref024] 24.Hwang HK, Jung MJ, Lee SH, Kang CM, Lee WJ. Adverse oncologic effects of intraoperative transfusion during pancreatectomy for left-sided pancreatic cancer: the need for strict transfusion policy. J Hepatobiliary Pancreat Sci. 2016;23(8):497–507. Epub 2016/06/15. doi: 10.1002/jhbp.368 . [DOI] [PubMed] [Google Scholar]

[pone.0259682.ref025] 25.Kanda T, Wakiya T, Ishido K, Kimura N, Nagase H, Kubota S, et al. Intraoperative Allogeneic Red Blood Cell Transfusion Negatively Influences Prognosis After Radical Surgery for Pancreatic Cancer: A Propensity Score Matching Analysis. Pancreas. 2021. in press. [DOI] [PubMed] [Google Scholar]

[pone.0259682.ref026] 26.Agha R, Abdall-Razak A, Crossley E, Dowlut N, Iosifidis C, Mathew G. STROCSS 2019 Guideline: Strengthening the reporting of cohort studies in surgery. Int J Surg. 2019;72:156–65. Epub 2019/11/11. doi: 10.1016/j.ijsu.2019.11.002 . [DOI] [PubMed] [Google Scholar]

[pone.0259682.ref027] 27.Lundsgaard-Hansen P. Component therapy of surgical hemorrhage: red cell concentrates, colloids and crystalloids. Bibliotheca haematologica. 1980;(46):147–69. Epub 1980/01/01. doi: 10.1159/000430555 . [DOI] [PubMed] [Google Scholar]

[pone.0259682.ref028] 28.Pedregosa F. Scikit-learn: Machine learning in python. J Machine Learn Res. 2011;12:2825–30. [Google Scholar]

[pone.0259682.ref029] 29.Braga M, Capretti G, Pecorelli N, Balzano G, Doglioni C, Ariotti R, et al. A prognostic score to predict major complications after pancreaticoduodenectomy. Ann Surg. 2011;254(5):702–7; discussion 7–8. doi: 10.1097/SLA.0b013e31823598fb . [DOI] [PubMed] [Google Scholar]

[pone.0259682.ref030] 30.Callery MP, Pratt WB, Kent TS, Chaikof EL, Vollmer CM. A prospectively validated clinical risk score accurately predicts pancreatic fistula after pancreatoduodenectomy. J Am Coll Surg. 2013;216(1):1–14. doi: 10.1016/j.jamcollsurg.2012.09.002 . [DOI] [PubMed] [Google Scholar]

[pone.0259682.ref031] 31.Kazanjian KK, Hines OJ, Duffy JP, Yoon DY, Cortina G, Reber HA. Improved Survival Following Pancreaticoduodenectomy to Treat Adenocarcinoma of the Pancreas: The Influence of Operative Blood Loss. Archives of Surgery. 2008;143(12):1166–71. doi: 10.1001/archsurg.143.12.1166 [DOI] [PubMed] [Google Scholar]

[pone.0259682.ref032] 32.Rystedt J, Tingstedt B, Ansorge C, Nilsson J, Andersson B. Major intraoperative bleeding during pancreatoduodenectomy—preoperative biliary drainage is the only modifiable risk factor. HPB (Oxford). 2019;21(3):268–74. Epub 2018/09/02. doi: 10.1016/j.hpb.2018.07.024 . [DOI] [PubMed] [Google Scholar]

[pone.0259682.ref033] 33.Seykora TF, Ecker BL, McMillan MT, Maggino L, Beane JD, Fong ZV, et al. The Beneficial Effects of Minimizing Blood Loss in Pancreatoduodenectomy. Ann Surg. 2019;270(1):147–57. Epub 2018/03/01. doi: 10.1097/SLA.0000000000002714 . [DOI] [PubMed] [Google Scholar]

[pone.0259682.ref034] 34.Trudeau MT, Casciani F, Maggino L, Seykora TF, Asbun HJ, Ball CG, et al. The Influence of Intraoperative Blood Loss on Fistula Development Following Pancreatoduodenectomy. Annals of Surgery. 9000; Publish Ahead of Print. doi: 10.1097/sla.0000000000004549 00000658-900000000-94033. [DOI] [PubMed] [Google Scholar]

[pone.0259682.ref035] 35.Wu X, Kumar V, Ross Quinlan J, Ghosh J, Yang Q, Motoda H, et al. Top 10 algorithms in data mining. Knowledge and Information Systems. 2008;14(1):1–37. doi: 10.1007/s10115-007-0114-2 [DOI] [Google Scholar]

[pone.0259682.ref036] 36.Lakshmi BN, Indumathi TS, Ravi N. A Study on C.5 Decision Tree Classification Algorithm for Risk Predictions During Pregnancy. Procedia Technology. 2016;24:1542–9. doi: 10.1016/j.protcy.2016.05.128 [DOI] [Google Scholar]

[pone.0259682.ref037] 37.Ren XS, Sato Y, Harada K, Sasaki M, Yoneda N, Lin ZH, et al. Biliary infection may exacerbate biliary cystogenesis through the induction of VEGF in cholangiocytes of the polycystic kidney (PCK) rat. Am J Pathol. 2011;179(6):2845–54. Epub 2011/10/22. doi: 10.1016/j.ajpath.2011.08.028 . [DOI] [PMC free article] [PubMed] [Google Scholar]

[pone.0259682.ref038] 38.Casciani F, Trudeau MT, Asbun HJ, Ball CG, Bassi C, Behrman SW, et al. Surgeon experience contributes to improved outcomes in pancreatoduodenectomies at high risk for fistula development. Surgery. 2021;169(4):708–20. Epub 2021/01/03. doi: 10.1016/j.surg.2020.11.022 . [DOI] [PubMed] [Google Scholar]

[pone.0259682.ref039] 39.Schmidt CM, Turrini O, Parikh P, House MG, Zyromski NJ, Nakeeb A, et al. Effect of Hospital Volume, Surgeon Experience, and Surgeon Volume on Patient Outcomes After Pancreaticoduodenectomy: A Single-Institution Experience. Archives of Surgery. 2010;145(7):634–40. doi: 10.1001/archsurg.2010.118 [DOI] [PubMed] [Google Scholar]

PERMALINK

Prediction of massive bleeding in pancreatic surgery based on preoperative patient characteristics using a decision tree

Taiichi Wakiya

Keinosuke Ishido

Norihisa Kimura

Hayato Nagase

Shunsuke Kubota

Hiroaki Fujita

Yusuke Hagiwara

Taishu Kanda

Masashi Matsuzaka

Yoshihiro Sasaki

Kenichi Hakamada

Roles

Abstract

Introduction

Materials and methods

Patients and study design

Perioperative variable selection

Surgical procedures and operative management

Definition of massive IBL

Statistical analyses

Decision tree analysis

Results

Patient characteristics from the training and testing data sets

Table 1. Patient characteristics in data sets.

Table 2. Information of IBL.

Comparison of the perioperative characteristics of the massive IBL and non-massive IBL groups

Table 3. Comparison of the perioperative characteristics of massive IBL and non-massive IBL groups.

Comparison of the postoperative outcomes of the massive IBL and non-massive IBL groups

Table 4. Comparison of the operative outcomes of the massive IBL and non-massive IBL groups.

Fig 1. Survival curves of the massive IBL and non-massive IBL groups.

Binary logistic regression analysis

Decision tree analysis

Fig 2. Illustration of the decision tree model for massive IBL occurrence.

Discussion

Conclusions

Supporting information

Acknowledgments

Data Availability

Funding Statement

References

Decision Letter 0

Ulrich Wellner

Roles

Author response to Decision Letter 0

Decision Letter 1

Ulrich Wellner

Roles

Acceptance letter

Ulrich Wellner

Roles

Associated Data

Supplementary Materials

Data Availability Statement

ACTIONS

PERMALINK

RESOURCES

Similar articles

Cited by other articles

Links to NCBI Databases