Skip to main content
. 2023 Nov 20;11:e47833. doi: 10.2196/47833

Table 2.

Baseline characteristics of studies predicting adverse BGa events (N=19).

First author (year), country Data source Sample size Object; setting Model Time Age (years), mean (SD)/range Threshold
Patients, n Data points, n Hypoglycemia, n
Pils (2014), United States [39] CGMb device 2 2518 152 T1DMc; out SVMd All —e 3.9
Seo (2019), Korea [15] CGM device 104 7052 412 DMf; out RFg, SVM, k-nearest neighbor (kNN), logistic regression (LR) Postprandial 52 3.9
Parcerisas (2022), Spain [29] CGM device 10 67 22 T1DM; out SVM Nocturnal 31.8 (SD 16.8) 3.9
Stuart (2017), Greece [30] EHRsh 9584 — 1327 DM; in Multivariable logistic regression (MLR) All — 4
Bertachi (2020), Spain [31] CGM device 10 124 39 T1DM; out SVM Nocturnal 31.8 (SD 16.8) 3.9
Elhadd (2020), Qatar [32] — 13 3918 172 T2DM; out XGBoosti All 35-63 —
Mosquera-Lopez (2020), United States [33] CGM device 10 117 17 T1DM; out SVM Nocturnal 33.7 (SD 5.8) 3.9
Mosquera-Lopez (2020), United States [33] CGM device 20 2706 258 T1DM; out SVM Nocturnal — 3.9
Ruan (2020), England [34] EHRs 17,658 3276 703 T1DM; in XGBoost, LR, stochastic gradient descent (SGD), kNN, DTj, SVM, quadratic discriminant analysis (QDA), RF, extra tree (ET), linear discriminant analysis (LDA), AdaBoost, bagging All 66 (SD 18) 4
Güemes (2020), United States [35] CGM device 6 55 6 T1DM; out SVM Nocturnal 40-60 3.9
Jensen (2020), Denmark [36] CGM device 463 921 79 T1DM; out LDA Nocturnal 43 (SD 15) 3
Oviedo (2019), Spain [37] CGM device 10 1447 420 T1DM; out SVM Postprandial 41 (SD 10) 3.9
Toffanin (2019), Italy [38] CGM device 20 7096 36 T1DM; out Individual model-based All 46 3.9
Bertachi (2018), United States [47] CGM device 6 51 6 T1DM; out NNMk Nocturnal 40-60 3.9
Eljil (2014), United Arab Emirates [48] CGM device 10 667 100 T1DM; out Bagging All 25 3.3
Dave (2021), United States [56] CGM device 112 546,640 12,572 T1DM; out RF All 12.67 (SD 4.84) 3.9
Marcus (2020), Israel [57] CGM device 11 43,533 5264 T1DM; out Kernel ridge regression (KRR) All 18-39 3.9
Reddy (2019), United States [58] — 55 90 29 T1DM; out RF — 33 (SD 6) 3.9
Sampath (2016), Australia [59] — 34 150 40 T1DM; out Ranking aggregation (RA) Nocturanl — —
Sudharsan (2015), United States [60] — — 839 428 T2DM; out RF All — 3.9

aBG: blood glucose.

bCGM: continuous glucose monitoring.

cT1DM: type 1 diabetes mellitus.

dSVM: support vector machine.

eNot applicable.

fDM: diabetes mellitus.

gRF: random forest.

hEHR: electronic health record.

iXGBoost: Extreme Gradient Boosting.

jDT: decision tree.

kNNM: neural network model.