Ability to Predict Melanoma Within 5 Years Using Registry Data and a Convolutional Neural Network: A Proof of Concept Study

Abstract

Research relating to machine learning algorithms, including convolutional neural networks, has increased during the past 5 years. The aim of this pilot study was to investigate how accurately a convolutional neural network, trained on Swedish registry data, could perform in predicting cutaneous invasive and in situ melanoma (CMM) within 5 years. A cohort of 1,208,393 individuals was used. Registry data ranged from 4 July 2005 to 31 December 2011, predicting CMM between 1 January 2012 and 31 December 2016. A convolutional neural network with one-dimensional convolutions with respect to time was trained using healthcare databases and registers. The algorithm was trained on 23,886 individuals. Validation was performed on a holdout validation set including 6,000 individuals. After training and validation, the convolutional neural network was evaluated on a test set (1,000 individuals with an CMM occurring within 5 years and 5,000 without). The area under the receiver-operating characteristic curve was 0.59 (95% confidence interval (95% CI) 0.57–0.61). The point on the receiver-operating characteristic curve where sensitivity equalled specificity had a value of 56% (sensitivity 95% CI 53–60% and specificity 95% CI 55–58%). Albeit at an early stage, this pilot investigation demonstrates potential usefulness for machine learning algorithms in predicting melanoma risk.

Machine learning (ML) algorithms including convolutional neural networks (CNNs) have recently pervaded every aspect of medical imaging, and noteworthy advancements have been made in several medical fields, including radiology (1), dermatology (2–5) and pathology (6). Furthermore, significant progress has been made using neural networks in domains other than image analysis, such as prediction models for specific diseases using available electronic healthcare data and registries. The concept of using neural networks on electronic healthcare data for prediction models, often referred to as computational phenotyping, was first published in 2016 by Cheng et al. (7). To date, only a few investigations have been performed to predict specific dermatological outcomes (8). In future healthcare, it is expected that prediction algorithms will be important to target the increased demands for precision medicine. Moreover, ML algorithms may prove particularly useful for targeted population screening, where high-risk individuals could be identified and automatically invited to screening visits, based on available data in healthcare registries. Finally, these models may reduce healthcare costs and prove to be time efficient.

SIGNIFICANCE

For all Swedish citizens extensive healthcare data are available in several registries and databases. In this proof of concept study, this data was used to train a machine learning model to predict future risk of melanoma, a potentially lethal skin tumour. Registry data ranging from 2005 to 2011 was used to predict risk of melanoma in the period 2012 to 2016. Using merely this data-set, the machine learning algorithm achieved significantly better than chance alone. While the model needs to be improved and refined in upcoming investigations, this study demonstrates potential usefulness for machine learning in this setting.

For a Swedish population, setting up a risk prediction model for cutaneous malignant melanoma (CMM) would be appealing, since the incidence is one of the highest in the world (9). The incidence of CMM has increased dramatically in the Nordic population during the past 3 decades. In Sweden, approximately 500 individuals die from advanced melanoma disease annually. In the early stages, CMM is treatable with an overall good prognosis, whereas in more advanced stages, the prognosis is poor and treatment is costly (10, 11). From a societal perspective, finding novel and complementary tools to identify individuals at higher risk of skin cancer in general and for CMM in particular is a high priority.

Sweden has a public healthcare system, which is largely documented with nationwide registers. This is a world-unique source of information, which, unlike many other countries, is completely disconnected from insurance and compensation systems. The aim of this pilot study was to investigate how accurately a CNN trained on Swedish registry data could perform in predicting CMM within 5 years in individuals without a previous history of CMM.

MATERIALS AND METHODS

Cohort description

This retrospective investigation included individuals from 8 cohorts used in previous research projects. This previous research primarily investigated patients with psoriasis and their respective controls. When merging all of these, the original source cohort consisted of approximately 1.7 million individuals. One of the 8 original cohorts (i.e. patients with psoriasis) has been used in 2 previous investigations (12, 13). A detailed description of all 8 cohorts is presented in Appendix S1. To exclude any systematic bias (i.e. to avoid an over-representation of patients with psoriasis), we only included the 4 control cohorts in our analyses. When merging all these data, 1,489,519 individuals were available.

The registry data ranged from 4 July 2005 to 31 December 2011, predicting CMM between, 1 January 2012 and 31 December 2016. The data comprised time-independent (age, sex, origin, country of birth, income and educational level) and time-dependent variables, including drug prescription (Anatomical Therapeutic Chemical (ATC) and diagnosis (International Classification of Diseases 10th Revision (ICD-10)) codes (Tables I and II). A brief overview of the registries and databases used is shown in Appendix S2.

Table I.

Time-independent variables

Time-independent variables	Variable description
Age	Normed age at 2012 normed in [–1,1]
Sex	Males: 1. Females: –1
One-hot encoding
Region of birth
Africa	Yes: 1. No: –1
Asia	Yes: 1. No: –1
European Union (EU) except the Nordic countries	Yes: 1. No: –1
Europe except the EUUnion and Nordic countries	Yes: 1. No: –1
North America	Yes: 1. No: –1
Nordic countries except Sweden	Yes: 1. No: –1
Oceania	Yes: 1. No: –1
Soviet Union	Yes: 1. No: –1
Sweden	Yes: 1. No: –1
South America	Yes: 1. No: –1
Disposable income
Disposable income 1st quartile	Yes: 1. No: –1
Disposable income 2nd quartile	Yes: 1. No: –1
Disposable income 3rd quartile	Yes: 1. No: –1
Disposable income 4th quartile	Yes: 1. No: –1
Missing data	Yes: 1. No: –1
Level of education
Pre-high-school education less than 9 years	Yes: 1. No: –1
Pre-high-school education less than 9–10 years	Yes: 1. No: –1
High-school education	Yes: 1. No: –1
University education shorter than 2 years	Yes: 1. No: –1
University education 2 years or longer	Yes: 1. No: –1
Postgraduate education	Yes: 1. No: –1
Missing data	Yes: 1. No: –1
Marital status
Surviving partner (previously unmarried)	Yes: 1. No: –1
Married	Yes: 1. No: –1
Unmarried	Yes: 1. No: –1
Registered partner	Yes: 1. No: –1
Divorced	Yes: 1. No: –1
Divorced partner	Yes: 1. No: –1
Widow/widower	Yes: 1. No: –1
Missing data	Yes: 1. No: –1
Origin
Born abroad	Yes: 1. No: –1
Born in Sweden with both parents born abroad	Yes: 1. No: –1
Born in Sweden with 1 parent born abroad	Yes: 1. No: –1
Born in Sweden with both parents born in Sweden	Yes: 1. No: –1
Missing data	Yes: 1. No: –1

Table II.

Time-dependent variables

Time-dependent variables	Variable description
221 rows in total
International Classification of Diseases 10th Revision (ICD-10) symbol
1 row for each occurring first symbol of ICD-10	Yes: 1. No: –1
1 row for each occurring second symbol of ICD-10	Yes: 1. No: –1
1 row for each occurring third symbol of ICD-10	Yes: 1. No: –1
1 row for each occurring fourth symbol of ICD-10	Yes: 1. No: –1
1 row for each occurring fifth symbol of ICD-10	Yes: 1. No: –1
Inpatient and/or outpatient diagnosis
Inpatient diagnosis present	Yes: 1. No: –1
Outpatient diagnosis present	Yes: 1. No: –1
Anatomical Therapeutic Chemical (ATC) symbol
1 row for each occurring first symbol of ATC	Yes: 1. No: –1
1 row for each occurring second symbol of ATC	Yes: 1. No: –1
1 row for each occurring third symbol of ATC	Yes: 1. No: –1
1 row for each occurring fourth symbol of ATC	Yes: 1. No: –1
1 row for each occurring fifth symbol of ATC	Yes: 1. No: –1
1 row for each occurring sixth symbol of ATC	Yes: 1. No: –1
1 row for each occurring seventh symbol of ATC	Yes: 1. No: –1

Included individuals needed to be ≥ 18 years on 4 July 2005 and were excluded if they were ≥ 95 years during 2012. All individuals had to be alive on 31 December 2011. No migration events between 4 July 2005 and 31 December 2016 were allowed. All individuals with a history of CMM (including melanoma in situ) before 1 January 2012 were excluded. After exclusions, the final cohort comprised 1,208,393 individuals in the age range 25–94 years. All these individuals were drawn from the general population, and constituted approximately 18% of the Swedish population within the same age range (i.e. 6.7 million individuals) (14).

Randomization of training, validation, and test-set

All individuals with an occurring CMM in the time-period 1 January 2012 to 31 December 2016 were identified (n = 5,981). To each such individual, 5 age- and sex-matched individuals were drawn randomly from the available controls (n = 29,905). The controls did not develop CMM in the same time-period. All included individuals (n = 35,886) were randomized into a training, validation, and test-set (Fig. 1). The default random number generator was used (Mersenne-Twister) in R version 3.5.3 (https://www.r-project.org/) for the randomization process.

Fig. 1.

Flow chart for selection of eligible controls. *All individuals were included in a previous research project (Appendix S1). ^§The disease cohort consisted primarily of patients with psoriasis (Appendix S1). ¶ Included individuals were drawn from the general Swedish population and were randomly matched to the disease cohort with respect to age, sex and geographical location. ^#The listed exclusion criteria are not mutually exclusive. ^†The individuals without CMM were matched to the individuals with CMM with respect to sex and age (same birth year). CMM: cutaneous malignant melanoma including in situ melanoma.

The study was reviewed and approved by the Swedish Ethical Review Authority (registration number 2020-06761) and the Ethics Review Appeals Board (registration number Ö14-2021/3.1).

Outcome

The primary outcome was to investigate at what sensitivity and specificity level a CNN, trained on Swedish registry data, could predict which individuals would be diagnosed with CMM within 5 years. A receiver-operating characteristics curve (ROC) was used to demonstrate the sensitivity and specificity for correctly identifying individuals that would develop CMM. The area under the ROC (AUC) was used to assess the overall model performance.

Model architecture

Different models were trained and validated on the holdout validation set after each epoch. All models were trained using healthcare databases and registers (Appendices S3 and S4). The number of dense layers in models varied from 1 to 5. Within dense layers the number of nodes varied from 64 to 1,024. Models with 1 and 2 convolutional layers (with strides) were trained and the number of filters within the convolutional layers were 4 or 8. In total, 68 different models were trained. Finally, a primary model was selected that achieved maximum performance on the holdout validation set. Only the primary model, along with 9 variations of the model (post-hoc analyses; Table III) were evaluated on the test-set.

Table III.

Primary and sensitivity (post-hoc) analyses

ICD-10 codes included (126 rows)	ATC-codes included (95 rows)	Demographic data included (37 rows)	Last 39 weeks censored in input	Uses 2 convolutional layers	AUC	95% CI	p-valueb
Primary model
Yes	Yes	Yes	No	No	0.59a	0.57–0.61	–
Sensitivity (post-hoc) analyses
Yes	Yes	Yes	Yes	Yes	0.59	0.57–0.61	0.79
Yes	No	Yes	No	No	0.60	0.58–0.62	0.26
No	No	Yes	No	No	0.59	0.57–0.61	0.39
No	Yes	Yes	No	No	0.59	0.57–0.61	0.52
Yes	Yes	No	No	No	0.56	0.54–0.58	0.009
Yes	No	No	No	No	0.54	0.52–0.56	< 0.0001
No	Yes	No	No	No	0.53	0.51–0.55	< 0.0001
Yes	Yes	No	Yes	Yes	0.55	0.53–0.57	0.0004
Yes	Yes	No	Yes	No	0.56	0.54–0.58	0.008

^aPrimary model.

^bp-value compared with primary model.

AUC: area under the receiver operating characteristic curve; 95% CI: 95% confidence interval; ATC: Anatomical Therapeutic Chemical; ICD-10: International Classification of Diseases 10^th Revision.

The primary model used 1 convolutional layer with 4 filters and a kernel of size (1, 351); i.e. 351 weeks. There were 3 dense layers with 512, 256 and 128 nodes in each, respectively (Fig. S1).

Sensitivity (post-hoc) analyses

To evaluate which data points were important for the model’s AUC, 9 sensitivity (post-hoc) analyses were conducted, which systematically omitted ICD-10 codes and/or ATC-codes, and/or demographic factors, respectively. Models that used 2 convolutional layers were also used, in which the first layer used kernels of size (1, 52) using strides; i.e. 1 year. The second convolutional layer had kernels of size (1, 6); i.e. 6 years. This implied that the last 39 (351-52•6) weeks of the time-dependent variables were censored (i.e. ICD-10 and ATC codes) (Appendices S5 and S6).

Statistical analysis

All data were analysed using R version 3.5.3 (https://www.r-project.org/). All tests were 2-sided and p < 0.05 was considered statistically significant. DeLong’s test for 2 correlated ROC curves was used to compare the performance of different models. Fisher’s exact test and Wilcoxon’s rank sum test were used for 2-sample comparisons.

Hardware and software

The Keras library (version 2.3.1) using the Tensorflow backend (version 1.14.0) was used running on Python version 3.6.9. Model construction was performed using R version 3.5.3 (https://www.r-project.org/) and the R-package Keras was used to call Python and its above libraries. The computer running the training was using the central processing unit (CPU) version on the Keras/Tensorflow routines. The CPU used was an Intel Xeon W-2135 @ 3.7 GHz, with 128 GB random-access memory (RAM). The training of the primary model (147 epochs) took 1 h and 11 min (Fig. S2).

RESULTS

Overall, median age at baseline was 65 years and there was a slight predominance of females (Table IV). The mean number of outpatient ICD-10 diagnoses before 1 January 2012 among all individuals was 14.0 (95% CI 13.7–14.3). The individuals with CMM had a mean of 15.2 diagnoses (95% CI 14.4–16.0) and the corresponding number for the controls was 13.8 (95% CI 13.5–14.1, p < 0.0001). The mean number of inpatient ICD-10 diagnoses before 1 January 2012 among all individuals was 7.4 (95% CI 7.3–7.6). The individuals with CMM had a mean of 6.9 diagnoses (95% CI 6.6–7.2) and the corresponding number for the controls was 7.5 (95% CI 7.4–7.7, p = 0.069). Individuals without CMM had dispensed more pharmaceutical drugs compared with individuals who developed CMM (Table IV).

Table IV.

Age, sex distribution and mean number of diagnoses and dispensed prescriptions of the individuals with and without cutaneous malignant melanoma including in situ melanoma (CMM)

	n	Sex		Agea		Diagnosesb		Dispensed prescriptionsc Mean n (95% CI)
		Females n (%)	Males n (%)	Median [IQR]	Mean (95% CI)	Outpatient Mean n (95% CI)	Inpatient Mean n (95% CI)
All individuals
Individuals without CMM	29,905	16,405 (54.9)	13,500 (45.1)	65 [55–73]	63.3 (63.1–63.4)	13.8 (13.5–14.1)	7.5 (7.4–7.7)	91.1 (89.2–93.0)
Individuals with CMM	5,981	3,281 (54.9)	2,700 (45.1)	65 [55–73]	63.3 (62.9–63.6)	15.2 (14.4–16.0)	6.9 (6.6–7.2)	81.1 (78.0–84.3)
Training set
Individuals without CMM	19,905	10,879 (54.7)	9,026 (45.3)	65 [55–73]	63.3 (63.1–63.5)	13.8 (13.4–14.1)	7.5 (7.3–7.7)	90.1 (87.9–92.4)
Individuals with CMM	3,981	2,190 (55.0)	1,791 (45.0)	65 [55–73]	63.3 (62.9–63.7)	15.6 (14.5–16.7)	6.8 (6.4–7.1)	80.3 (76.6–83.9)
Holdout validation set
Individuals without CMM	5,000	2,801 (56.0)	2,199 (44.0)	65 [55–72]	63.1 (62.7–63.4)	13.6 (13.1–14.3)	7.6 (7.3–8.0)	92.0 (87.3–96.7)
Individuals with CMM	1,000	560 (56.0)	440 (44.0)	65 [55–72]	63.1 (62.3–63.9)	14.8 (13.6–16.0)	7.4 (6.5–8.3)	82.9 (74.3–91.5)
Test set
Individuals without CMM	5,000	2,725 (54.5)	2,275 (45.5)	65 [56–73]	63.4 (63.0–63.8)	14.0 (13.0–14.9)	7.6 (7.2–8.0)	94.1 (89.4–98–8)
Individuals with CMM	1,000	531 (53.1)	469 (46.9)	65 [56–72]	63.4 (62.6–64.2)	14.1 (13.0–15.2)	7.1 (6.3–7.9)	82.9 (74.6–91.3)

The individuals without CMM were drawn with respect to age and sex distribution compared with the individuals with CMM.

^aAge at 1 January 2012.

^bMean number of in- and out-patient diagnoses in the period 4 July 2005 to 31 December 2011.

^cMean number of dispensed pharmaceutical drug in the period 4 July 2005 to 31 December 2011.

95% CI: 95% confidence interval; IQR: interquartile range.

Of individuals with CMM, 5,786 (96.7%) originated from Nordic countries. The corresponding number among individuals without CMM was 27,212 (91.0%, p < 0.0001) (Table V). Among all 29,905 individuals who did not develop CMM in the time-period, 3,359 (11.2%) had no available ICD-10 diagnoses. The corresponding value among individuals who developed CMM (n = 5,981) was 564 (9.4%, p < 0.0001). Overall, 355 (5.9%) and 2,450 (8.2%) of the individuals with and without CMM died during the observation period (p < 0.0001). For individuals who developed CMM, the median time (interquartile range; IQR) from baseline (i.e. 1 January 2012) to their first CMM was 2.8 years (1.4–3.9) (range 0–5.0 years). The median (IQR) age at CMM diagnosis was 67 years (57–75) (Table V).

Table V.

Additional characteristics of the individuals with and without cutaneous malignant melanoma including in situ melanoma (CMM)

	Age at CMM diagnosis, years Median (IQR)	Time from baseline to CMM diagnosis, years Median (IQR)	Individuals without ICD-10 diagnoses n (%)	Individuals born in the Nordic countries n (%)	Individuals that died during the observation period n (%)
Patients with CMM	67 (57–64)	2.8 (1.4–3.9)	564 (9.4)	5,786 (96.7)	355 (5.9)
Patients without CMM	–	–	3,359 (11.2)	27,212 (91.0)	2,450 (8.2)
p-value	–	–	< 0.0001	< 0.0001	< 0.0001

ICD-10: International Classification of Diseases 10^th Revision; IQR: interquartile range.

Primary analysis

The AUC for correctly identifying individuals with CMM was 0.59 (95% CI 0.57–0.61). The point on the ROC where sensitivity equalled specificity had a value of 56% (sensitivity 95% CI 53–60% and specificity 95% CI 55–58%) (Fig. 2).

Fig. 2.

Receiver-operating characteristics (ROC) curve. The ROC curve represents the overall model performance (i.e. sensitivity and specificity) in terms of correctly identifying individuals with CMM in a 5-year time-period (i.e. in the period 1 January 2012 to 31 December 2016) based on registry data obtained in the period 4 July 2005 to 31 December 2011.

Sensitivity (post-hoc) analyses

The model that used only ICD-10- and ATC-codes, but not demographic data, had an AUC of 0.56 (95% CI 0.54–0.58). The models that censored the last 39 weeks did not perform significantly worse than the corresponding non-censored models (p = 0.98). Moreover, using 2 convolutional layers did not alter the performance compared with similar models with 1 layer (p = 0.79). The model that included only demographic data performed on par with the primary model that included ICD-10-, ATC-codes and demographic data (Table III).

DISCUSSION

In this pilot investigation, using only routinely sampled registry data, we were able to predict the risk of development of CMM within a 5-year time period with an AUC of 0.59, when matching individuals with respect to age and sex. Non time-dependent variables (including origin, marital status, education level, disposable income, and region of birth) played a more important role for the model performance compared with time-dependent variables (including ATC- and ICD-10 codes).

In a publication by Wang et al. (15), the authors conducted a retrospective analysis of a randomized set of the Taiwanese population. The aim was to generate a prediction model for 1-year risk of non-melanoma skin cancer (NMSC) in previously cancer-free individuals, based on routinely sampled healthcare registry data. Similar to our model, their CNN did not include traditional risk factors, such as sun exposure, smoking, or family history of skin cancer. Instead, the prediction model included sequential diagnoses and a selection of prescription codes for the past 3 years. The training of the model used 5-fold cross-validation, which included 1,829 individuals with NMSC and 7,665 randomly selected controls. The sensitivity (standard deviation; SD) and specificity (SD) for identifying those individuals who developed NMSC was 83.1% (3.5) and 82.3% (4.1), respectively. The network achieved an AUC of 0.89 (0.007) and a positive predictive value (SD) of 57.1% (4.9). The authors concluded that the predictive analytic model may help healthcare professionals to target high-risk populations and optimize prevention strategies. However, the control individuals were not matched with respect to age, meaning that they were significantly younger (47.5 years) than the corresponding individuals who had NMSC (65.3 years). In their investigation age alone was an important predictor for NMSC. Most importantly no holdout validation set nor external test set was used (16, 17). This limits the external validation of the findings to the general population at large. Finally, the investigation included a population with Asian descent, which limits the external generalizability to other populations.

This investigation has some important limitations. For this binary classification problem, a CNN model was employed; however, other approaches could have been used, including recurrent neural networks, random forests and gradient boosting (18). While the model outperformed chance alone, the overall AUC (0.59, 95% CI 0.57–0.61) for predicting CMM within 5 years, is low and far from acceptable to be used in routine healthcare. Nonetheless, we cannot rule out that other ML models would outperform a CNN in this setting. Future investigations with direct comparison of the performance level of a variety of ML architectures would be useful to investigate the most appropriate modality for this setting. The peak AUC, using registry data alone, that can be expected for CMM prediction is yet to be determined. Moreover, what AUC levels would be acceptable to move forward with this application as a tool in healthcare is also subject to debate. Even then the place for these algorithms must be clearly defined. One potential application would be to use this tool as a guide to select individuals for CMM screening or CMM prevention campaigns. Another, and perhaps more clinically feasible, application is to let trained physicians use the algorithmic output as an aid when weighing risk factors for skin cancer in the in- and out-patient settings. A complete patient history, including all previous diagnoses and a detailed list of all medications dispensed for the past decade, is of, course, impossible to systematically compile during a patient visit. However, if this data, including an algorithmic output of the future risk of skin cancer, were available using simple computer techniques it might add value to the physicians and could help enable personalized precision medicine. Moreover, if clinicians could gain access to the registry data that is important, the usability of this method would probably increase further. This type of application would only be suitable for physicians who have received adequate training in interpretation of algorithmic output. Finally, it should preferably be used when a physician is able to integrate other risk factors that are not captured in the registries.

This investigation included time-dependent variables (dispensed pharmaceutical drugs and diagnoses). This deserves particular mention as they, intrinsically, may indicate information about future events (i.e. disease evolution). However, we believe that this is of minor importance, since our post-hoc analysis, in which the last 39 weeks of time-dependent variables were censored, yielded results on par with our primary model. However, to limit this issue further all individuals with a history of CMM at 31 December 2011 were excluded. Notably, the model only including demographic data performed on par with our original model including demographic data, ATC- and ICD-10 codes. One possible explanation could be that the demographic data already captures the relevant information in the ICD-10- and ATC-codes needed to predict CMM. However, the models in which demographic data were omitted still performed better than chance alone (AUC, 0.56). While there are thousands of available ATC- and ICD-10 codes, in order to preserve computing memory, a generic lossless embedding was used, in which each character in the respective position in the code was simply given its own row (Table II). This means that if several different ICD-10 or ATC codes, respectively, occurred in the same week, then the model could not distinguish between them. However, the model could still learn that certain combinations of characters are probabilistically related to certain outcomes. In upcoming investigations, it is our intention to update the model and include a less compressed version of the set of these codes.

Importantly, our investigation was performed in a population that is comprised mainly of individuals with Fitzpatrick skin types ranging from I to III. Furthermore, melanoma incidence in Sweden is high (9), and Swedish citizens have universal access to healthcare. The external validity of the current findings is, by design, intrinsically limited to the Swedish population alone, and the usefulness of similar prediction models in other populations with more limited access to healthcare might be more restrained. Finally, while 1.2 million individuals were used as eligible controls in the current investigation, also drawn from the general population, the controls represent a non-random subset of the corresponding Swedish adult population (approximately 6.7 million individuals). In future studies, the complete adult population will be used to further develop, refine, and update new registry-based prediction models for skin cancer including CMM. While computational phenotyping holds promise in this setting, future prospective clinical trials integrating algorithmic output with relevant clinical metadata will be required to fully assess the potential of these ancillary tools. Moreover, even if these models perform well in a research setting, political stakeholders and legislation must be involved before any broad implementation of these tools can be made in everyday clinical practice.

Research involving ML prediction models, based on registry data, is still in its initial stages, and adequate standardization is still pending (19). Nonetheless, the current investigation illustrates the potential usefulness of computational phenotyping for risk assessment in prediction of CMM in a Swedish population.