Evaluation of Machine Learning Methods Developed for Prediction of Diabetes Complications: A Systematic Review

Abstract

Background: With the rising prevalence of diabetes, machine learning (ML) models have been increasingly used for prediction of diabetes and its complications, due to their ability to handle large complex data sets. This study aims to evaluate the quality and performance of ML models developed to predict microvascular and macrovascular diabetes complications in an adult Type 2 diabetes population. Methods: A systematic review was conducted in MEDLINE®, Embase®, the Cochrane® Library, Web of Science®, and DBLP Computer Science Bibliography databases according to the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) checklist. Studies that developed or validated ML prediction models for microvascular or macrovascular complications in people with Type 2 diabetes were included. Prediction performance was evaluated using area under the receiver operating characteristic curve (AUC). An AUC >0.75 indicates clearly useful discrimination performance, while a positive mean relative AUC difference indicates better comparative model performance. Results: Of 13 606 articles screened, 32 studies comprising 87 ML models were included. Neural networks (n = 15) were the most frequently utilized. Age, duration of diabetes, and body mass index were common predictors in ML models. Across predicted outcomes, 36% of the models demonstrated clearly useful discrimination. Most ML models reported positive mean relative AUC compared with non-ML methods, with random forest showing the best overall performance for microvascular and macrovascular outcomes. Majority (n = 31) of studies had high risk of bias. Conclusions: Random forest was found to have the overall best prediction performance. Current ML prediction models remain largely exploratory, and external validation studies are required before their clinical implementation. Protocol Registration: Open Science Framework (registration number: 10.17605/OSF.IO/UP49X).

Machine‐learning algorithms in screening for type 2 diabetes mellitus: Data from Fasa Adults Cohort Study

“…Previous studies have identified RF, SVM, KNN, and GBM as the optimal ML models for T2DM prediction. 15,16 While GBM demonstrated the best performance on our dataset, the present study yielded similar results, given the minor differences observed between the performances of other models. In this study, SVM, KNN, and RF showed an average AUC of 0.75, 0.73, and 0.75 for females, respectively.…”

“…Notably, in the studies by Abhari et al and Tan et al, KNN, NVM, and NB were the most utilized ML models for T2DM data. 15,19 We analysed the performance of each ML model separately for males and females in our study. Our findings indicated that the overall AUC of ML models was between 67 and 80 for females and 51 and 82 for males.…”

Comparison of Different Machine Learning Techniques to Predict Diabetic Kidney Disease

“…Our results show that IBK and random tree classifiers with a dataset of 410 patients and 18 attributes achieved an accuracy of 93.6585%. A systematic review on machine learning methods for prediction of diabetes complications found that random forest algorithm is the overall best prediction performing classifier [29]. We found that the IBK algorithm is the best prediction performing classifier, in general, IBK means KNN algorithm is one of the best classifiers.…”

Artificial Intelligence Methodologies Applied to Technologies for Screening, Diagnosis and Care of the Diabetic Foot: A Narrative Review

“…In this review, we focused on the use of artificial intelligence techniques applied to data derived from different sensors and technologies for the study of diabetic foot syndrome. Previous reviews, such as some of those mentioned previously [ 17 , 19 ], indicated diabetic foot as one of the fields for the application of artificial intelligence in the more general context of diabetes, but they were not focused specifically on the diabetic foot. On the other hand, one review focused on the diabetic foot, but artificial intelligence methodologies were only covered in a small part of the review [ 61 ].…”

“…In fact, artificial intelligence has unique capabilities to analyze problems affected by the behavior or the condition of a wide battery of factors and measured parameters, finally providing crucial indications about those that are more relevant to focus on in the problem under investigation. In the general field of diabetes, artificial intelligence has proven to be effective for several applications, as summarized by many review studies, such as those by Fregoso-Aparicio et al, Nomura et al, Tan et al, and Gautier et al, to mention some of the latest [ 16 , 17 , 18 , 19 ]. However, studies related to diabetic foot syndrome, with exploitation of the artificial intelligence applied to different technologies, are not as common as for other diabetic complications, such as diabetic retinopathy [ 20 ].…”