Data-Driven Machine-Learning Methods for Diabetes Risk Prediction

Abstract

Diabetes mellitus is a chronic condition characterized by a disturbance in the metabolism of carbohydrates, fats and proteins. The most characteristic disorder in all forms of diabetes is hyperglycemia, i.e., elevated blood sugar levels. The modern way of life has significantly increased the incidence of diabetes. Therefore, early diagnosis of the disease is a necessity. Machine Learning (ML) has gained great popularity among healthcare providers and physicians due to its high potential in developing efficient tools for risk prediction, prognosis, treatment and the management of various conditions. In this study, a supervised learning methodology is described that aims to create risk prediction tools with high efficiency for type 2 diabetes occurrence. A features analysis is conducted to evaluate their importance and explore their association with diabetes. These features are the most common symptoms that often develop slowly with diabetes, and they are utilized to train and test several ML models. Various ML models are evaluated in terms of the Precision, Recall, F-Measure, Accuracy and AUC metrics and compared under 10-fold cross-validation and data splitting. Both validation methods highlighted Random Forest and K-NN as the best performing models in comparison to the other models.

Metabolomic Selection in the Progression of Type 2 Diabetes Mellitus: A Genetic Algorithm Approach

“…In comparison with clinical or anthropometric data, metabolite data are presented as complements of models; however, the metabolites presented in this study can perform better than clinical and anthropometric data [ 41 ]. This behavior can be explained by the use of genetic algorithms as selectors and the proper preselection and prediction of the most important metabolites or family-related metabolites with respect to the disease.…”

Long-Term Coronary Artery Disease Risk Prediction with Machine Learning Models

“…Nowadays, medicine has a variety of modern diagnostic tests, which, in cooperation with Information technology and, especially, the fields of artificial intelligence (AI) and machine learning (ML), in the hands of cardiologists are powerful weapons for the prevention or diagnosis of coronary artery disease. ML techniques now play an important role in the early prediction of disease complications in diabetes (as classification [ 15 , 16 ] or regression tasks for continuous glucose prediction [ 17 , 18 ]), cholesterol [ 19 , 20 ], hypertension [ 21 , 22 ], chronic obstructive pulmonary disease (COPD) [ 23 ], COVID-19 [ 24 ], stroke [ 25 ], chronic kidney disease (CKD) [ 26 ], liver disease (LD) [ 27 ], sleep disorders [ 28 , 29 ], hepatitis C [ 30 ], cardiovascular diseases (CVDs) [ 31 ], lung cancer [ 32 ], and metabolic syndrome [ 33 ] etc. In particular, the long-term risk prediction of CAD will concern us in the context of this study.…”

Efficient Data-Driven Machine Learning Models for Cardiovascular Diseases Risk Prediction

“…Moreover, ML techniques now enable medical researchers to detect significant diseases in a more sophisticated and accurate way. In this direction, ML plays an essential role in the early prediction of disease complications in diabetes (as classification [ 23 , 24 ] or regression task for continuous glucose prediction [ 25 , 26 ]), cholesterol [ 27 ], hypertension [ 28 , 29 ], hypercholesterolemia [ 30 ], chronic obstructive pulmonary disease (COPD) [ 31 ], COVID-19 [ 32 ], stroke [ 33 ], chronic kidney disease (CKD) [ 34 ], liver disease [ 35 ], hepatitis-C [ 36 ], lung cancer [ 37 ], sleep disorders [ 38 ], metabolic syndrome [ 39 ], etc.…”