A Machine Learning Approach to Predicting Diabetes Complications

Abstract

Diabetes mellitus (DM) is a chronic disease that is considered to be life-threatening. It can affect any part of the body over time, resulting in serious complications such as nephropathy, neuropathy, and retinopathy. In this work, several supervised classification algorithms were applied for building different models to predict and classify eight diabetes complications. The complications include metabolic syndrome, dyslipidemia, neuropathy, nephropathy, diabetic foot, hypertension, obesity, and retinopathy. For this study, a dataset collected by the Rashid Center for Diabetes and Research (RCDR) located in Ajman, UAE, was utilized. The dataset consists of 884 records with 79 features. Some essential preprocessing steps were applied to handle the missing values and unbalanced data problems. Furthermore, feature selection was performed to select the top five and ten features for each complication. The final number of records used to train and build the binary classifiers for each complication was as follows: 428—metabolic syndrome, 836—dyslipidemia, 223—neuropathy, 233—nephropathy, 240—diabetic foot, 586—hypertension, 498—obesity, 228—retinopathy. Repeated stratified k-fold cross-validation (with k = 10 and a total of 10 repetitions) was employed for a better estimation of the performance. Accuracy and F1-score were used to evaluate the models’ performance reaching a maximum of 97.8% and 97.7% for accuracy and F1-scores, respectively. Moreover, by comparing the performance achieved using different attributes’ sets, it was found that by using a selected number of features, we can still build adequate classifiers.

Comparison of Different Machine Learning Techniques to Predict Diabetic Kidney Disease

“…e AdaBoost classifier algorithm was found to be highly accurate (0.917) for the prediction of diabetic nephropathy in a dataset of 884 patients and 70 attributes. When the attributes were decreased to the top 5 only, the performance was not affected [28]. Our results show that IBK and random tree classifiers with a dataset of 410 patients and 18 attributes achieved an accuracy of 93.6585%.…”

DDPIS: Diabetes Disease Prediction by Improvising SVM

“…Yazan Jian et al ( 2021) used a dataset from the Rashid Center for Diabetes and Research, which is situated in UAE and applied ML to predict diabetes disease. (Jian et al, 2021) Finally, Xue et al (2020) used SVM, NB and Light GBM, collected datasets from UCI ML Repository, and achieved the best accuracy with SVM. (Xue et al, 2020) In our work, we found that most diabetes disease predictions are based on gestational diabetes, which is present in pregnant ladies.…”

Diabetes Prediction Using Machine Learning Algorithms and Ontology

“…In another way, the authors of the paper [13] have built models to predict and classify diabetes complications. In this work, several supervised classification algorithms were applied to predict and classify 8 diabetes complications.…”