Machine Learning Based Diabetes Classification and Prediction for Healthcare Applications

Abstract

The remarkable advancements in biotechnology and public healthcare infrastructures have led to a momentous production of critical and sensitive healthcare data. By applying intelligent data analysis techniques, many interesting patterns are identified for the early and onset detection and prevention of several fatal diseases. Diabetes mellitus is an extremely life-threatening disease because it contributes to other lethal diseases, i.e., heart, kidney, and nerve damage. In this paper, a machine learning based approach has been proposed for the classification, early-stage identification, and prediction of diabetes. Furthermore, it also presents an IoT-based hypothetical diabetes monitoring system for a healthy and affected person to monitor his blood glucose (BG) level. For diabetes classification, three different classifiers have been employed, i.e., random forest (RF), multilayer perceptron (MLP), and logistic regression (LR). For predictive analysis, we have employed long short-term memory (LSTM), moving averages (MA), and linear regression (LR). For experimental evaluation, a benchmark PIMA Indian Diabetes dataset is used. During the analysis, it is observed that MLP outperforms other classifiers with 86.08% of accuracy and LSTM improves the significant prediction with 87.26% accuracy of diabetes. Moreover, a comparative analysis of the proposed approach is also performed with existing state-of-the-art techniques, demonstrating the adaptability of the proposed approach in many public healthcare applications.

A Decision Support System for Diagnosing Diabetes Using Deep Neural Network

“…More effective supervised learning algorithms for disease prediction can significantly reduce these medical errors. The healthcare sector has been supplied with a variety of supervised learning methods by researchers ( 9 ). In the health sector, data scientists are encouraged to build useful applications that may help healthcare experts diagnose and manage diabetes illness ( 10 ).…”

“…In the past several years, a number of scientists have investigated the possibility of using health data to predict diabetes using computational approaches like machine learning (ML) ( 9 , 10 ). This research's major goal was to discover ways to detect diabetes before symptoms appear.…”

“…Butt et al developed an ML-based prediction approach for diabetic disease ( 9 ). ML was used to better predict diabetes using random forest (RF), support vector machine (SVM), and other classifiers.…”

“…As a result, typical machine learning algorithms are often inefficient at accurately predicting diabetes risk from medical information. Because this study effort had certain limitations ( 9 ), we proposed an updated DL model called BiLSTM, which has previously been effectively employed in several fields such as DDoS attack prediction, behavior recognition, and others ( 2 , 11 ). To predict diabetes, we created the BiLSTM model.…”

“…The use of traditional feature sets followed by an ML classifier makes it difficult to accurately predict diabetes from patient data ( 9 , 10 ). Furthermore, the lack of relevant context makes DL models for diabetic illness prediction less effective.…”