Diabetes prediction using machine learning and explainable AI techniques

Abstract

Globally, diabetes affects 537 million people, making it the deadliest and the most common non-communicable disease. Many factors can cause a person to get affected by diabetes, like excessive body weight, abnormal cholesterol level, family history, physical inactivity, bad food habit etc. Increased urination is one of the most common symptoms of this disease. People with diabetes for a long time can get several complications like heart disorder, kidney disease, nerve damage, diabetic retinopathy etc. But its risk can be reduced if it is predicted early. In this paper, an automatic diabetes prediction system has been developed using a private dataset of female patients in Bangladesh and various machine learning techniques. The authors used the Pima Indian diabetes dataset and collected additional samples from 203 individuals from a local textile factory in Bangladesh. Feature selection algorithm mutual information has been applied in this work. A semi-supervised model with extreme gradient boosting has been utilized to predict the insulin features of the private dataset. SMOTE and ADASYN approaches have been employed to manage the class imbalance problem. The authors used machine learning classification methods, that is, decision tree, SVM, Random Forest, Logistic Regression, KNN, and various ensemble techniques, to determine which algorithm produces the best prediction results. After training on and testing all the classification models, the proposed system provided the best result in the XGBoost classifier with the ADASYN approach with 81% accuracy, 0.81 F1 coefficient and AUC of 0.84. Furthermore, the domain adaptation method has been implemented to demonstrate the versatility of the proposed system. The explainable AI approach with LIME and SHAP frameworks is implemented to understand how the model predicts the final results. Finally, a website framework and an Android smartphone application have been developed to input various features and predict diabetes instantaneously. The private dataset of female Bangladeshi patients and programming codes are available at the following link: https://github.com/tansin-nabil/Diabetes-Prediction-Using-Machine-Learning.

Explainable AI Evaluation: A Top-Down Approach for Selecting Optimal Explanations for Black Box Models

“…As an example, our results aligned with the research conducted by Tasin et al (2022), where LIME and SHAP were employed as their explainer, identifying XGBoost as the best-performing model. Remarkably, Glucose, BMI, and Age were recognized as the most salient features [68]. Similarly, another study employed similar methods including RF and XGBoost, and employed LIM and SHAP as explainers [69].…”

Predictive Modeling for Diabetes Using GraphLIME

“…The paper [4] is centered on developing machine learning models for diabetes prediction, with a strong emphasis on the use of explainable AI to improve the predictions’ trust-worthiness. This research aims to offer a valuable tool for the early detection of diabetes, vital for effective management and treatment in healthcare.…”

A systematic review of prediction accuracy as an evaluation measure for determining machine learning model performance in healthcare systems

“…ML principles and applications in real world systems have also been explored [15]. An automatic prediction system for diabetic patients using dataset of females and several ML techniques for an explainable artificial intelligence [16] concluded with prediction accuracy score of 81% and an auc score of 0.84. Furthermore studies such as prediction of an occurrence of pressure ulcer nursing adverse event [17] using four different ML techniques namely; Decision trees, Support Vector Machines, Random Forest and Artificial Neural Networks achieved a prediction accuracy scores of 94.94% for Support vector machine, 97.93% for Decision trees, 99.88% for Random Forests and 79.02% for Artificial Neural Networks.…”