Predicting Diabetes Risk using Anomaly-Based Modeling of Physiological and Lifestyle Data

Diabetes is a major global health burden that is rapidly expanding and needs to be detected early and prevention strategies to be effective. Identifying the risk of diabetes early is very important to prevent complications such as cardiovascular diseases, kidney failure and nerve damage. But, conventional predictive methods aren't always able to find subtle and complex patterns in patient data, which makes them less effective when it comes to early diagnosis. Research’s objective is to seek innovative, accurate and strong strategies for early detection of high risk individuals. The aim of this study is to create an anomaly based machine learning model for diabetes risk prediction based on physiologic and lifestyle data. Parameters measured and included in the data are key physiological parameters such as blood glucose, BMI, blood pressure, insulin level, age and cholesterol, as well as lifestyle parameters such as physical activity, smoking status, alcohol consumption, sleep length, and dietary habits. The target variable is the outcome of diabetes (positive or negative). For anomaly detection, the study employs modelling algorithms based on anomalies (One-Class SVM, Local Outlier Factor (LOF), Autoencoders, and Hybrid Model which is combination of several of these). The methodology involves data preprocessing, feature selection, model construction and evaluation using accuracy, precision, recall, F1 score and ROC-AUC. The results demonstrated the highest accuracy and ROC-AUC value of the Hybrid Model, suggesting it effectively performed in detecting high-risk diabetes cases. Important predictors are blood glucose and BMI, additional factors are lifestyle behaviours. In conclusion, the proposed anomaly-based method improves diabetes risk prediction and aids in the detection of anomalies, which may be beneficial for diabetes prevention services and clinical actions.