Diabetes, Hypertension and Stroke Prediction Using Computational Algorithms
R. Yashvanth, Mohammed Rehan, Ashwini Kodipalli, B R Rohini, Trupthi Rao
Abstract
Diabetes, stroke, and hypertension are the three among main global causes of mortality and disability. Early identification and prediction of these chronic diseases is crucial for effective treatment and management. Machine learning (ML) models have shown promise in predicting these diseases based on patient data. This study focuses to review the current state of the art in using ML models for diabetes, stroke, and hypertension prediction. The literature review also revealed that challenges exist in the quality and availability of patient data, which can affect the performance of ML models for disease prediction. For example, data often suffers from missing values and imbalanced classes, which can affect the performance of ML models. In addition, selecting appropriate ML models for a particular task is challenging because there are many models available and each model has different strengths and weaknesses. Therefore, this study offers a widespread overview of the current state of art in using ML models for diabetes, stroke, and hypertension prediction. The study highlights the potential and limitations of ML models in this field, and provides a basis for future research in this area. The study also has important implications for healthcare practitioners, researchers, and policy makers, as it highlights the need for further investment in improving the quality of patient data and in developing effective and reliable ML models for disease prediction.