Keywords: Non-communicable diseases (NCDs), Cardiovascular disease, Type 2 Diabetes disease, AI-Platform
TL;DR: This paper proposes a privacy-preserving AI platform that accurately predicts non-communicable disease risks and alerts high-risk individuals via a mobile app.
Abstract: Non-communicable diseases (NCDs) are chronic medical conditions that are not caused by infectious agents and are primarily associated with lifestyle factors. This paper highlights the significant impact of NCDs on global public health, particularly in low- and middle-income countries where they account for most premature deaths. A privacy-preserving AI platform is proposed as a solution to predict the risks of having NCDs, such as cardiovascular diseases and type 2 diabetes, using clinical data and advanced machine learning algorithms such as ANN, SVM, Naive Bayes, and Random Forest. ANN proved to be the best performing for Diabetes and SVM for Heart disease with an accuracy of 92.15% and 92.59 respectively. Utilizing the top-performing models for predictions, the mobile application alerts users who are at high risk and also offers them the opportunity for further medical consultation.
Submission Category: Machine learning algorithms
Submission Number: 77
Loading