A Group Recommender System Based on Machine Learning for Hypertensive Patients

Kargari, Mehrdad; Valiollahi, Arefeh

doi:10.30491/ijtmgh.2024.452621.1411

A Group Recommender System Based on Machine Learning for Hypertensive Patients

Document Type : Original Article

Authors

Mehrdad Kargari ¹

Arefeh Valiollahi ²

¹ Faculty of Industrial Engineering and Systems, Tarbiat Modares University, Tehran, Iran

² Information Technology dept., Tarbiat Modares University, Tehran, Iran

10.30491/ijtmgh.2024.452621.1411

Abstract

Hypertension, a severe chronic disease and a primary risk factor for cardiovascular issues, poses significant challenges in treatment and decision-making for physicians. Recommender systems present a promising avenue for enhancing hypertension care decision-making processes. However, traditional approaches such as collaborative filtering encounter challenges like data sparsity and scalability. To address these challenges, machine learning based recommender systems have been explored. This study presents an enhanced collaborative filtering method, integrating clustering and group recommendation techniques. The proposed research aggregates group recommendations for each cluster using static and dynamic methods. For new patients, three similarity measures are employed to select relevant recommendations from the most similar case cluster. The findings demonstrate the model's satisfactory performance, particularly when employing dynamic group recommendation and Euclidean similarity, showcasing improved accuracy in terms of Mean Absolute Error (MAE).

Keywords

Clustering

Hypertension

Machine learning

Recommender system