Recommender Algorithm for Supporting Self-Management of CVD Risk Factors in an Adult Population at Home

TL;DR

This paper presents a knowledge-based recommendation algorithm that combines rule-based logic with large language models to support self-management of cardiovascular risk factors at home, aiming to improve CVD prevention effectiveness.

Contribution

It introduces a novel multidimensional user profile model and integrates LLMs into a knowledge-based recommendation system for CVD risk management.

Findings

The algorithm evaluates more CVD risk factors than existing methods.

It generates more informative and semantically rich recommendations.

Verification shows improved support for self-management at home.

Abstract

One of the new trends in the development of recommendation algorithms is the dissemination of their capabilities to support the population in managing their health. This article focuses on the problem of improving the effectiveness of cardiovascular diseases (CVD) prevention, since CVD is the leading cause of death worldwide. To address this issue, a knowledge-based recommendation algorithm was proposed to support self-management of CVD risk factors in adults at home. The proposed algorithm is based on the original multidimensional recommendation model and on a new user profile model, which includes predictive assessments of CVD health in addition to its current ones as outlined in official guidelines. The main feature of the proposed algorithm is the combination of rule-based logic with the capabilities of a large language model in generating human-like text for explanatory component of multidimensional recommendation. The verification and evaluation of the proposed algorithm showed the usefulness of the proposed recommendation algorithm for supporting adults in self-management of their CVD risk factors at home. As follows from the comparison with similar knowledge-based recommendation algorithms, the proposed algorithm evaluates a larger number of CVD risk factors and has a greater information and semantic capacity of the generated recommendations.