Enhancing Medication Recommendations Through Multi-Criteria Collaborative Filtering

The exponential growth of online healthcare platforms has resulted in an overwhelming volume of medication information, posing challenges for patients seeking appropriate treatments for their specific conditions. Recommendation systems have emerged as valuable tools in various applications, including healthcare, helping users navigate information overload. However, their effectiveness in recommending medications is often limited by data sparsity, which arises from insufficient user-item interaction data and hinders accurate prediction. This study proposes a collaborative multi-criteria filtering approach that improves medication recommendations without relying on external knowledge sources. The proposed approach leverages multi-criteria ratings, implicit user and item similarities, similarity transitivity, and global similarity concepts. By effectively utilizing implicit information embedded within existing user-item multi-criteria ratings, the proposed approach effectively expands user and medication neighborhoods, resulting in more accurate and diverse recommendations, even in sparse data scenarios. Empirical analysis on a real-world medicine dataset demonstrated that the proposed approach significantly outperformed existing recommendation methods, resulting in substantial improvements in predictive accuracy and recommendation coverage, particularly in sparse environments.