Beyond Traditional Diagnostics: Transforming Patient-Side Information into Predictive Insights with Knowledge Graphs and Prototypes
This work addresses the problem of improving disease prediction for patients and healthcare systems by enhancing accuracy and interpretability, though it appears incremental as it builds on existing methods like knowledge graphs and LLMs.
The paper tackles the problem of predicting diseases from patient-side information by addressing challenges like imbalanced distributions and lack of interpretability, resulting in a framework that outperforms state-of-the-art methods in accuracy and provides clinically valid explanations.
Predicting diseases solely from patient-side information, such as demographics and self-reported symptoms, has attracted significant research attention due to its potential to enhance patient awareness, facilitate early healthcare engagement, and improve healthcare system efficiency. However, existing approaches encounter critical challenges, including imbalanced disease distributions and a lack of interpretability, resulting in biased or unreliable predictions. To address these issues, we propose the Knowledge graph-enhanced, Prototype-aware, and Interpretable (KPI) framework. KPI systematically integrates structured and trusted medical knowledge into a unified disease knowledge graph, constructs clinically meaningful disease prototypes, and employs contrastive learning to enhance predictive accuracy, which is particularly important for long-tailed diseases. Additionally, KPI utilizes large language models (LLMs) to generate patient-specific, medically relevant explanations, thereby improving interpretability and reliability. Extensive experiments on real-world datasets demonstrate that KPI outperforms state-of-the-art methods in predictive accuracy and provides clinically valid explanations that closely align with patient narratives, highlighting its practical value for patient-centered healthcare delivery.