Enabling Patient-side Disease Prediction via the Integration of Patient Narratives

TL;DR

This work tackles early disease prediction from patient narratives rather than laboratory data, addressing access and timeliness barriers in clinical workflows. It introduces PoMP, a model with separate encoders for textual descriptions and demographics that uses a two-tier hierarchical classifier to predict disease category and then the specific disease. Evaluated on the Haodf-based dataset of patient-doctor consultations, PoMP delivers state-of-the-art performance in most scenarios and demonstrates the added value of incorporating demographic information through ablation studies. By providing a public dataset and code, the paper advances patient-centered triage and lays a foundation for future research in patient-side disease prediction.

Abstract

Disease prediction holds considerable significance in modern healthcare, because of its crucial role in facilitating early intervention and implementing effective prevention measures. However, most recent disease prediction approaches heavily rely on laboratory test outcomes (e.g., blood tests and medical imaging from X-rays). Gaining access to such data for precise disease prediction is often a complex task from the standpoint of a patient and is always only available post-patient consultation. To make disease prediction available from patient-side, we propose Personalized Medical Disease Prediction (PoMP), which predicts diseases using patient health narratives including textual descriptions and demographic information. By applying PoMP, patients can gain a clearer comprehension of their conditions, empowering them to directly seek appropriate medical specialists and thereby reducing the time spent navigating healthcare communication to locate suitable doctors. We conducted extensive experiments using real-world data from Haodf to showcase the effectiveness of PoMP.

Figures (1)

• Figure 1: Distribution of patient demographics across six categories.