CohortNet: Empowering Cohort Discovery for Interpretable Healthcare Analytics

TL;DR

CohortNet is a novel interpretable model that automates cohort discovery in healthcare, enabling meaningful patient subgroup identification and analysis without manual pattern definition, thus enhancing healthcare analytics.

Contribution

The paper introduces CohortNet, a new method for automated, interpretable cohort discovery that effectively captures medically relevant patient patterns and improves upon existing approaches.

Findings

Outperforms state-of-the-art methods on three real-world datasets.

Provides interpretable cohort insights from multiple perspectives.

Effectively identifies meaningful patient cohorts with concrete patterns.

Abstract

Cohort studies are of significant importance in the field of healthcare analysis. However, existing methods typically involve manual, labor-intensive, and expert-driven pattern definitions or rely on simplistic clustering techniques that lack medical relevance. Automating cohort studies with interpretable patterns has great potential to facilitate healthcare analysis but remains an unmet need in prior research efforts. In this paper, we propose a cohort auto-discovery model, CohortNet, for interpretable healthcare analysis, focusing on the effective identification, representation, and exploitation of cohorts characterized by medically meaningful patterns. CohortNet initially learns fine-grained patient representations by separately processing each feature, considering both individual feature trends and feature interactions at each time step. Subsequently, it classifies each feature into distinct states and employs a heuristic cohort exploration strategy to effectively discover substantial cohorts with concrete patterns. For each identified cohort, it learns comprehensive cohort representations with credible evidence through associated patient retrieval. Ultimately, given a new patient, CohortNet can leverage relevant cohorts with distinguished importance, which can provide a more holistic understanding of the patient's conditions. Extensive experiments on three real-world datasets demonstrate that it consistently outperforms state-of-the-art approaches and offers interpretable insights from diverse perspectives in a top-down fashion.