Cohort aware model improves clinical reasoning from patient records
CODA: Cohort- and Drift-aware Foundation Model for Multimodal Clinical Reasoning
Artificial IntelligenceMachine Learning
Summary
Clinical decisions often depend on understanding groups of similar patients while also noticing individual differences. The authors introduce CODA, a computer model that learns group patterns of patients and also tracks how each patient is unique. CODA uses reinforcement learning to find meaningful patient groups and models individual variations as a kind of signal that helps with better predictions. This approach helps the computer give more accurate and general results across many clinical tasks, such as answering questions and generating reports from patient data.
What this means in practice
- •For clinical data teams: Improve accuracy of automated clinical question answering and report generation by modeling patient group patterns and individual differences in EHR data.
- •For healthcare ai developers: Build smarter AI systems for clinical decision support that integrate cohort-based patient grouping with personal variation modeling.
Authors
Changshuo Liu, Jiaqi Zhu, Wenqiao Zhang, Xiaokui Xiao, Beng Chin Ooi
Abstract
Recent advances in multimodal foundation models have demonstrated strong performance across diverse clinical tasks. However, existing approaches predominantly operate at the individual sample level and fail to model the interplay between population-level cohort patterns and patient-specific variation that underlie real-world clinical reasoning. In practice, clinicians routinely reason through patient cohorts sharing similar demographic, physiological, or pathological characteristics, while accounting for patient-specific deviations from the group prototype. Motivated by this gap, we propose CODA, a cohort- and drift-aware foundation model for multimodal clinical reasoning. CODA explicitly integrates cohort structure into the modeling pipeline through two complementary mechanisms: cohort-aware population stratification and drift-aware individual adaptation. In particular, we leverage reinforcement learning to discover clinically meaningful patient cohorts, and further model each patient's deviation from cohort prototypes as a structured drift signal encoding fine-grained individual heterogeneity. These cohort- and drift-aware representations are incorporated into the foundation model to enable reasoning that is simultaneously informed by population-level patterns and sensitive to individual-level variation. Extensive experiments on real-world electronic health record (EHR) benchmarks demonstrate that CODA achieves consistent effectiveness and strong generalizability across diverse clinical tasks, including closed-QA, open-QA, and report generation.