PerCaM-Health: Personalized Dynamic Causal Graphs for Healthcare Reasoning

2026-05-08

AI Summary

Existing causal discovery methods struggle to construct stable and personalized dynamic causal graphs from short, noisy, irregular, and non-stationary individual health time-series data, resulting in population-level models that lack individual adaptability and purely individual models that suffer from instability. This work proposes PerCaM-Health, a novel framework that jointly models personalization and temporal evolution for the first time: it first learns a population-level temporal causal graph guided by domain knowledge, then conservatively evolves this graph by integrating patient-specific evidence within a rolling window to generate an interpretable and auditable sequence of personalized dynamic causal graphs. The framework further supports counterfactual intervention reasoning at the individual level. Evaluated on a semi-synthetic dynamic health benchmark, PerCaM-Health significantly outperforms population-based, individual-only, and non-personalized temporal baselines, achieving consistent improvements in causal graph recovery accuracy, dynamic edge tracking, and intervention effect prediction.

Abstract

Personalized healthcare decisions require reasoning about how physiological and behavioral variables influence an individual patient over time. Existing temporal causal discovery methods are poorly matched to this setting: cohort-level models provide stable but non-personalized structures, while per-patient discovery is unreliable because individual trajectories are short, noisy, irregular, and non-stationary. This creates a fundamental gap between population-level causal modeling and the patient-specific, time-varying mechanisms needed for intervention reasoning. We introduce PerCaM-Health, a framework for learning personalized dynamic causal graphs from longitudinal health data. The framework learns a knowledge-guided population temporal graph, then conservatively adapts and evolves it using patient-specific temporal evidence and rolling-window updates, producing interpretable and auditable graph sequences. By coupling these graphs with temporal structural equations, the framework enables patient-level counterfactual queries, such as estimating short-horizon outcome changes under hypothetical behavioral interventions. Experiments on a semi-synthetic dynamic health benchmark show that PerCaM-Health improves graph recovery, dynamic edge tracking, and intervention direction accuracy compared to cohort-level, per-patient, and non-personalized temporal baselines. These results demonstrate that jointly modeling personalization and temporal evolution yields more reliable causal structure and intervention reasoning.

Problem

• personalized healthcare
• temporal causal discovery
• dynamic causal graphs
• intervention reasoning
• longitudinal health data

Innovation

• personalized causal discovery
• dynamic causal graphs
• temporal structural equations
• counterfactual reasoning
• longitudinal health data