Towards Trustworthy Medical Diagnosis via Causal Machine Learning and Graph Neural Networks (Malaysia)

Modern clinical decision-making is constrained by associative models that conflate correlation with causation and overlook interactions among patient factors. This project introduces a unified framework that fuses causal inference with graph neural networks to deliver interpretable, high-precision diagnosis. Using electronic health records, Double Machine Learning isolates causal drivers (e.g., treatment effects, biomarkers) from spurious associations while adjusting for confounders such as socioeconomic status. Causally screened features flow into a temporal GNN that captures nonlinear relations across evolving histories and comorbidities. Fairness is built in: subgroup accuracy and calibration are audited, uncertainty is reported, and counterfactual explanations are provided.  This project is supported by an NVIDIA hardware grant.