DoAtlas-1: A Causal Compilation Paradigm for Clinical AI
This addresses the need for auditable and verifiable causal reasoning in clinical AI, representing a new paradigm rather than an incremental improvement.
The paper tackled the problem of medical foundation models lacking the ability to quantify intervention effects or validate claims by proposing causal compilation, a paradigm that transforms narrative medical evidence into executable code, resulting in DoAtlas-1 with 98.5% canonicalization accuracy and 80.5% query executability from 1,445 effect kernels.
Medical foundation models generate narrative explanations but cannot quantify intervention effects, detect evidence conflicts, or validate literature claims, limiting clinical auditability. We propose causal compilation, a paradigm that transforms medical evidence from narrative text into executable code. The paradigm standardizes heterogeneous research evidence into structured estimand objects, each explicitly specifying intervention contrast, effect scale, time horizon, and target population, supporting six executable causal queries: do-calculus, counterfactual reasoning, temporal trajectories, heterogeneous effects, mechanistic decomposition, and joint interventions. We instantiate this paradigm in DoAtlas-1, compiling 1,445 effect kernels from 754 studies through effect standardization, conflict-aware graph construction, and real-world validation (Human Phenotype Project, 10,000 participants). The system achieves 98.5% canonicalization accuracy and 80.5% query executability. This paradigm shifts medical AI from text generation to executable, auditable, and verifiable causal reasoning.