Research map / Probabilistic and scientific modeling / Causal discovery
Towards Causality-Aware Inferring: A Sequential Discriminative Approach for Medical Diagnosis
Junfan Lin, Keze Wang, Ziliang Chen, Xiaodan Liang, Liang Lin
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add intervention module (ablation) | P2A · MZ (Out.) | diagnosis success rate: 0.696 -> 0.784 | Improved |
| add intervention module (ablation) | P2A · DX (Out.) | diagnosis success rate: 0.840 -> 0.928 | Improved |
| add intervention module (ablation) | P2A · MZ (In.) | diagnosis success rate: 0.864 -> 0.888 | Improved |
| add bootstrapping diagnosers (ablation) | P2A · MZ (In.) | diagnosis success rate: 0.834 -> 0.888 | Improved |
| add bootstrapping diagnosers (ablation) | P2A · MZ (Out.) | diagnosis success rate: 0.784 -> 0.784 | No clear effect |
| add bootstrapping diagnosers (ablation) | P2A · DX (Out.) | diagnosis success rate: 0.911 -> 0.928 | Improved |
| add decision threshold (bootstrapping and intervention) (ablation) | P2A · MZ (Out.) | diagnosis success rate: 0.620 -> 0.784 | Improved |
| add decision threshold (bootstrapping and intervention) (ablation) | P2A · DX (Out.) | diagnosis success rate: 0.669 -> 0.928 | Improved |
| add intervention when training diagnosers (no inquiry) (ablation) | P2A diagnosers · MZ (In.) | diagnosis success rate: 0.935 -> 0.972 | Improved |
| add intervention when training diagnosers (no inquiry) (ablation) | P2A diagnosers · DX (In.) | diagnosis success rate: 0.971 -> 0.981 | Improved |
| use propensity latent matching instead of propensity score matching | patient simulator · MZ | Inference Ability (IA): 0.23 -> 0.62 | Improved |
| condition on all symptoms' propensity scores (vector matching) instead of per-inquiry PSM | patient simulator · DX | Inference Ability (IA): 0.27 -> 0.58 | Improved |
Closest papers by meaning
- MedExAgent: Training LLM Agents to Ask, Examine, and Diagnose in Noisy Clinical Environments (NeurIPS 2026 · similarity 0.86)
- MedTVT-R1: A Multimodal LLM Empowering Medical Reasoning and Diagnosis (CVPR 2026 · similarity 0.84)
- MedAgent-Pro: Towards Evidence-based Multi-modal Medical Diagnosis via Reasoning Agentic Workflow (ICLR 2026 · similarity 0.84)
- PatientVLM Meets DocVLM: Pre-Consultation Dialogue Between Vision-Language Models for Efficient Diagnosis (AAAI 2026 · similarity 0.84)
- DoAtlas-1: A Causal Compilation Paradigm for Clinical AI (NeurIPS 2026 · similarity 0.84)
- Simulating Viva Voce Examinations to Evaluate Clinical Reasoning in Large Language Models (NeurIPS 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
