Research map / Probabilistic and scientific modeling / Molecules and proteins
DDXPlus: A New Dataset For Automatic Medical Diagnosis
Arsene Fansi Tchango, Rishab Goel, Zhi Wen, Julien Martel, Joumana Ghosn
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 |
|---|---|---|---|
| train to predict differential diagnosis instead of ground-truth pathology (ablation) | AARLC · DDXPlus test set | DDF1: 31.28 -> 78.24 | Improved |
| train to predict differential diagnosis instead of ground-truth pathology (ablation) | AARLC · DDXPlus test set | DDR: 21.96 -> 97.73 | Improved |
| train to predict differential diagnosis instead of ground-truth pathology (ablation) | AARLC · DDXPlus test set | PER: 32.78 -> 54.55 | Improved |
| train to predict differential diagnosis instead of ground-truth pathology (ablation) | AARLC · DDXPlus test set | IL: 6.73 -> 25.75 | Hurt |
| train to predict differential diagnosis instead of ground-truth pathology (ablation) | AARLC · DDXPlus test set | DDP: 99.19 -> 69.53 | Hurt |
| train to predict differential diagnosis instead of ground-truth pathology (ablation) | BASD · DDXPlus test set | DDF1: 31.31 -> 83.69 | Improved |
| train to predict differential diagnosis instead of ground-truth pathology (ablation) | BASD · DDXPlus test set | PER: 88.45 -> 88.18 | No clear effect |
| train to predict differential diagnosis instead of ground-truth pathology (ablation) | BASD · DDXPlus test set | GTPA@1: 97.15 -> 67.71 | Hurt |
| train to predict differential diagnosis instead of ground-truth pathology (ablation) | BASD · DDXPlus test set | IL: 17.99 -> 17.86 | No clear effect |
Closest papers by meaning
- PatientVLM Meets DocVLM: Pre-Consultation Dialogue Between Vision-Language Models for Efficient Diagnosis (AAAI 2026 · similarity 0.85)
- MedExAgent: Training LLM Agents to Ask, Examine, and Diagnose in Noisy Clinical Environments (NeurIPS 2026 · similarity 0.84)
- DDx-TRACE: A Benchmark for Medical Diagnostic Trajectories in VLMs (NeurIPS 2026 · similarity 0.84)
- RAD: Towards Trustworthy Retrieval-Augmented Multi-modal Clinical Diagnosis (NeurIPS 2025 · similarity 0.83)
- Multi-modal Medical Diagnosis via Large-small Model Collaboration (CVPR 2025 · similarity 0.83)
- Timely Clinical Diagnosis through Active Test Selection (NeurIPS 2025 · similarity 0.83)
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.
