Research map / Learning theory and algorithms / Prediction and decision losses
Closing the loop in medical decision support by understanding clinical decision-making: A case study on organ transplantation
Yuchao Qin, Fergus Imrie, Alihan Hüyük, Daniel Jarrett, Alexander Edward Gimson, Mihaela van der Schaar
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 |
|---|---|---|---|
| use individualized policies instead of global logistic regression | iTransplant · OPTN liver offers | AUC-ROC: 0.794 -> 0.895 | Improved |
| use individualized policies instead of per-cluster logistic regression | iTransplant · OPTN liver offers | AUC-PRC: 0.352 -> 0.502 | Improved |
| use iTransplant instead of behavioral cloning (black box) | iTransplant · OPTN liver offers | AUC-ROC: 0.899 -> 0.895 | No clear effect |
| use iTransplant instead of behavioral cloning (black box) | iTransplant · OPTN liver offers | log-likelihood: -0.383 -> -0.396 | Hurt |
| use iTransplant instead of locally weighted regression | iTransplant · OPTN liver offers | log-likelihood: -0.256 -> -0.396 | Hurt |
| use iTransplant instead of random forest | iTransplant · OPTN liver offers | AUC-ROC: 0.852 -> 0.895 | Improved |
| use iTransplant instead of INVASE | iTransplant · OPTN liver offers | AUC-ROC: 0.790 -> 0.895 | Improved |
| use iTransplant interpretation instead of post-hoc LIME on BC | iTransplant · interpretation consistency | consistency: 46.8% -> 85.0% | Improved |
| use iTransplant interpretation instead of post-hoc LIME on INVASE | iTransplant · interpretation consistency | consistency: 41.7% -> 85.0% | Improved |
| ignore low-weight match criteria (ablation) | iTransplant · average precision | average precision: no more than 0.1% loss | No clear effect |
| per-cluster decision tree instead of global decision tree | decision tree · OPTN liver offers | AUC-ROC: 0.775 -> 0.773 | No clear effect |
Closest papers by meaning
- OrganITE: Optimal transplant donor organ offering using an individual treatment effect (NeurIPS 2020 · similarity 0.85)
- MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making (NeurIPS 2024 · similarity 0.81)
- Diagnosing Transformers: Illuminating Feature Spaces for Clinical Decision-Making (ICLR 2024 · similarity 0.81)
- Contextualized Policy Recovery: Modeling and Interpreting Medical Decisions with Adaptive Imitation Learning (ICML 2024 · similarity 0.80)
- MedChain: Bridging the Gap Between LLM Agents and Clinical Practice with Interactive Sequence (NeurIPS 2025 · similarity 0.80)
- MTBBench: A Multimodal Sequential Clinical Decision-Making Benchmark in Oncology (NeurIPS 2025 · similarity 0.80)
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.
