Research map / Probabilistic and scientific modeling / Treatment effects
OrganITE: Optimal transplant donor organ offering using an individual treatment effect
Jeroen Berrevoets, James Jordon, Ioana Bica, alexander 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 |
|---|---|---|---|
| add organ-rarity and distance terms (OrganITE) to ITE-based policy (IS) | incremental survival policy · Synthetic, ITE model | population life years: 111228 -> 112359 | Improved |
| add organ-rarity and distance terms (OrganITE) vs IS | incremental survival policy · Real data, NN CF | population life years: 102303 -> 108217 | Improved |
| add organ-rarity and distance terms vs IS | incremental survival policy · Real data, TB CF | population life years: 101585 -> 102773 | Improved |
| use ITE-based policies (BM, IS) instead of queue-based FIFO | FIFO · Synthetic, ITE model | population life years: 83509 -> 111228 | Improved |
| use OrganITE ITE model vs linear TransplantBenefit outcome model | OrganITE policy · Synthetic | population life years: 106392 (TB) -> 112359 (ITE model) | Improved |
| add domain-adversarial balancing (gamma 0 -> 0.15) | padded ITE network, 15 clusters · synthetic ITE | NRMSE: 0.1845 -> 0.1550 | Improved |
| use padded network instead of siamese network (ablation) | ITE network, 15 clusters · synthetic ITE | NRMSE: 0.2345 -> 0.1550 | Improved |
| use padded network instead of two separate networks (ablation) | ITE network, 15 clusters · synthetic ITE | NRMSE: 0.2730 -> 0.1550 | Improved |
| OrganITE ITE model vs ConfidentMatch two models | ITE estimator · synthetic ITE | NRMSE: 0.6372 -> 0.1550 | Improved |
| use 15 clusters instead of 7 for propensity balancing (ablation) | padded ITE network gamma=0.15 · synthetic ITE | NRMSE: 0.1837 -> 0.1550 | Improved |
| make organs rarer (lower temperature tau) for OrganITE vs other prediction policies (ablation) | OrganITE · synthetic, temperature sweep | population life years | Improved |
Later papers that compared with this method
1 later accepted paper reports OrganITE as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Learning Queueing Policies for Organ Transplantation Allocation using Interpretable Counterfactual Survival Analysis (ICML 2021 · better on 7 of 10 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Learning Queueing Policies for Organ Transplantation Allocation using Interpretable Counterfactual Survival Analysis (ICML 2021 · similarity 0.89)
- Adapting a Kidney Exchange Algorithm to Align With Human Values (AAAI 2018 · similarity 0.86)
- Causal Explanation-Guided Learning for Organ Allocation (NeurIPS 2025 · similarity 0.86)
- Closing the loop in medical decision support by understanding clinical decision-making: A case study on organ transplantation (NeurIPS 2021 · similarity 0.85)
- Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation? (NeurIPS 2024 · similarity 0.79)
- Towards Generalizable Tumor Synthesis (CVPR 2024 · similarity 0.78)
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.
