# ICU Transfer Prediction on MIMIC-IV Source: [ICU Transfer Prediction on MIMIC-IV]() Collection index: [llms.txt]() Data updated: 2026-06-17T07:01:19.492Z Evaluation of models predicting patient transfer to the Intensive Care Unit (ICU) using the MIMIC-IV clinical database, often evaluated using information-theoretic metrics like Mutual Information. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | ICU transfer prediction (ICU) | | Dataset (including any stated split) | MIMIC-IV | | Metric | MI (x10^2) | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 16 of 16 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [MI (x10^2)](): Higher is better; unit: SCALAR. ## Recorded results | Method | MI (x10^2) | Result date | Report paper | | --- | --- | --- | --- | | DeepSets | 19.24 | Not recorded | 6a322a39d33dfb23e783ec5b | | MLCI | 19.01 | Not recorded | 6a322a39d33dfb23e783ec5b | | Star-GAT | 18.89 | Not recorded | 6a322a39d33dfb23e783ec5b | | Pure MIL Attention Pooling | 18.71 | Not recorded | 6a322a39d33dfb23e783ec5b | | Set Transformer | 18.59 | Not recorded | 6a322a39d33dfb23e783ec5b | | Deep MLP Bag-of-Codes | 18.45 | Not recorded | 6a322a39d33dfb23e783ec5b | | Deep and Cross Network | 18.33 | Not recorded | 6a322a39d33dfb23e783ec5b | | Gradient Boosted Trees | 17.67 | Not recorded | 6a322a39d33dfb23e783ec5b | | FusedLogits LR | 17.6 | Not recorded | 6a322a39d33dfb23e783ec5b | | Factorization Machine | 16.99 | Not recorded | 6a322a39d33dfb23e783ec5b | | Multinomial Naive Bayes | 13.37 | Not recorded | 6a322a39d33dfb23e783ec5b | | Complement Naive Bayes | 13.26 | Not recorded | 6a322a39d33dfb23e783ec5b | | kNN | 13.06 | Not recorded | 6a322a39d33dfb23e783ec5b | | CCI+ECI | 4.86 | Not recorded | 6a322a39d33dfb23e783ec5b | | Elixhauser | 3.85 | Not recorded | 6a322a39d33dfb23e783ec5b | | Charlson | 1.99 | Not recorded | 6a322a39d33dfb23e783ec5b | ### DeepSets MI (x10^2): 19.24. Result ID: 6a324584fbc373592c2f3c24. [Reporting paper]() Recorded evaluation configuration: {"Pooling":"mean ⊕ max pool"}. This record does not assert independent reproduction. ### MLCI MI (x10^2): 19.01. Result ID: 6a324584fbc373592c2f3c25. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Star-GAT MI (x10^2): 18.89. Result ID: 6a324584fbc373592c2f3c21. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Pure MIL Attention Pooling MI (x10^2): 18.71. Result ID: 6a324584fbc373592c2f3c22. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Set Transformer MI (x10^2): 18.59. Result ID: 6a324584fbc373592c2f3c23. [Reporting paper]() Recorded evaluation configuration: {"Mode":"single-logit"}. This record does not assert independent reproduction. ### Deep MLP Bag-of-Codes MI (x10^2): 18.45. Result ID: 6a324584fbc373592c2f3c20. [Reporting paper]() Recorded evaluation configuration: {"Implementation":"EmbeddingBag"}. This record does not assert independent reproduction. ### Deep and Cross Network MI (x10^2): 18.33. Result ID: 6a324584fbc373592c2f3c1f. [Reporting paper]() Recorded evaluation configuration: {"Acronym":"DCN"}. This record does not assert independent reproduction. ### Gradient Boosted Trees MI (x10^2): 17.67. Result ID: 6a324584fbc373592c2f3c1e. [Reporting paper]() Recorded evaluation configuration: {"Evaluation":"Score/Logit"}. This record does not assert independent reproduction. ### FusedLogits LR MI (x10^2): 17.6. Result ID: 6a324584fbc373592c2f3c1c. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Factorization Machine MI (x10^2): 16.99. Result ID: 6a324584fbc373592c2f3c1d. [Reporting paper]() Recorded evaluation configuration: {"Metric":"FM score"}. This record does not assert independent reproduction. ### Multinomial Naive Bayes MI (x10^2): 13.37. Result ID: 6a324584fbc373592c2f3c1a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Complement Naive Bayes MI (x10^2): 13.26. Result ID: 6a324584fbc373592c2f3c1b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### kNN MI (x10^2): 13.06. Result ID: 6a324584fbc373592c2f3c19. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### CCI+ECI MI (x10^2): 4.86. Result ID: 6a324584fbc373592c2f3c18. [Reporting paper]() Recorded evaluation configuration: {"Mode":"scalar"}. This record does not assert independent reproduction. ### Elixhauser MI (x10^2): 3.85. Result ID: 6a324584fbc373592c2f3c17. [Reporting paper]() Recorded evaluation configuration: {"Acronym":"ECI"}. This record does not assert independent reproduction. ### Charlson MI (x10^2): 1.99. Result ID: 6a324584fbc373592c2f3c16. [Reporting paper]() Recorded evaluation configuration: {"Acronym":"CCI"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.