# Length of stay prediction (LOS) on MIMIC-III Source: [Length of stay prediction (LOS) on MIMIC-III]() Collection index: [llms.txt]() Data updated: 2026-06-17T07:01:19.608Z Evaluation of models predicting patient Length of Stay (LOS) using the MIMIC-III clinical database, specifically measured using Mutual Information (MI). 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 | Length of stay prediction (LOS) | | Dataset (including any stated split) | MIMIC-III | | Metric | Mutual Information (MI) | | 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 - [Mutual Information (MI)](): Higher is better; unit: SCALAR. ## Recorded results | Method | Mutual Information (MI) | Result date | Report paper | | --- | --- | --- | --- | | MLCI | 0.1645 | Not recorded | 6a322a39d33dfb23e783ec5b | | DeepSets | 0.1517 | Not recorded | 6a322a39d33dfb23e783ec5b | | Gradient Boosted Trees | 0.1476 | Not recorded | 6a322a39d33dfb23e783ec5b | | Set Transformer | 0.1454 | Not recorded | 6a322a39d33dfb23e783ec5b | | Pure MIL Attention Pooling | 0.1432 | Not recorded | 6a322a39d33dfb23e783ec5b | | Star-GAT | 0.141 | Not recorded | 6a322a39d33dfb23e783ec5b | | Deep MLP Bag-of-Codes | 0.1383 | Not recorded | 6a322a39d33dfb23e783ec5b | | Factorization Machine | 0.1362 | Not recorded | 6a322a39d33dfb23e783ec5b | | Deep and Cross Network | 0.1347 | Not recorded | 6a322a39d33dfb23e783ec5b | | FusedLogits LR | 0.1325 | Not recorded | 6a322a39d33dfb23e783ec5b | | kNN | 0.0855 | Not recorded | 6a322a39d33dfb23e783ec5b | | Multinomial Naive Bayes | 0.0727 | Not recorded | 6a322a39d33dfb23e783ec5b | | Complement Naive Bayes | 0.0712 | Not recorded | 6a322a39d33dfb23e783ec5b | | CCI+ECI | 0.034 | Not recorded | 6a322a39d33dfb23e783ec5b | | Elixhauser | 0.0314 | Not recorded | 6a322a39d33dfb23e783ec5b | | Charlson | 0.0094 | Not recorded | 6a322a39d33dfb23e783ec5b | ### MLCI Mutual Information (MI): 0.1645. Result ID: 6a324584fbc373592c2f3c55. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### DeepSets Mutual Information (MI): 0.1517. Result ID: 6a324584fbc373592c2f3c54. [Reporting paper]() Recorded evaluation configuration: {"Pooling":"mean ⊕ max pool"}. This record does not assert independent reproduction. ### Gradient Boosted Trees Mutual Information (MI): 0.1476. Result ID: 6a324584fbc373592c2f3c4e. [Reporting paper]() Recorded evaluation configuration: {"Evaluation":"Score/Logit"}. This record does not assert independent reproduction. ### Set Transformer Mutual Information (MI): 0.1454. Result ID: 6a324584fbc373592c2f3c53. [Reporting paper]() Recorded evaluation configuration: {"Mode":"single-logit"}. This record does not assert independent reproduction. ### Pure MIL Attention Pooling Mutual Information (MI): 0.1432. Result ID: 6a324584fbc373592c2f3c52. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Star-GAT Mutual Information (MI): 0.141. Result ID: 6a324584fbc373592c2f3c51. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Deep MLP Bag-of-Codes Mutual Information (MI): 0.1383. Result ID: 6a324584fbc373592c2f3c50. [Reporting paper]() Recorded evaluation configuration: {"Implementation":"EmbeddingBag"}. This record does not assert independent reproduction. ### Factorization Machine Mutual Information (MI): 0.1362. Result ID: 6a324584fbc373592c2f3c4d. [Reporting paper]() Recorded evaluation configuration: {"Metric":"FM score"}. This record does not assert independent reproduction. ### Deep and Cross Network Mutual Information (MI): 0.1347. Result ID: 6a324584fbc373592c2f3c4f. [Reporting paper]() Recorded evaluation configuration: {"Acronym":"DCN"}. This record does not assert independent reproduction. ### FusedLogits LR Mutual Information (MI): 0.1325. Result ID: 6a324584fbc373592c2f3c4c. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### kNN Mutual Information (MI): 0.0855. Result ID: 6a324584fbc373592c2f3c49. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Multinomial Naive Bayes Mutual Information (MI): 0.0727. Result ID: 6a324584fbc373592c2f3c4a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Complement Naive Bayes Mutual Information (MI): 0.0712. Result ID: 6a324584fbc373592c2f3c4b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### CCI+ECI Mutual Information (MI): 0.034. Result ID: 6a324584fbc373592c2f3c48. [Reporting paper]() Recorded evaluation configuration: {"Mode":"scalar"}. This record does not assert independent reproduction. ### Elixhauser Mutual Information (MI): 0.0314. Result ID: 6a324584fbc373592c2f3c47. [Reporting paper]() Recorded evaluation configuration: {"Acronym":"ECI"}. This record does not assert independent reproduction. ### Charlson Mutual Information (MI): 0.0094. Result ID: 6a324584fbc373592c2f3c46. [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.