{"id":"W4322216946","doi":"10.1101/2023.02.21.23286247","title":"Improving Clinical Decision Making with a Two-Stage Recommender System: A Case Study on MIMIC-III Dataset","year":2023,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Recommender system; Context (archaeology); Artificial intelligence; Machine learning; Field (mathematics); Clinical decision support system; Task (project management); Baseline (sea); Medical prescription; Medical record; Health care; Data science; Decision support system; Medicine","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005070543,0.001004585,0.0009638077,0.001252867,0.0007184825,0.001191275,0.001603843,0.002253127,0.001500649],"category_scores_gemma":[0.01331368,0.0002521754,0.0008996589,0.001299593,0.0004199879,0.001036093,0.0006729362,0.001312083,0.000692224],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001616706,"about_ca_system_score_gemma":0.001819312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0370874,"about_ca_topic_score_gemma":0.06748109,"domain_scores_codex":[0.9970505,0.001503381,0.0002991184,0.000508883,0.0004964684,0.0001415958],"domain_scores_gemma":[0.9896619,0.007092645,0.0003521762,0.001235039,0.001188842,0.0004693987],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004533528,0.007209444,0.2269402,0.001993686,0.001626535,0.00599888,0.001162458,0.1991645,0.00983497,0.002941581,0.1508804,0.3877138],"study_design_scores_gemma":[0.001214522,0.001759108,0.07451593,0.0002287813,0.0004536988,0.001591914,0.001343756,0.872361,0.01043573,0.003549727,0.03231114,0.0002347275],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.9439387,0.004360885,0.01737959,0.006977879,0.0004897609,0.0006275325,0.01911777,0.002207227,0.004900714],"genre_scores_gemma":[0.8957295,0.0008359688,0.06670658,0.001434279,0.0002154605,0.0002283685,0.03192845,0.00007460027,0.00284684],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.0370874,"threshold_uncertainty_score":0.07374305,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1459179298159615,"score_gpt":0.4448747252368436,"score_spread":0.2989567954208821,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}