{"id":"W4225264631","doi":"10.2196/37239","title":"A Framework for Modeling and Interpreting Patient Subgroups Applied to Hospital Readmission: Visual Analytical Approach","year":2022,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; Patient-Centered Outcomes Research Institute; U.S. National Library of Medicine; National Institute on Aging; National Institutes of Health; University of Texas MD Anderson Cancer Center","keywords":"Medicine; Logistic regression; COPD; Interpretability; Medicaid; Internal medicine; Intensive care medicine; Psychological intervention; Emergency medicine; Physical therapy; Machine learning; Health care; Computer science","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008576764,0.0001752425,0.0002789359,0.000147866,0.0003882797,0.0001296354,0.0007469052,0.0001364915,0.00003485745],"category_scores_gemma":[0.0007305123,0.0001563241,0.0000598558,0.0004173559,0.00003611148,0.000165468,0.001705831,0.0009903664,0.000004769716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001099356,"about_ca_system_score_gemma":0.0001682495,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006359138,"about_ca_topic_score_gemma":1.641478e-7,"domain_scores_codex":[0.9973633,0.0000676714,0.000723629,0.0002618906,0.001134886,0.0004485999],"domain_scores_gemma":[0.998382,0.0003610426,0.0001506176,0.0003542874,0.00006502388,0.0006870214],"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":[0.0001475257,0.0005294046,0.0008569818,0.0009839117,0.00005153859,0.00001444271,0.1975035,0.02197658,0.000001084314,0.3380797,0.002722912,0.4371324],"study_design_scores_gemma":[0.0001989742,0.0005991728,0.00001752226,0.00006559942,0.000003470608,0.00002409332,0.005441988,0.9895256,0.000001151576,0.002001877,0.001921325,0.0001991959],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1318077,0.00001480478,0.8638936,0.002492778,0.0002170536,0.0007667355,0.000003372747,0.0001600282,0.0006438789],"genre_scores_gemma":[0.7056984,0.000001023246,0.2903402,0.003435313,0.0000673151,0.0004286559,0.00001283431,0.00001166628,0.000004591911],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.967549,"threshold_uncertainty_score":0.637471,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01794598250685179,"score_gpt":0.3306488185323535,"score_spread":0.3127028360255017,"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."}}