{"id":"W2892005286","doi":"10.23889/ijpds.v3i4.840","title":"Machine learning: how much does it improve the prediction of unplanned hospital admissions?","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Logistic regression; Machine learning; Decision tree; Random forest; Predictive modelling; Primary care; Medical record; Artificial intelligence; Lasso (programming language); Medicine; Computer science; Family medicine","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.01330373,0.00134442,0.001250683,0.001294673,0.0004068912,0.00372269,0.001776894,0.001994463,0.008890629],"category_scores_gemma":[0.05377864,0.0002778206,0.001096545,0.001440473,0.001227899,0.003769799,0.001019772,0.002823666,0.002309139],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001547031,"about_ca_system_score_gemma":0.001551667,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005986183,"about_ca_topic_score_gemma":0.003984718,"domain_scores_codex":[0.9938385,0.003861833,0.0002010989,0.0006577825,0.001203764,0.0002370383],"domain_scores_gemma":[0.9732733,0.02001237,0.001420428,0.001452614,0.003209061,0.0006320556],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000812572,0.0003081983,0.05282079,0.0009526961,0.0008867604,0.00004902827,0.0001428132,0.02191776,0.0002656598,0.01212091,0.07886101,0.8308617],"study_design_scores_gemma":[0.0005687221,0.002177805,0.07337119,0.007701824,0.001231987,0.000264,0.0008758198,0.5192029,0.004185248,0.2461127,0.1439185,0.0003893865],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.1311893,0.2358041,0.1594138,0.397942,0.01405703,0.0003077279,0.006279855,0.003062021,0.05194419],"genre_scores_gemma":[0.7794524,0.06821582,0.09779772,0.02505255,0.01349074,0.0002227131,0.003738962,0.0005716515,0.01145742],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01330373,"threshold_uncertainty_score":0.07035768,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04399816139798792,"score_gpt":0.3665846899376288,"score_spread":0.3225865285396409,"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."}}