{"id":"W2900910515","doi":"10.1186/s12918-018-0624-4","title":"An interpretable boosting model to predict side effects of analgesics for osteoarthritis","year":2018,"lang":"en","type":"article","venue":"BMC Systems Biology","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":59,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"National Institutes of Health; National Natural Science Foundation of China","keywords":"Interpretability; Machine learning; Artificial intelligence; Osteoarthritis; Medicine; Boosting (machine learning); Predictive modelling; Computer science; Medical record; Internal medicine; Alternative 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006604627,0.0001430366,0.0003533268,0.0001367303,0.0001122563,0.00003815302,0.0007783662,0.0001420788,5.50942e-7],"category_scores_gemma":[0.000749545,0.0001319925,0.00005288704,0.0002058289,0.0000574893,0.0001308416,0.0001871387,0.00009173981,0.00001026502],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004012495,"about_ca_system_score_gemma":0.0001317354,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005564819,"about_ca_topic_score_gemma":0.000182569,"domain_scores_codex":[0.9982117,0.0003889941,0.000415151,0.0004914465,0.00009497412,0.0003977619],"domain_scores_gemma":[0.998037,0.0006489707,0.0001985228,0.0006976348,0.0002699276,0.0001479621],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003705252,0.0002206879,0.3835484,0.00813657,0.000114802,0.00001224317,0.01188591,0.06566413,0.1120626,0.2365438,0.001397843,0.1800424],"study_design_scores_gemma":[0.0003471865,0.003143613,0.001660509,0.0002930469,0.000005375411,0.00001874794,0.00002522836,0.9916502,0.001600076,0.0006539593,0.0004526608,0.0001493666],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1612091,0.0003039794,0.8359575,0.00005248655,0.001148153,0.0008317651,0.00001652387,0.0001430362,0.0003375174],"genre_scores_gemma":[0.9271202,9.772563e-7,0.07218194,0.0001335079,0.0003213373,0.0001572297,0.000007157241,0.00001492625,0.00006274154],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9259861,"threshold_uncertainty_score":0.5382497,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02334702948595664,"score_gpt":0.3211614191044852,"score_spread":0.2978143896185286,"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."}}