{"id":"W4367319158","doi":"10.2196/47995","title":"Reporting and Methodological Observations on Prognostic and Diagnostic Machine Learning Studies","year":2023,"lang":"en","type":"article","venue":"JMIR AI","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Agricultural Research Institute of Ontario; University of Ottawa","funders":"","keywords":"Key (lock); Data science; Artificial intelligence; Computer science; Psychology; Machine learning","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":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5915914,0.001521748,0.002910862,0.02505689,0.00341943,0.01476937,0.006656998,0.0049384,0.003440621],"category_scores_gemma":[0.9148299,0.00204446,0.003928684,0.02289507,0.009187081,0.008531571,0.009486941,0.006616355,0.001044317],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.009715016,"about_ca_system_score_gemma":0.01791679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006309848,"about_ca_topic_score_gemma":0.00627398,"domain_scores_codex":[0.2050631,0.3450111,0.3109723,0.02138146,0.1133028,0.004269291],"domain_scores_gemma":[0.03306918,0.7341167,0.08930346,0.02997465,0.1117026,0.001833512],"domain_codex":"methods","domain_gemma":"reporting","domain_candidate":"reporting","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.003573426,0.0001233382,0.03886975,0.1720931,0.01145478,0.0006717465,0.02732902,0.0009167201,0.002688388,0.03858181,0.3243979,0.3793],"study_design_scores_gemma":[0.001918162,0.0007067969,0.05884064,0.2306553,0.01151095,0.001771798,0.01467468,0.00229445,0.006928315,0.05864503,0.6109712,0.001082615],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.0232594,0.4892308,0.04302958,0.3334964,0.06961022,0.005590254,0.01427195,0.0007013882,0.02081007],"genre_scores_gemma":[0.3725073,0.2359252,0.08519226,0.1768915,0.08622336,0.02434654,0.01221015,0.002358929,0.004344748],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4084086,"threshold_uncertainty_score":0.5036407,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3717432222961256,"score_gpt":0.4492624438026238,"score_spread":0.0775192215064982,"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."}}