{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001662301,0.0001118226,0.0002186576,0.0001022704,0.0003521902,0.000133334,0.0001560603,0.00004350601,0.000002298365],"category_scores_gemma":[0.03520812,0.00009009634,0.00002486937,0.0005713678,0.00008563543,0.0002659533,0.0003679438,0.0002302409,0.00003290136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001658872,"about_ca_system_score_gemma":0.00001796567,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002356129,"about_ca_topic_score_gemma":0.00001998597,"domain_scores_codex":[0.9985301,0.000209623,0.0004437948,0.0003920476,0.0001694146,0.0002549469],"domain_scores_gemma":[0.9936104,0.005778138,0.0002508627,0.0001967239,0.00009486119,0.00006902623],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000167244,0.0001417225,0.6811616,0.0002207976,0.00009724705,0.00101182,0.01351175,0.005136422,0.002734827,0.1481719,0.002231472,0.1455638],"study_design_scores_gemma":[0.000146773,0.0008065213,0.6777446,0.0002423943,0.0000226682,0.000069782,0.001515001,0.2426887,0.002295447,0.07037979,0.003641989,0.000446319],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9658263,0.0005823577,0.0234843,0.008806119,0.0001719579,0.0004112477,7.452184e-7,0.0005607274,0.0001562599],"genre_scores_gemma":[0.9878705,0.0002422241,0.01077997,0.0005352605,0.0000469613,0.0001534453,0.000002457127,0.000008601677,0.0003606052],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2375523,"threshold_uncertainty_score":0.9729187,"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."}}