{"id":"W4281492908","doi":"10.1097/acm.0000000000004758","title":"Development and Pilot Testing of a Data-Rich Clinical Reasoning Training and Assessment Tool","year":2022,"lang":"en","type":"article","venue":"Academic Medicine","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Formative assessment; Medical education; Computer science; Workload; Summative assessment; Psychology; Medicine; Mathematics education","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":[],"consensus_categories":[],"category_scores_codex":[0.01520464,0.001098383,0.0006361521,0.001816405,0.0005621063,0.002255181,0.004037491,0.002151659,0.003674313],"category_scores_gemma":[0.064868,0.0007189959,0.0009035187,0.0008565945,0.0008540822,0.00324363,0.002021187,0.001758947,0.001536663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008470257,"about_ca_system_score_gemma":0.002397702,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001055704,"about_ca_topic_score_gemma":0.001077996,"domain_scores_codex":[0.9905605,0.004217966,0.001433229,0.001053817,0.002304347,0.0004302346],"domain_scores_gemma":[0.9207772,0.057733,0.001726031,0.004362478,0.0132366,0.002164727],"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":[0.001639389,0.01766798,0.03726865,0.002234305,0.0003189993,0.002045134,0.008026777,0.009153134,0.03840793,0.002410903,0.01767746,0.8631493],"study_design_scores_gemma":[0.007052254,0.03980326,0.1305577,0.003571312,0.001357142,0.0102374,0.008683555,0.3745134,0.2615103,0.0117416,0.1499057,0.001066469],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5512072,0.0002425989,0.401681,0.002097262,0.0004408607,0.01822668,0.002052348,0.01907929,0.004972698],"genre_scores_gemma":[0.3207795,0.0001423525,0.6679991,0.0005718133,0.00007196862,0.005221677,0.00249905,0.0004746101,0.002239946],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01520464,"threshold_uncertainty_score":0.08041078,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3150575699023435,"score_gpt":0.4788030286876891,"score_spread":0.1637454587853456,"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."}}