{"id":"W2994056206","doi":"10.1097/phm.0000000000001359","title":"Evaluation of Longitudinal Assessment for Use in Maintenance of Certification","year":2019,"lang":"en","type":"article","venue":"American Journal of Physical Medicine & Rehabilitation","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Sunnybrook Health Science Centre","funders":"","keywords":"Certification; Maintenance of Certification; Medicine; Rehabilitation; Physical therapy; Physical examination; Internal medicine; Management","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":[0.0281738,0.0003765072,0.0004445287,0.00160426,0.0006580089,0.0009761922,0.0008230328,0.0004748018,0.001459789],"category_scores_gemma":[0.05597705,0.0002777358,0.000729748,0.001040625,0.0002913695,0.001070858,0.001229181,0.000708577,0.0004011818],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000931217,"about_ca_system_score_gemma":0.002414295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005407823,"about_ca_topic_score_gemma":0.005988984,"domain_scores_codex":[0.9894937,0.006743411,0.0007873204,0.000534681,0.00211971,0.0003211222],"domain_scores_gemma":[0.9590209,0.01096544,0.01509226,0.002156193,0.01039914,0.002366082],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005931036,0.000762124,0.967225,0.00005689808,0.0001304104,0.00002913837,0.0003572941,0.0001838711,0.0002691726,0.00005401055,0.0006844704,0.02965451],"study_design_scores_gemma":[0.0001183441,0.002422705,0.9944043,0.0000576789,0.00006430699,0.0000597637,0.0002217239,0.001341661,0.0003214752,0.00003486295,0.0009415274,0.00001160394],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9928941,0.0004673423,0.002383339,0.000292124,0.00008002709,0.0007113296,0.0006508785,0.0001290384,0.002391814],"genre_scores_gemma":[0.9941817,0.000175991,0.003171368,0.00007314042,0.00003574847,0.0009127591,0.0008373017,0.00001256084,0.0005993703],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0281738,"threshold_uncertainty_score":0.148999,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3580259271085565,"score_gpt":0.5333457614917764,"score_spread":0.1753198343832199,"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."}}