{"id":"W2793870071","doi":"10.1007/s40037-018-0410-4","title":"i-Assess: Evaluating the impact of electronic data capture for OSCE","year":2018,"lang":"en","type":"article","venue":"Perspectives on Medical Education","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; McMaster University; Impact","funders":"","keywords":"Cronbach's alpha; Generalizability theory; Rasch model; Reliability (semiconductor); Modality (human–computer interaction); Internal consistency; Inter-rater reliability; Medicine; Repeated measures design; Post hoc; Rating scale; Post-hoc analysis; Kappa; Statistics; Physical therapy; Psychology; Clinical psychology; Psychometrics; Mathematics; Artificial intelligence; Computer science; Internal 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03105211,0.0008167035,0.0008988879,0.002016611,0.000456097,0.001956323,0.001315252,0.000776033,0.004754897],"category_scores_gemma":[0.1296503,0.0004703386,0.001835043,0.001258722,0.0006258765,0.001669992,0.00228376,0.0007712744,0.0006932975],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001023166,"about_ca_system_score_gemma":0.001282741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007677265,"about_ca_topic_score_gemma":0.001380253,"domain_scores_codex":[0.9705255,0.01646888,0.003017368,0.001681095,0.007744819,0.0005624479],"domain_scores_gemma":[0.8466902,0.1172494,0.01696614,0.007268473,0.008699397,0.003126304],"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":[0.03834789,0.006682603,0.4428149,0.00529824,0.002526669,0.0001406204,0.004718594,0.002407798,0.01231067,0.0008370969,0.004810723,0.4791042],"study_design_scores_gemma":[0.002113711,0.07571767,0.8928856,0.0008689244,0.002269386,0.0004998343,0.002366527,0.005560967,0.01034089,0.0004898596,0.006681261,0.0002054795],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.978696,0.0008183133,0.008011889,0.0003402618,0.00009378811,0.003191633,0.001365629,0.00035238,0.007130061],"genre_scores_gemma":[0.9595904,0.0007494254,0.03207013,0.000247418,0.0001286945,0.004118229,0.001508002,0.00009188963,0.001495779],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03105211,"threshold_uncertainty_score":0.1642212,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.60814605761424,"score_gpt":0.6509570250056883,"score_spread":0.0428109673914483,"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."}}