{"id":"W4405166223","doi":"10.1101/2024.12.07.24318566","title":"Early identification of Family Medicine residents at risk of failure using Natural Language Processing and Explainable Artificial Intelligence","year":2024,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Artificial intelligence; Certification; Identification (biology); Computer science; Machine learning; Champion; Support vector machine; Artificial neural network; Natural language processing","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":[0.001378578,0.0005203327,0.0002749809,0.001671043,0.0002625823,0.0009996769,0.0004446295,0.0004931631,0.00173524],"category_scores_gemma":[0.008715297,0.0001871387,0.0005070886,0.0004832591,0.0002648189,0.0009586137,0.0005064037,0.0006534997,0.0003327686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008132402,"about_ca_system_score_gemma":0.0009053137,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007659298,"about_ca_topic_score_gemma":0.009043578,"domain_scores_codex":[0.9994674,0.0002221292,0.00003826987,0.0001319448,0.00009033017,0.000050009],"domain_scores_gemma":[0.9945116,0.003889516,0.0007010243,0.0001838352,0.0005971526,0.0001168875],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004753064,0.00110952,0.5220671,0.0003823086,0.0002651811,0.0006896338,0.001207344,0.1253568,0.008975677,0.001760474,0.00511555,0.332595],"study_design_scores_gemma":[0.00001665603,0.0002281405,0.08912724,0.00007426243,0.00005483439,0.0001274753,0.0004532512,0.9018689,0.004095443,0.002786057,0.001133755,0.00003401882],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8822289,0.0002624896,0.1099812,0.001636001,0.00004389613,0.0002258469,0.001201867,0.001291332,0.003128514],"genre_scores_gemma":[0.9723424,0.00006357867,0.02643141,0.00009541676,0.00001306292,0.00004993041,0.0005149826,0.00001396033,0.0004752534],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007659298,"threshold_uncertainty_score":0.0152294,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1219023059895695,"score_gpt":0.4233147165798343,"score_spread":0.3014124105902648,"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."}}