{"id":"W4401548587","doi":"10.1177/10711813241260676","title":"Evaluating Active Learning Strategies for Automated Classification of Patient Safety Event Reports in Hospitals","year":2024,"lang":"en","type":"article","venue":"Proceedings of the Human Factors and Ergonomics Society Annual Meeting","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Agency for Healthcare Research and Quality","keywords":"Workload; Computer science; Annotation; Machine learning; Artificial intelligence; Process (computing); Event (particle physics)","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":[0.008576354,0.001514169,0.0009381227,0.001631318,0.0006420834,0.001549595,0.002299618,0.001864661,0.0009208267],"category_scores_gemma":[0.02479524,0.0004508576,0.0007095382,0.001002665,0.0008174898,0.002385827,0.001268857,0.001520015,0.0005037985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001495274,"about_ca_system_score_gemma":0.001228723,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007439145,"about_ca_topic_score_gemma":0.006947215,"domain_scores_codex":[0.9956884,0.002336015,0.0003936304,0.0008554272,0.0005013752,0.0002251951],"domain_scores_gemma":[0.9704334,0.02372125,0.001228414,0.001408525,0.00262047,0.0005878769],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003848711,0.005714898,0.03383255,0.0005408674,0.0003937672,0.0001172081,0.000595121,0.3191572,0.01019332,0.001377363,0.005298444,0.6189305],"study_design_scores_gemma":[0.00007344824,0.0005845086,0.001818058,0.000011737,0.00003294829,0.00001839399,0.0001106239,0.9922065,0.004166179,0.0006589797,0.0003067368,0.00001177031],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8770232,0.001522794,0.1141656,0.001036709,0.000237409,0.0005610258,0.0005865722,0.002502449,0.002364263],"genre_scores_gemma":[0.9433522,0.0001984892,0.05381291,0.0002610985,0.00008862909,0.0002056581,0.001054334,0.00005201076,0.0009747755],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008576354,"threshold_uncertainty_score":0.04535663,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0168930833551049,"score_gpt":0.299991809120692,"score_spread":0.2830987257655871,"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."}}