{"id":"W4401173939","doi":"10.3390/bioengineering11080770","title":"An Unsupervised Error Detection Methodology for Detecting Mislabels in Healthcare Analytics","year":2024,"lang":"en","type":"article","venue":"Bioengineering","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Interpretability; Computer science; Cluster analysis; Unsupervised learning; Artificial intelligence; Data mining; Reliability (semiconductor); Machine learning; Pattern recognition (psychology)","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":[0.006273373,0.001255984,0.001347215,0.005542808,0.001612013,0.002136458,0.002702006,0.001658275,0.0006301302],"category_scores_gemma":[0.02675494,0.0005083939,0.001352789,0.003563581,0.001172491,0.002182591,0.001951932,0.002105814,0.0006299789],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001131451,"about_ca_system_score_gemma":0.002960874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003417792,"about_ca_topic_score_gemma":0.005448742,"domain_scores_codex":[0.9919003,0.001608669,0.001063113,0.002342421,0.002796097,0.0002893168],"domain_scores_gemma":[0.9762428,0.009050407,0.00444141,0.003545255,0.006383717,0.0003363872],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004405698,0.0006046203,0.04390409,0.0003852813,0.0004324231,0.0004647991,0.001014494,0.04926596,0.02355877,0.007813861,0.007197748,0.8649173],"study_design_scores_gemma":[0.00005706089,0.0002407863,0.01312481,0.0001215265,0.0001162545,0.0009270399,0.0002810069,0.9063808,0.05430343,0.01668658,0.007644919,0.0001157127],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02264465,0.0002453249,0.9739424,0.000240362,0.00007809063,0.0002570128,0.0002666306,0.00179569,0.0005298361],"genre_scores_gemma":[0.2311249,0.0001863041,0.765297,0.0002623506,0.00009592915,0.0003753581,0.0009664835,0.0002014086,0.001490152],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006273373,"threshold_uncertainty_score":0.0331772,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3677459445365586,"score_gpt":0.5273353419595005,"score_spread":0.1595893974229419,"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."}}