{"id":"W4399462990","doi":"10.2196/52896","title":"Unsupervised Feature Selection to Identify Important ICD-10 and ATC Codes for Machine Learning on a Cohort of Patients With Coronary Heart Disease: Retrospective Study","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Medical Coding and Health Information","field":"Health Professions","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Feature selection; Autoencoder; Artificial intelligence; Computer science; Overfitting; Machine learning; Feature (linguistics); Unsupervised learning; Pattern recognition (psychology); Data mining; Artificial neural network","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001939617,0.00042293,0.0005977078,0.001352232,0.0005234009,0.0004648243,0.0007291357,0.0005043614,0.0006419586],"category_scores_gemma":[0.0059386,0.000232072,0.0009103175,0.001245747,0.0004612564,0.0003684136,0.0004405784,0.0005481837,0.0001870017],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007618346,"about_ca_system_score_gemma":0.001135995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01714858,"about_ca_topic_score_gemma":0.01899835,"domain_scores_codex":[0.998697,0.0003533182,0.0001138477,0.0003350239,0.0003407716,0.0001601857],"domain_scores_gemma":[0.9954929,0.001146583,0.001102209,0.000712638,0.00116307,0.0003824493],"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":[0.000222673,0.000071139,0.9971032,0.000007055185,0.00007602005,0.0000797394,0.00006704736,0.0001719814,0.0002763219,0.00001448155,0.0001766769,0.001733728],"study_design_scores_gemma":[0.00001828829,0.0001980724,0.9961599,0.000005568566,0.00006456728,0.0003096836,0.0001531762,0.002638851,0.0002098078,0.0000367319,0.0001955307,0.000009688847],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9989448,0.00007527971,0.0005476404,0.00001372973,0.000003343728,0.0000258372,0.0003069065,0.0000055603,0.00007687524],"genre_scores_gemma":[0.9981331,0.00004924956,0.0006147175,0.00001572414,0.000008988218,0.00003429767,0.001062802,0.00000558532,0.00007553627],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01714858,"threshold_uncertainty_score":0.03409755,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04065006443302908,"score_gpt":0.4207781042163397,"score_spread":0.3801280397833106,"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."}}