{"id":"W4206829205","doi":"10.1109/access.2021.3133700","title":"A Machine Learning Analysis of Health Records of Patients With Chronic Kidney Disease at Risk of Cardiovascular Disease","year":2021,"lang":"en","type":"article","venue":"IEEE Access","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Kidney disease; Medicine; Context (archaeology); Disease; Diabetes mellitus; Medical record; Renal function; Ranking (information retrieval); Feature (linguistics); Term (time); Artificial intelligence; Intensive care medicine; Computer science; Machine learning; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001036342,0.0002044905,0.001105182,0.000319822,0.0004761101,0.000004997407,0.000364573,0.00008932057,0.0007250378],"category_scores_gemma":[0.001412887,0.0001748602,0.000523004,0.001802852,0.0001378599,0.0002084412,0.0002362112,0.0004764276,0.000008559186],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004434772,"about_ca_system_score_gemma":0.002787754,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03291003,"about_ca_topic_score_gemma":0.006449398,"domain_scores_codex":[0.994502,0.002325665,0.001373185,0.0005008206,0.0008056402,0.0004926538],"domain_scores_gemma":[0.9951383,0.0004636204,0.001405098,0.001131108,0.001195345,0.0006665551],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004775413,0.0001877217,0.9463993,0.002391504,0.002026477,0.00000689168,0.0007240385,0.04292313,0.000002849061,0.00002150238,0.00008587325,0.004753147],"study_design_scores_gemma":[0.0005575336,0.0001581487,0.9742447,0.0008793606,0.003239862,3.16285e-8,0.0001881168,0.01760283,0.0002275602,0.00008156089,0.002615122,0.0002052421],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9886837,0.006327132,0.001529009,0.0002807009,0.0003966512,0.0008208865,0.00187427,0.00003108155,0.00005654986],"genre_scores_gemma":[0.9966437,0.002327142,0.00006379889,0.0001392583,0.0000715919,0.00007632923,0.0005349718,0.00003814904,0.0001050523],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02784531,"threshold_uncertainty_score":0.9735299,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07544052414019527,"score_gpt":0.4171521250970025,"score_spread":0.3417116009568072,"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."}}