{"id":"W4415230878","doi":"10.1609/aies.v8i1.36550","title":"A Critical Look at a Critical Care Dataset: MIMIC-IV's Construction, Contents, & Consequences","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI/ACM Conference on AI Ethics and Society","topic":"Primary Care and Health Outcomes","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Process (computing); Field (mathematics); Order (exchange); Intensive care; Information system; Work (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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02396498,0.0003683989,0.0003171406,0.004928985,0.002910524,0.007702962,0.001890018,0.001458799,0.005237626],"category_scores_gemma":[0.1424832,0.0004967898,0.0006992462,0.007649967,0.005627751,0.008020559,0.006935652,0.003379769,0.001069869],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006384039,"about_ca_system_score_gemma":0.004906374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01233969,"about_ca_topic_score_gemma":0.02059367,"domain_scores_codex":[0.9837447,0.009191352,0.001284259,0.00133114,0.003988087,0.000460477],"domain_scores_gemma":[0.8653111,0.08482675,0.008284386,0.02109752,0.01820078,0.002279389],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0005885924,0.0001377566,0.06806649,0.001130117,0.00008507722,0.0008115838,0.02599796,0.003018018,0.002811522,0.5261239,0.2829258,0.08830312],"study_design_scores_gemma":[0.00008755724,0.0001440343,0.0400447,0.001860715,0.00006991985,0.001141119,0.02425902,0.01398409,0.006858678,0.2116104,0.699739,0.0002007888],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.2757227,0.002867109,0.2492909,0.1984348,0.003586235,0.002989433,0.1180271,0.004175603,0.1449061],"genre_scores_gemma":[0.6340098,0.001277619,0.2606352,0.01525269,0.001368603,0.002122424,0.0719739,0.001982772,0.01137687],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.976035,"threshold_uncertainty_score":0.1267405,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1548304729848033,"score_gpt":0.4807062888538632,"score_spread":0.3258758158690599,"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."}}