{"id":"W4413420910","doi":"10.1038/s41598-025-16376-9","title":"Machine learning enhanced expert system for detecting heart failure decompensation using patient reported vitals and electronic health records","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto; Public Health Ontario; Ted Rogers Centre for Heart Research; University Health Network","funders":"University Health Network","keywords":"Decompensation; Health records; Computer science; Electronic health record; Heart failure; Artificial intelligence; Medicine; Machine learning; Medical emergency; Internal medicine; Health care","routes":{"ca_aff":true,"ca_fund":true,"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":["sts"],"consensus_categories":[],"category_scores_codex":[0.006058271,0.0002432028,0.0005333092,0.0003961929,0.004905586,0.0001091791,0.00008887304,0.0002166327,0.00003123423],"category_scores_gemma":[0.002173435,0.000237627,0.0001049355,0.000791326,0.0001007839,0.0002267569,0.0001292106,0.0006638985,0.000005435223],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001479267,"about_ca_system_score_gemma":0.002059143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003662424,"about_ca_topic_score_gemma":0.004599067,"domain_scores_codex":[0.994293,0.00075638,0.002267649,0.001172933,0.0004019495,0.001108142],"domain_scores_gemma":[0.9960862,0.0005748568,0.001631074,0.0007077497,0.0007932557,0.000206834],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005395294,0.0002476635,0.355739,0.00855908,0.0002791091,0.000104581,0.05014621,0.003505834,0.408042,0.00247129,0.01061156,0.1597542],"study_design_scores_gemma":[0.001081929,0.001321066,0.001653663,0.01359845,0.0001486679,0.0006348873,0.1423057,0.1930758,0.3219004,0.01774673,0.3045115,0.002021116],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9618808,0.001457551,0.02105441,0.001198181,0.01040686,0.003487015,0.000003256349,0.0003343805,0.0001775204],"genre_scores_gemma":[0.9945546,0.00001325944,0.003967444,0.0002507621,0.0001294683,0.0003510371,0.00005248048,0.00003838867,0.000642563],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3540853,"threshold_uncertainty_score":0.9963899,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07177287947946756,"score_gpt":0.4342754160562995,"score_spread":0.362502536576832,"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."}}