{"id":"W4391934252","doi":"10.1016/j.ijmedinf.2024.105384","title":"hART: Deep learning-informed lifespan heart failure risk trajectories","year":2024,"lang":"en","type":"article","venue":"International Journal of Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; McGill University Health Centre","funders":"Fonds de Recherche du Québec - Santé; Heart And Stroke Foundation Of Quebec; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Heart and Stroke Foundation of Canada","keywords":"Medicine; Heart failure; Recall; Cohort; Psychological intervention; Heart disease; Framingham Risk Score; Disease; Cardiology; Internal medicine; Psychology; Cognitive psychology; Psychiatry","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002064915,0.0001626353,0.0002593685,0.0004437328,0.00009938231,0.0006903581,0.002137406,0.0001871924,0.0002986888],"category_scores_gemma":[0.003530768,0.0001234108,0.0002027525,0.0003076885,0.0000853979,0.001579516,0.0003032788,0.002055182,0.0001765582],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001799548,"about_ca_system_score_gemma":0.0009399501,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003733402,"about_ca_topic_score_gemma":0.00003245584,"domain_scores_codex":[0.9949499,0.0001341787,0.001253307,0.000092029,0.003302164,0.0002683997],"domain_scores_gemma":[0.9975986,0.0007468352,0.0004866345,0.0001766124,0.0005848534,0.0004064516],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006834188,0.0001398376,0.03297212,0.0006832332,0.0009378777,0.0007000101,0.05193122,0.006856255,0.000007804844,0.07709524,0.111548,0.7170601],"study_design_scores_gemma":[0.0003752024,0.000224984,0.001231564,0.0005140112,0.00001218902,0.001521523,0.000627953,0.4718702,0.00003564864,0.00100286,0.5224428,0.0001410555],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04668152,0.001096203,0.872063,0.06396877,0.01440806,0.0001378001,0.000008048159,0.0003452057,0.001291361],"genre_scores_gemma":[0.9085054,0.0007970778,0.08580824,0.002444494,0.002155949,0.000004642645,0.00001087532,0.00002226931,0.0002509916],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8618239,"threshold_uncertainty_score":0.8928858,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01185906906088453,"score_gpt":0.3288418832135166,"score_spread":0.3169828141526321,"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."}}