{"id":"W4413846771","doi":"10.1016/j.ijcha.2025.101783","title":"Evaluating artificial intelligence-enabled medical tests in cardiology: Best practice","year":2025,"lang":"en","type":"review","venue":"IJC Heart & Vasculature","topic":"Cardiac Imaging and Diagnostics","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Montreal Heart Institute","funders":"Novo Nordisk Fonden; Hartstichting; Austrian Science Fund; ZonMw; Villum Fonden; Novo Nordisk; Danish Cardiovascular Academy; European Federation of Pharmaceutical Industries and Associations; HORIZON EUROPE Framework Programme; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; National Institutes of Health; Hjerteforeningen; European Commission; Deutsche Forschungsgemeinschaft; Danish Data Science Academy","keywords":"Medicine; Medical physics; Cardiology; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02314774,0.001482228,0.004043605,0.006630759,0.0003809184,0.004034553,0.003145525,0.003619045,0.004741098],"category_scores_gemma":[0.06890131,0.0007126721,0.002284273,0.00470947,0.001430849,0.003932606,0.001713271,0.003017163,0.002552916],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00206364,"about_ca_system_score_gemma":0.004380092,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002550061,"about_ca_topic_score_gemma":0.003442858,"domain_scores_codex":[0.9882356,0.005424565,0.002248598,0.0007963408,0.003116405,0.0001784938],"domain_scores_gemma":[0.9334129,0.05179309,0.003935239,0.0012938,0.008966601,0.0005984159],"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":[0.00009643333,0.00005333203,0.0006455051,0.04229163,0.0004800895,0.00008049097,0.0001207448,0.0005979923,0.0002341106,0.004854636,0.0178303,0.9327149],"study_design_scores_gemma":[0.0002100601,0.000577666,0.005300064,0.2967173,0.003333593,0.001639508,0.0004857662,0.001695661,0.002007773,0.02954171,0.6582916,0.0001992727],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"methods","genre_scores_codex":[0.0002204931,0.9929038,0.001697853,0.002895378,0.0005235778,0.00006578406,0.00009508622,0.00003352087,0.001564548],"genre_scores_gemma":[0.004548274,0.9854649,0.006731963,0.001760404,0.0006992047,0.0001250716,0.0001865192,0.00002921956,0.0004544831],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.02314774,"threshold_uncertainty_score":0.1224185,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0982604628301758,"score_gpt":0.4782843423211831,"score_spread":0.3800238794910072,"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."}}