{"id":"W4412805891","doi":"10.1093/eurheartjsupp/suaf083.100","title":"Machine learning modelling using cardiac magnetic resonance images to predict cancer therapy related cardiac dysfunction with external validation in HER2+ breast cancer patients","year":2025,"lang":"en","type":"article","venue":"European Heart Journal Supplements","topic":"Cardiac Imaging and Diagnostics","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Women's College Hospital; Toronto General Hospital; Health Sciences Centre; Sunnybrook Health Science Centre; Princess Margaret Cancer Centre; Libin Cardiovascular Institute of Alberta","funders":"","keywords":"Medicine; Cancer; Breast cancer; Cardiac magnetic resonance; Magnetic resonance imaging; Cardiac dysfunction; Internal medicine; Oncology; Cardiology; Radiology; Heart failure","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.002084943,0.0006879735,0.0005323348,0.0007396622,0.0002243704,0.0008479742,0.0007038504,0.0006201512,0.001433879],"category_scores_gemma":[0.004526882,0.0002011645,0.0006519973,0.0003571594,0.0003388613,0.000260646,0.0005714254,0.0007898204,0.0003767541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008920416,"about_ca_system_score_gemma":0.0007554902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01653961,"about_ca_topic_score_gemma":0.00804823,"domain_scores_codex":[0.9996301,0.0001460434,0.00002655263,0.0001017469,0.00003896364,0.00005653174],"domain_scores_gemma":[0.9974474,0.001665324,0.000251937,0.0001621402,0.000329928,0.0001433212],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001101731,0.0005268405,0.2973044,0.00008657781,0.0003437575,0.0003909087,0.0001114146,0.6376961,0.002383944,0.0003678696,0.001790307,0.05789617],"study_design_scores_gemma":[0.00001582504,0.0001117091,0.01784293,0.00001307396,0.00002738226,0.00004604737,0.00001627974,0.9807892,0.000747546,0.0001968002,0.0001844449,0.000008785504],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9770915,0.0003809666,0.01983155,0.0004124759,0.00002610884,0.00008549678,0.0009329648,0.000227735,0.001011311],"genre_scores_gemma":[0.9953567,0.00006158087,0.003251858,0.0000458308,0.00001002646,0.00004648382,0.0008569805,0.00001081168,0.0003595962],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01653961,"threshold_uncertainty_score":0.03288668,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01679146336678474,"score_gpt":0.2884186846268227,"score_spread":0.271627221260038,"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."}}