{"id":"W4394827593","doi":"10.1016/j.jocmr.2024.100166","title":"Machine Learning Can Distinguish Hypertrophic Cardiomyopathy, Cardiac Light Chain and Transthyretin Amyloidosis Using Cardiac Magnetic Resonance Imaging Data and Standard Clinical Information","year":2024,"lang":"en","type":"article","venue":"Journal of Cardiovascular Magnetic Resonance","topic":"Parathyroid Disorders and Treatments","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Transthyretin; Medicine; Hypertrophic cardiomyopathy; Cardiac amyloidosis; Angiology; Amyloidosis; Cardiac magnetic resonance; Magnetic resonance imaging; Cardiac magnetic resonance imaging; Cardiology; Internal medicine; Cardiomyopathy; Heart failure; Radiology","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":[0.002784457,0.0009312925,0.000959569,0.002405556,0.0002741667,0.001587915,0.0005600164,0.001249029,0.001584093],"category_scores_gemma":[0.009661389,0.0002009066,0.0006868185,0.0009838636,0.0003624021,0.001338138,0.0007528365,0.001141836,0.001157079],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003592481,"about_ca_system_score_gemma":0.0006007731,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001756526,"about_ca_topic_score_gemma":0.002146118,"domain_scores_codex":[0.9989949,0.0003418,0.0001611157,0.0002288098,0.0001583229,0.0001151564],"domain_scores_gemma":[0.9942482,0.003988951,0.0004811607,0.0005016794,0.0005359253,0.0002439887],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00274657,0.001187466,0.6174874,0.000220468,0.0005796711,0.0009712905,0.0001119687,0.02095519,0.008443701,0.0007937807,0.006276899,0.3402257],"study_design_scores_gemma":[0.0002021492,0.001240849,0.2655363,0.0002276211,0.0003829678,0.00211303,0.0004672883,0.7009463,0.0103024,0.01285782,0.005613174,0.0001101166],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9506626,0.001918122,0.03474359,0.001826515,0.0002556655,0.0001431514,0.004358215,0.000777283,0.005314874],"genre_scores_gemma":[0.9882296,0.0002889105,0.007427993,0.0002017351,0.000134884,0.000030619,0.003199641,0.00002652905,0.0004600441],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002784457,"threshold_uncertainty_score":0.0147258,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01536834933613607,"score_gpt":0.2704785284050455,"score_spread":0.2551101790689095,"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."}}