{"id":"W6977768531","doi":"10.6084/m9.figshare.c.6254850.v1","title":"Natural language processing for identification of hypertrophic cardiomyopathy patients from cardiac magnetic resonance reports","year":2022,"lang":"en","type":"other","venue":"Figshare","topic":"Military Technology and Strategies","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Hypertrophic cardiomyopathy; Mitral regurgitation; Ejection fraction; Text mining; Magnetic resonance imaging; Cardiac magnetic resonance; Cardiomyopathy","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":[0.005403473,0.0003428655,0.0004382987,0.003190984,0.0003877067,0.0008955845,0.0005363395,0.0003798214,0.001968757],"category_scores_gemma":[0.02783218,0.0001478667,0.0005934629,0.001188874,0.0003547152,0.0006529121,0.0008076902,0.000445643,0.0006509235],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006383127,"about_ca_system_score_gemma":0.001096627,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001772525,"about_ca_topic_score_gemma":0.001597985,"domain_scores_codex":[0.9956971,0.002139184,0.0009161906,0.0006539921,0.0004904438,0.000102963],"domain_scores_gemma":[0.9652159,0.02744662,0.003288656,0.0009484132,0.00270403,0.0003965578],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004270964,0.001050192,0.3258401,0.002263108,0.0002764046,0.002950862,0.003408235,0.008901512,0.02665455,0.001675576,0.01497307,0.6077355],"study_design_scores_gemma":[0.0009177472,0.002181569,0.5374911,0.0009863386,0.0006345674,0.007087288,0.005403989,0.3623063,0.04060751,0.01341198,0.02871909,0.0002523681],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8916466,0.001317009,0.08663261,0.001727092,0.0001158584,0.002702141,0.01071842,0.001614965,0.003525261],"genre_scores_gemma":[0.8184686,0.0003665935,0.1673582,0.0003901999,0.00009091973,0.001470304,0.01126228,0.00004727256,0.0005456079],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005403473,"threshold_uncertainty_score":0.02857667,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006298827925405242,"score_gpt":0.1981987752175107,"score_spread":0.1918999472921055,"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."}}