{"id":"W3112990870","doi":"10.1038/s41598-020-78888-w","title":"Multimodal fusion with deep neural networks for leveraging CT imaging and electronic health record: a case-study in pulmonary embolism detection","year":2020,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Venous Thromboembolism Diagnosis and Management","field":"Medicine","cited_by":242,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"U.S. National Library of Medicine; National Heart, Lung, and Blood Institute; National Institutes of Health","keywords":"Workflow; Artificial intelligence; Deep learning; Context (archaeology); Triage; Medical imaging; Computer science; Pulmonary embolism; Modality (human–computer interaction); Multimodality; Radiology; Medicine; Medical physics; Machine learning; Medical emergency; Surgery","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":[0.003874469,0.000760297,0.0006228678,0.00158918,0.0003468118,0.0008688958,0.0007396578,0.001485348,0.0008622453],"category_scores_gemma":[0.01008105,0.0002371233,0.0008367467,0.00112263,0.0005597203,0.001209329,0.0008558913,0.001135499,0.0003441092],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008410629,"about_ca_system_score_gemma":0.0007857644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007188926,"about_ca_topic_score_gemma":0.00694539,"domain_scores_codex":[0.9984574,0.000672524,0.0001232407,0.0002406407,0.0003325732,0.0001736332],"domain_scores_gemma":[0.9968407,0.001887579,0.0002667221,0.0003691458,0.0004773836,0.0001583781],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001928027,0.001897669,0.4571121,0.0004554469,0.0008630505,0.01288938,0.0006359401,0.08891943,0.01014,0.003187798,0.007383689,0.4145876],"study_design_scores_gemma":[0.00008951274,0.0009086163,0.05768576,0.0001419434,0.000463618,0.007480525,0.000478788,0.9109206,0.01299277,0.005280864,0.003469833,0.00008725492],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9246411,0.002949668,0.06502331,0.003175305,0.00009382476,0.0001348407,0.0007997825,0.0005089242,0.002673154],"genre_scores_gemma":[0.984672,0.000451187,0.01391709,0.0001391203,0.00004045238,0.00002416058,0.0004162658,0.00001709267,0.0003225503],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007188926,"threshold_uncertainty_score":0.02049041,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01523699138096179,"score_gpt":0.2661443572783903,"score_spread":0.2509073658974285,"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."}}