{"id":"W4385186385","doi":"10.1097/bsd.0000000000001498","title":"Using Machine Learning (ML) Models to Predict Risk of Venous Thromboembolism (VTE) Following Spine Surgery","year":2023,"lang":"en","type":"article","venue":"Clinical Spine Surgery A Spine Publication","topic":"Venous Thromboembolism Diagnosis and Management","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Columbia College","funders":"National Heart, Lung, and Blood Institute; Vagelos College of Physicians and Surgeons, Columbia University; National Institutes of Health","keywords":"Medicine; Cohort; Logistic regression; Venous thromboembolism; Medical history; Retrospective cohort study; Population; Decision tree; Comorbidity; Machine learning; Surgery; Internal medicine; Computer science; Thrombosis","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.008032971,0.0005572455,0.003035097,0.001406377,0.0003404105,0.0001006432,0.0003282904,0.0003644348,0.0001700408],"category_scores_gemma":[0.007814234,0.0005311397,0.001533971,0.003350036,0.000142365,0.0005726727,0.0004517034,0.000786844,0.0001431591],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001710902,"about_ca_system_score_gemma":0.0004752729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007769338,"about_ca_topic_score_gemma":0.00003746031,"domain_scores_codex":[0.993089,0.000498914,0.003059949,0.001226065,0.001061278,0.001064852],"domain_scores_gemma":[0.9953114,0.0007266571,0.001285413,0.001258014,0.0006658055,0.0007526508],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003140552,0.01058347,0.6574197,0.001992763,0.005410627,0.0002609038,0.0007909262,0.01820686,0.004884104,0.002767887,0.05560736,0.2417614],"study_design_scores_gemma":[0.001085316,0.0006260623,0.9038676,0.0009539914,0.001407966,0.00001648584,0.00009343445,0.07313024,0.0004203613,0.0004441194,0.01727309,0.0006813595],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9799706,0.0006752709,0.008625691,0.005841519,0.001767317,0.001583765,0.0000393702,0.0008333918,0.0006630743],"genre_scores_gemma":[0.9875749,0.003357312,0.004262168,0.001357962,0.001201379,0.0002116931,0.001274086,0.0001867482,0.000573795],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2464479,"threshold_uncertainty_score":0.999714,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1261036902997236,"score_gpt":0.3676734507228301,"score_spread":0.2415697604231065,"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."}}