{"id":"W4390005903","doi":"10.1097/sla.0000000000006181","title":"Using Machine Learning (XGBoost) to Predict Outcomes After Infrainguinal Bypass for Peripheral Artery Disease","year":2023,"lang":"en","type":"article","venue":"Annals of Surgery","topic":"Peripheral Artery Disease Management","field":"Medicine","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"University Health Network; University of Toronto; St. Michael's Hospital","funders":"","keywords":"Medicine; Brier score; Receiver operating characteristic; Logistic regression; Surgery; Thrombolysis; Amputation; Adverse effect; Internal medicine; Machine learning","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":[0.003953533,0.001059894,0.0007929315,0.001599573,0.0002613909,0.0007135454,0.0007136536,0.0007999136,0.0008269157],"category_scores_gemma":[0.00516333,0.0002842108,0.0007691222,0.0006894217,0.0003183581,0.0005420581,0.0005433143,0.0008593189,0.0004380072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005976136,"about_ca_system_score_gemma":0.001000758,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00516262,"about_ca_topic_score_gemma":0.003625606,"domain_scores_codex":[0.999158,0.0004105953,0.0000638212,0.0001645587,0.0001112089,0.00009177641],"domain_scores_gemma":[0.9977543,0.001560394,0.0002810739,0.00007281877,0.00025132,0.00008010943],"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":[0.001578914,0.001034917,0.2795049,0.0002414248,0.001029964,0.0002020981,0.00009627319,0.4840136,0.001591764,0.0004055599,0.004713077,0.2255875],"study_design_scores_gemma":[0.00005845391,0.000357394,0.01449451,0.00003616005,0.00006371483,0.00006579236,0.00001763164,0.9832904,0.0007378322,0.0005330684,0.0003347636,0.00001030811],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8647959,0.002344999,0.126982,0.001114367,0.0001794893,0.0002219185,0.000806337,0.001831147,0.001723802],"genre_scores_gemma":[0.9661381,0.0002927643,0.03127707,0.00019534,0.0000743348,0.0001424218,0.001089661,0.00004363684,0.0007466956],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00516262,"threshold_uncertainty_score":0.02090853,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1956809341312676,"score_gpt":0.3736814874092211,"score_spread":0.1780005532779535,"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."}}