{"id":"W4312220943","doi":"10.1016/j.jvsv.2022.12.006","title":"Developing and optimizing a machine learning predictive model for post-thrombotic syndrome in a longitudinal cohort of patients with proximal deep venous thrombosis","year":2022,"lang":"en","type":"article","venue":"Journal of Vascular Surgery Venous and Lymphatic Disorders","topic":"Venous Thromboembolism Diagnosis and Management","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Shanghai Municipal Health Bureau; National Natural Science Foundation of China","keywords":"Post-thrombotic syndrome; Receiver operating characteristic; Medicine; Logistic regression; Deep vein; Random forest; Decision tree; Cohort; Venous thrombosis; Body mass index; Predictive modelling; Thrombosis; Surgery; Artificial intelligence; Machine learning; Internal medicine; Computer science","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":[0.002793103,0.0005536154,0.0008100148,0.0008838814,0.0004607477,0.001345284,0.0009703924,0.0008302353,0.001073439],"category_scores_gemma":[0.005088911,0.0004734021,0.001082266,0.0003948482,0.0002047787,0.0005649549,0.0005565292,0.001391413,0.0003378833],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006408301,"about_ca_system_score_gemma":0.001222543,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01370937,"about_ca_topic_score_gemma":0.01159042,"domain_scores_codex":[0.999593,0.0001527133,0.00003683646,0.0001246431,0.00003572366,0.00005710922],"domain_scores_gemma":[0.998041,0.001376461,0.0001645249,0.0001157734,0.0001975638,0.000104646],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007499252,0.0009557088,0.7710313,0.00002894694,0.0007807983,0.0004560469,0.0001361132,0.1782035,0.001482445,0.0005779309,0.001913661,0.04368373],"study_design_scores_gemma":[0.0000213527,0.000117272,0.03615165,0.000008482541,0.0001237921,0.0001029096,0.00006024377,0.9624845,0.0002852416,0.0004608545,0.0001716822,0.0000119219],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9744087,0.0002504285,0.02366436,0.0005865322,0.00004050037,0.00005167415,0.0005304135,0.0001480751,0.0003192218],"genre_scores_gemma":[0.9915835,0.0001011948,0.006600373,0.00004922912,0.00002589207,0.00004827938,0.001028446,0.0000137789,0.0005493024],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01370937,"threshold_uncertainty_score":0.02725911,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0125256312546433,"score_gpt":0.2282380436056231,"score_spread":0.2157124123509798,"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."}}