{"id":"W4317940592","doi":"10.1016/j.jtha.2022.11.013","title":"Redefining clinical venous thromboembolism phenotypes: a novel approach using latent class analysis","year":2023,"lang":"en","type":"article","venue":"Journal of Thrombosis and Haemostasis","topic":"Venous Thromboembolism Diagnosis and Management","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"Daiichi Sankyo Europe; LEO Pharma; Pfizer","keywords":"Venous thromboembolism; Latent class model; Phenotype; Medicine; Class (philosophy); Clinical phenotype; Venous thrombosis; Computational biology; Internal medicine; Computer science; Thrombosis; Genetics; Biology; Artificial intelligence; Machine learning; Gene","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":[0.005440777,0.001015662,0.001512075,0.003132073,0.000774967,0.002768408,0.001285615,0.001033544,0.00208138],"category_scores_gemma":[0.01164284,0.0003154152,0.001761411,0.001583338,0.0005645544,0.001205824,0.001436988,0.002376409,0.0006515284],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004510033,"about_ca_system_score_gemma":0.001256434,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003012487,"about_ca_topic_score_gemma":0.003739726,"domain_scores_codex":[0.9966339,0.001544571,0.0002682323,0.0008354586,0.0004719544,0.0002459035],"domain_scores_gemma":[0.9919111,0.005267693,0.0007748336,0.0009373736,0.0008473356,0.0002616172],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001544191,0.001407952,0.2871383,0.0002301188,0.00153691,0.0003251236,0.0004344949,0.0258623,0.01078211,0.007978788,0.007944241,0.6548156],"study_design_scores_gemma":[0.0002404383,0.0005130531,0.1260193,0.0001099274,0.0008719868,0.0006795368,0.0004263856,0.8277452,0.0036415,0.03436165,0.005199071,0.0001919392],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1998913,0.001514641,0.7914674,0.001587753,0.0002164644,0.0002297867,0.001925807,0.001252865,0.001914038],"genre_scores_gemma":[0.8614214,0.0002998863,0.1349326,0.0001981258,0.0002121206,0.0001584562,0.001530775,0.0001524878,0.001094037],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005440777,"threshold_uncertainty_score":0.0287739,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1906199070553681,"score_gpt":0.3985620265437307,"score_spread":0.2079421194883626,"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."}}