{"id":"W4393857732","doi":"10.1016/j.rpth.2024.102403","title":"Machine learning analysis of bleeding status in venous thromboembolism patients","year":2024,"lang":"en","type":"article","venue":"Research and Practice in Thrombosis and Haemostasis","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa; Ottawa Hospital","funders":"Alliance de recherche numérique du Canada","keywords":"Venous thromboembolism; Medicine; Intensive care medicine; Internal medicine; Thrombosis","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.002994484,0.000112731,0.0003667527,0.001528751,0.0001216749,0.0003887437,0.000272352,0.0000794293,0.00001577169],"category_scores_gemma":[0.00147576,0.0001046134,0.00003044618,0.003677435,0.0001466257,0.00147467,0.0003750743,0.0005834591,0.000002538801],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009239438,"about_ca_system_score_gemma":0.00008384571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002081716,"about_ca_topic_score_gemma":0.0001856534,"domain_scores_codex":[0.9977096,0.0005211876,0.0003463738,0.0004900018,0.000514658,0.0004181845],"domain_scores_gemma":[0.9965016,0.002823484,0.00008156191,0.00029533,0.0001987839,0.00009919017],"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":[0.0001042422,0.00127604,0.1715349,0.0003916413,0.0008446229,0.0000439614,0.01800221,0.00006622534,0.00198505,0.07919306,0.0004864428,0.7260716],"study_design_scores_gemma":[0.001017009,0.001300087,0.8076552,0.0005416301,0.0002593874,0.000008063768,0.002611396,0.1438616,0.002612609,0.008475367,0.03110079,0.0005568855],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9541802,0.01670161,0.01130252,0.007712463,0.0001615955,0.0009881847,0.0002095987,0.0002575877,0.008486195],"genre_scores_gemma":[0.9627809,0.03000413,0.007090996,0.00003608328,0.000007747138,0.00002394501,0.00003723025,0.000009327527,0.000009654843],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7255147,"threshold_uncertainty_score":0.4266009,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1276848708195365,"score_gpt":0.4325571690511426,"score_spread":0.3048722982316061,"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."}}