{"id":"W4402987528","doi":"10.1200/op.2024.20.10_suppl.409","title":"Impact of applying machine learning to the electronic medical record on prediction of cancer-associated thrombosis.","year":2024,"lang":"en","type":"article","venue":"JCO Oncology Practice","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Sunnybrook Health Science Centre; University of Toronto; Princess Margaret Cancer Centre; Health Sciences Centre; University Health Network","funders":"Princess Margaret Cancer Foundation; TD Bank","keywords":"Thrombosis; Cancer; Electronic medical record; Medical record; Machine learning; Artificial intelligence; Computer science; Medicine; Medical emergency; Internal medicine","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":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00510391,0.0001487897,0.0004150789,0.0001549018,0.0004982491,0.000005459507,0.0002783416,0.0005120364,0.001346321],"category_scores_gemma":[0.01600549,0.0001019178,0.0001169633,0.0007208965,0.00008571656,0.0001678571,0.0001203463,0.003333252,0.0002106775],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002325054,"about_ca_system_score_gemma":0.004046194,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.04256791,"about_ca_topic_score_gemma":0.02593952,"domain_scores_codex":[0.994516,0.003147653,0.0009272224,0.0003107124,0.0005089004,0.0005895386],"domain_scores_gemma":[0.9851497,0.01338659,0.0006378561,0.0002484094,0.0004275106,0.0001499026],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002528528,0.001244271,0.560456,0.0007091201,0.001647509,0.00003897779,0.03870085,0.004263275,0.003004279,0.00908127,0.02670215,0.3516238],"study_design_scores_gemma":[0.0005578525,0.01228916,0.0714125,0.002224124,0.0005527473,0.00001448326,0.01351876,0.09348305,0.0002523924,0.0008240324,0.8045701,0.0003007996],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9419881,0.00126808,0.0002891633,0.04565758,0.002580479,0.00184061,0.00008339168,0.0001914708,0.006101082],"genre_scores_gemma":[0.9954646,0.00190873,0.00005455677,0.001315154,0.0004395298,0.0004807463,0.00001811564,0.00003387937,0.0002846694],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.777868,"threshold_uncertainty_score":0.9995666,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1587365689895234,"score_gpt":0.5772817834033115,"score_spread":0.4185452144137881,"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."}}