{"id":"W4398137865","doi":"10.1038/s41598-024-61721-z","title":"Medical calculators derived synthetic cohorts: a novel method for generating synthetic patient data","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Heart and Stroke Foundation; University of Toronto; Ontario Brain Institute","funders":"","keywords":"Calculator; Confidence interval; Computer science; Raw data; Plan (archaeology); Synthetic data; Machine learning; Data science; Data mining; Medicine; Artificial intelligence; Internal medicine","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.008212553,0.0002753459,0.0003689712,0.0003062948,0.000676377,0.001459843,0.001525014,0.0001623478,0.00009102815],"category_scores_gemma":[0.004495564,0.0002312329,0.0001459584,0.0009410347,0.0001803278,0.0005052421,0.001361002,0.0003976807,0.00002220237],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001243183,"about_ca_system_score_gemma":0.001223001,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001720109,"about_ca_topic_score_gemma":0.00005095562,"domain_scores_codex":[0.9935897,0.0002464281,0.001069359,0.002729955,0.001677393,0.0006871947],"domain_scores_gemma":[0.9942107,0.0007732121,0.0002910572,0.004023726,0.0002483857,0.0004528916],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008830576,0.0003620885,0.001408356,0.001621985,0.0002339281,0.004177598,0.006020291,0.008469974,0.03280922,0.02020809,0.02960818,0.8950714],"study_design_scores_gemma":[0.00004903232,0.00003734459,0.00003067209,0.0003480719,0.00002484785,0.00218276,0.00003102924,0.9157106,0.001636659,0.001544386,0.07814221,0.0002624374],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02255808,0.0009868231,0.9535375,0.00252644,0.01886851,0.0007831417,0.00001933309,0.0005792561,0.0001409127],"genre_scores_gemma":[0.4645717,0.000003075261,0.534271,0.0002742163,0.0002250259,0.0001525063,0.0001276111,0.00005128016,0.00032354],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9072406,"threshold_uncertainty_score":0.9995767,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03984080657851431,"score_gpt":0.3512376264875789,"score_spread":0.3113968199090646,"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."}}