{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01591408,0.0008150723,0.0007073046,0.001829032,0.0005294888,0.001775408,0.001836995,0.001254722,0.002792153],"category_scores_gemma":[0.07119514,0.0005569408,0.00125243,0.001379885,0.0007051962,0.0009592898,0.001568597,0.001842944,0.0007450091],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006746282,"about_ca_system_score_gemma":0.001728395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002728486,"about_ca_topic_score_gemma":0.003169166,"domain_scores_codex":[0.9948457,0.003363581,0.000298371,0.0006745307,0.0006593395,0.0001584014],"domain_scores_gemma":[0.9388611,0.04826544,0.003034794,0.006724201,0.002366442,0.0007479248],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002334634,0.0007246571,0.1381998,0.0004384147,0.0008424155,0.00113303,0.001362391,0.5661858,0.003642667,0.04473979,0.0227775,0.217619],"study_design_scores_gemma":[0.0002846174,0.0002250152,0.004261845,0.00009758564,0.00006897311,0.0002670038,0.0001311181,0.9468163,0.002187934,0.03961813,0.005985281,0.00005614592],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1735049,0.0003777748,0.8121344,0.001118261,0.0003296837,0.001094839,0.006819071,0.002512211,0.002108839],"genre_scores_gemma":[0.5975646,0.0002114933,0.3856853,0.0006686093,0.0001521507,0.001477422,0.01264762,0.0003133721,0.001279367],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01591408,"threshold_uncertainty_score":0.08416271,"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."}}