{"id":"W4225525527","doi":"10.1186/s12911-022-01837-2","title":"Developing a random forest algorithm to identify patent foramen ovale and atrial septal defects in Ontario administrative databases","year":2022,"lang":"en","type":"article","venue":"BMC Medical Informatics and Decision Making","topic":"Cardiovascular and Diving-Related Complications","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Public Health; Institute for Clinical Evaluative Sciences; University of Toronto; University Health Network; Toronto General Hospital; Canadian Institute for Advanced Research; Toronto Rehabilitation Institute","funders":"CorHealth Ontario; Ontario Ministry of Health and Long-Term Care","keywords":"Medicine; Patent foramen ovale; Algorithm; Random forest; Population; Closure (psychology); Pediatrics; Machine learning; Surgery; Computer science; Environmental health","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001190411,0.0001399999,0.0003863208,0.0002428269,0.0002482477,0.0000858169,0.00009997009,0.00005803253,0.0001392363],"category_scores_gemma":[0.0006769683,0.0001203271,0.000216562,0.0002713602,0.00004239235,0.000131106,0.0005979348,0.0003688409,0.00000732288],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001818288,"about_ca_system_score_gemma":0.0006575121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004903324,"about_ca_topic_score_gemma":0.00772261,"domain_scores_codex":[0.9979842,0.00005082667,0.0006603766,0.0001829574,0.0008936962,0.0002279254],"domain_scores_gemma":[0.9984244,0.0009246975,0.0001024137,0.0002303749,0.00005654282,0.0002616118],"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":[0.003788678,0.0001800203,0.09062918,0.0003688176,0.0005578823,0.0004160944,0.008954029,0.003448196,0.000004351051,0.004472901,0.00119,0.8859898],"study_design_scores_gemma":[0.06203271,0.001199817,0.2583142,0.004650822,0.0009300851,0.004805509,0.01557366,0.6131413,0.00001163812,0.008469407,0.02956329,0.001307558],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5018687,0.0002606831,0.4969931,0.00002195021,0.0001118192,0.0004239835,0.00001116381,0.0000139316,0.0002946805],"genre_scores_gemma":[0.7544794,0.00004892612,0.2446404,0.0005909035,0.00006121406,0.00007525841,0.00007635542,0.00001039169,0.0000171586],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8846823,"threshold_uncertainty_score":0.4906796,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1246373197004509,"score_gpt":0.3785490984011207,"score_spread":0.2539117787006698,"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."}}