{"id":"W3164214033","doi":"10.1136/annrheumdis-2021-eular.446","title":"OP0288 MACHINE LEARNING ALGORITHMS TO PREDICT COVID-19 ACUTE RESPIRATORY DISTRESS SYNDROME IN PATIENTS WITH RHEUMATIC DISEASES: RESULTS FROM THE GLOBAL RHEUMATOLOGY ALLIANCE PROVIDER REGISTRY","year":2021,"lang":"en","type":"article","venue":"Annals of the Rheumatic Diseases","topic":"COVID-19 Clinical Research Studies","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"Metro North Hospital and Health Service; Swedish Orphan Biovitrum; Brigham and Women's Hospital; University College London; University of Otago; School of Medicine, Boston University; Biogen; Massachusetts General Hospital; Pfizer; Beth Israel Deaconess Medical Center; University College London Hospitals NHS Foundation Trust; McMaster University","keywords":"Medicine; ARDS; Internal medicine; Logistic regression; Rheumatology; Algorithm; Comorbidity; Odds ratio; Machine learning; Population; Intensive care 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005680289,0.0007071903,0.0009904084,0.001419741,0.0003109726,0.001408419,0.0008209543,0.0006404726,0.002670068],"category_scores_gemma":[0.01573397,0.0003055534,0.001241194,0.001600517,0.0002459424,0.0009723869,0.001004371,0.001194154,0.0009715859],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005575744,"about_ca_system_score_gemma":0.001192414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005737198,"about_ca_topic_score_gemma":0.004409211,"domain_scores_codex":[0.9964942,0.001899472,0.0003302578,0.000478789,0.0005453303,0.0002518951],"domain_scores_gemma":[0.9934875,0.003375437,0.0009681095,0.0007992482,0.001090058,0.0002797236],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00269942,0.0008392466,0.9119169,0.0001285259,0.0008185235,0.00007888189,0.00005485813,0.005845067,0.0004801461,0.000252639,0.009007929,0.06787789],"study_design_scores_gemma":[0.001431983,0.002132944,0.8879028,0.0001845705,0.001049324,0.0005406317,0.0003404826,0.09759065,0.001448922,0.0011156,0.006202252,0.00005989766],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9751839,0.001638064,0.003116866,0.0008868008,0.0001129019,0.0002186994,0.01629158,0.0001550012,0.002396129],"genre_scores_gemma":[0.9521468,0.001097399,0.008056729,0.0003310108,0.0001820042,0.0003978593,0.03598329,0.00006198998,0.001742848],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005737198,"threshold_uncertainty_score":0.03004062,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04594436854534031,"score_gpt":0.3789887102674974,"score_spread":0.3330443417221571,"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."}}