{"id":"W4386776358","doi":"10.1016/j.eclinm.2023.102210","title":"Characterization of long COVID temporal sub-phenotypes by distributed representation learning from electronic health record data: a cohort study","year":2023,"lang":"en","type":"article","venue":"EClinicalMedicine","topic":"Long-Term Effects of COVID-19","field":"Medicine","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Ontario; University of Toronto","funders":"National Center for Advancing Translational Sciences; National Institute of Environmental Health Sciences; National Heart, Lung, and Blood Institute; British Heart Foundation; National Medical Research Council; National Institute of Neurological Disorders and Stroke; National Institute of Allergy and Infectious Diseases; Medical Research Council; National Institutes of Health; European Commission; National Institute on Aging; Horizon 2020 Framework Programme","keywords":"Medicine; Coronavirus disease 2019 (COVID-19); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Electronic health record; 2019-20 coronavirus outbreak; Cohort; Phenotype; Representation (politics); Cohort study; Health records; Pandemic; Virology; Pathology; Genetics; Outbreak; Infectious disease (medical specialty); Health care; Disease","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":[],"consensus_categories":[],"category_scores_codex":[0.003228657,0.0002552032,0.00114731,0.0001864115,0.0001309325,0.00001862011,0.0003372987,0.0001802259,0.0001470245],"category_scores_gemma":[0.008269702,0.0002235907,0.0000819542,0.0009890184,0.0001461263,0.0002331728,0.0002377994,0.0008256579,0.00006948977],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002259885,"about_ca_system_score_gemma":0.0006781712,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002257606,"about_ca_topic_score_gemma":0.0003066534,"domain_scores_codex":[0.9957181,0.0006677471,0.001373923,0.0009252726,0.0008165142,0.0004984364],"domain_scores_gemma":[0.9952791,0.002129639,0.000844011,0.001203428,0.0001525845,0.0003912815],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0008509384,0.0005162951,0.9793851,0.00016496,0.0003232806,0.00007985193,0.0002432189,0.000009599498,0.007127319,0.000003358599,0.006984856,0.004311182],"study_design_scores_gemma":[0.005122392,0.002864768,0.9853137,0.0002840157,0.0003260489,0.000005306561,0.0001786673,0.002611834,0.0002997019,0.00004633636,0.002777047,0.00017025],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9708827,0.000157412,0.00815408,0.0172907,0.0003717373,0.002545424,0.0002128578,0.0003729349,0.00001215033],"genre_scores_gemma":[0.941494,0.0007434817,0.00005754824,0.00131559,0.0005566065,0.00006152773,0.05550834,0.0000523143,0.0002105488],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05529548,"threshold_uncertainty_score":0.9900203,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04767289743164643,"score_gpt":0.3964368965460534,"score_spread":0.348763999114407,"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."}}