{"id":"W4392413980","doi":"10.2196/49997","title":"A Case Demonstration of the Open Health Natural Language Processing Toolkit From the National COVID-19 Cohort Collaborative and the Researching COVID to Enhance Recovery Programs for a Natural Language Processing System for COVID-19 or Postacute Sequelae of SARS CoV-2 Infection: Algorithm Development and Validation","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; U.S. National Library of Medicine; National Heart, Lung, and Blood Institute","keywords":"Coronavirus disease 2019 (COVID-19); Artificial intelligence; Natural language processing; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Preprint; Task (project management); 2019-20 coronavirus outbreak; Computer science; Medicine; World Wide Web; Pathology; Disease; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01655025,0.0008128018,0.0005081783,0.001471576,0.003565926,0.002485256,0.00197009,0.003495885,0.005605928],"category_scores_gemma":[0.04206096,0.0004362928,0.0009814407,0.001018396,0.001986955,0.00248065,0.003381419,0.003475918,0.001957186],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003252895,"about_ca_system_score_gemma":0.0049086,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0221579,"about_ca_topic_score_gemma":0.0390189,"domain_scores_codex":[0.9900303,0.00543267,0.0007864719,0.001141834,0.002148399,0.0004602753],"domain_scores_gemma":[0.9598854,0.032157,0.0009399768,0.002436687,0.003012256,0.001568606],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001697095,0.001060413,0.08510508,0.002611211,0.0002017642,0.1403132,0.08648294,0.01972512,0.01616219,0.04670974,0.2690925,0.3308386],"study_design_scores_gemma":[0.0004390352,0.0007848953,0.03648961,0.001975499,0.0002016851,0.07289511,0.03322059,0.1347934,0.03470657,0.04398874,0.6400258,0.0004792042],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3752586,0.002219317,0.4537077,0.08168645,0.001865651,0.003294584,0.01334026,0.009543852,0.05908361],"genre_scores_gemma":[0.5808748,0.001487399,0.3772247,0.009902256,0.0004468264,0.0021448,0.009365924,0.002275302,0.016278],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0221579,"threshold_uncertainty_score":0.08752716,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05779017490292085,"score_gpt":0.4253979188147319,"score_spread":0.3676077439118111,"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."}}