{"id":"W4312125493","doi":"10.3390/v14122761","title":"Clinical Application of Detecting COVID-19 Risks: A Natural Language Processing Approach","year":2022,"lang":"en","type":"article","venue":"Viruses","topic":"Topic Modeling","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Ontario; University of Toronto; Toronto Metropolitan University","funders":"","keywords":"Novelty; Computer science; Machine learning; Artificial intelligence; Artificial neural network; Pipeline (software); Pandemic; Transformer; F1 score; Task (project management); Named-entity recognition; Coronavirus disease 2019 (COVID-19); Natural language processing; Infectious disease (medical specialty); Disease; Medicine; Psychology; Engineering","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":[0.0007959539,0.0000666495,0.0001327779,0.00007079056,0.0002139796,0.00003535373,0.0006299786,0.00002487044,0.000004216842],"category_scores_gemma":[0.0002245839,0.00006478341,0.00004651505,0.0003210082,0.00002879805,0.000186075,0.0004253624,0.0002324091,0.000002131417],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005387919,"about_ca_system_score_gemma":0.0001284206,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003325987,"about_ca_topic_score_gemma":0.000007143059,"domain_scores_codex":[0.9988595,0.0001434563,0.0002915827,0.0003258225,0.0002465392,0.0001330937],"domain_scores_gemma":[0.99922,0.0001401254,0.0001955925,0.000366748,0.00002185009,0.00005567368],"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":[0.00002001128,0.0001597505,0.01660393,0.0001381009,0.00001490757,0.00000651959,0.005363371,0.0148075,0.005064653,0.002611128,0.00005361804,0.9551565],"study_design_scores_gemma":[0.0002434385,0.0000303402,0.0006054165,0.000003543948,0.000005535876,0.00001801526,0.0007912096,0.9951892,0.000690108,0.0002784664,0.002033844,0.0001108152],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1940521,0.001000662,0.8043229,0.00006534541,0.0001051372,0.0001356618,0.000001995394,0.0001567326,0.0001595076],"genre_scores_gemma":[0.9249684,0.000001736183,0.07388359,0.001009614,0.00006931602,0.00004994986,0.000001330471,0.000005938569,0.00001017864],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9803818,"threshold_uncertainty_score":0.2641791,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1179992466228597,"score_gpt":0.404890190535899,"score_spread":0.2868909439130393,"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."}}