{"id":"W4310464163","doi":"10.2196/41529","title":"Natural Language Processing for Improved Characterization of COVID-19 Symptoms: Observational Study of 350,000 Patients in a Large Integrated Health Care System","year":2022,"lang":"en","type":"article","venue":"JMIR Public Health and Surveillance","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Medicine; myalgia; Sore throat; Chills; Vomiting; Nausea; Vital signs; Medical record; Diarrhea; Observational study; Pediatrics; Internal medicine; Surgery","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001395365,0.0001466812,0.000618051,0.0003209104,0.0002348939,0.00001864842,0.0001019719,0.00004169237,0.000006207671],"category_scores_gemma":[0.0006512268,0.0001391413,0.00003674983,0.0008269935,0.0000234927,0.0001050405,0.00006645273,0.0002021509,4.725393e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001271357,"about_ca_system_score_gemma":0.004072657,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001512296,"about_ca_topic_score_gemma":0.001087745,"domain_scores_codex":[0.9976285,0.0004652107,0.0008109164,0.0003580661,0.0003456814,0.000391587],"domain_scores_gemma":[0.99824,0.0001941984,0.000666071,0.0001999506,0.0003998571,0.0002999263],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004489497,0.001208597,0.9412262,0.007793949,0.000018753,0.000001213337,0.03355767,0.000004286998,0.00008894188,0.00002033053,0.0002552097,0.01537586],"study_design_scores_gemma":[0.008118521,0.002282911,0.941003,0.000127706,0.000001631825,0.000002956665,0.02557963,0.008993536,0.000001300255,2.810022e-7,0.01375166,0.0001368375],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9831635,0.0008111674,0.0001324867,0.01103124,0.0001368538,0.00365527,0.001004352,0.00006391192,0.000001189967],"genre_scores_gemma":[0.9846821,0.00001132117,0.00004955711,0.01106097,0.00002985047,0.0006999988,0.003432164,0.00002201503,0.0000120194],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01523903,"threshold_uncertainty_score":0.722472,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03885459927312459,"score_gpt":0.3622610122043899,"score_spread":0.3234064129312653,"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."}}