{"id":"W4387007762","doi":"10.1101/2023.09.24.23295960","title":"Moving Biosurveillance Beyond Coded Data: AI for Symptom Detection from Physician Notes","year":2023,"lang":"en","type":"preprint","venue":"medRxiv","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hospital for Sick Children","funders":"National Institute of Child Health and Human Development; Centers for Disease Control and Prevention; U.S. Department of Health and Human Services","keywords":"Recall; Emergency department; Medicine; Gold standard (test); Artificial intelligence; Electronic health record; Health records; Population; Retrospective cohort study; Coronavirus disease 2019 (COVID-19); Cohort; Natural language processing; Pediatrics; Computer science; Health care; Psychology; Disease; Psychiatry; Internal medicine; Infectious disease (medical specialty)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007900741,0.000477036,0.0009250931,0.0002828243,0.0001656787,0.0001355663,0.000693106,0.0004385953,0.00001656106],"category_scores_gemma":[0.00293664,0.000490099,0.000250114,0.0003282218,0.0000976273,0.0001141454,0.001260983,0.0007732135,0.0001246666],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002875287,"about_ca_system_score_gemma":0.0003338545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002101456,"about_ca_topic_score_gemma":0.001627615,"domain_scores_codex":[0.9967177,0.0001106887,0.0005701772,0.001626404,0.0004999427,0.0004750806],"domain_scores_gemma":[0.9941739,0.002402594,0.0003691414,0.002629927,0.00026124,0.0001632344],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001530477,0.001608897,0.4131468,0.009823422,0.00436998,0.0003557496,0.002605011,0.008142621,0.3368498,0.00008149319,0.0775948,0.143891],"study_design_scores_gemma":[0.005519149,0.0004176017,0.4980985,0.005454921,0.001997982,0.000007167731,0.0001197628,0.2333855,0.1273183,0.006816202,0.1185003,0.002364675],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8994851,0.0007214675,0.03885411,0.04743819,0.00590498,0.002297624,0.003875606,0.001397321,0.00002565841],"genre_scores_gemma":[0.9764665,0.0002037544,0.002213381,0.01331986,0.003162752,0.0003607536,0.00389094,0.000241518,0.0001405288],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2252428,"threshold_uncertainty_score":0.9997551,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0731613636287202,"score_gpt":0.353814342137556,"score_spread":0.2806529785088359,"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."}}