{"id":"W4410127530","doi":"10.2196/58097","title":"Concordance between survey and electronic health record data in the COVID-19 Citizen Science study: a retrospective cohort analysis (Preprint)","year":2024,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Preprint; Concordance; Coronavirus disease 2019 (COVID-19); Health records; 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Electronic health record; Survey data collection; Cohort; Medicine; Virology; Health care; Political science; Statistics; Computer science; World Wide Web; Infectious disease (medical specialty); Outbreak; Pathology; Mathematics; Internal medicine","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":["metaresearch","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.07342584,0.0001903394,0.0004817698,0.00153942,0.001056904,0.001155053,0.005128521,0.00005023785,0.00001660333],"category_scores_gemma":[0.003024962,0.0001404116,0.00004064465,0.01450104,0.0006549343,0.001452278,0.003239903,0.002334641,0.00003150661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002170943,"about_ca_system_score_gemma":0.004070461,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02784284,"about_ca_topic_score_gemma":0.01498431,"domain_scores_codex":[0.9876574,0.006495554,0.0006077962,0.001535459,0.002422118,0.001281669],"domain_scores_gemma":[0.9924654,0.004145063,0.0001367448,0.002484681,0.0004157903,0.0003523255],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001201974,0.00004985099,0.9558616,0.00009617132,0.00008840155,0.00001302154,0.0289083,0.00001894927,4.693056e-7,0.004703765,0.0007095694,0.009537839],"study_design_scores_gemma":[0.0001768633,0.0007227436,0.9246466,0.00002528429,0.000005018936,0.000007485274,0.001291562,0.06943404,5.677158e-7,0.002733038,0.0008300864,0.0001266699],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9358857,0.0005533508,0.04725806,0.01228627,0.00008884912,0.003160484,0.0001366023,0.0001730294,0.0004576717],"genre_scores_gemma":[0.99892,0.0001504343,0.000284792,0.0002474328,0.00004074612,0.0002613082,0.00004777139,0.00001029238,0.00003723671],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07040088,"threshold_uncertainty_score":0.999967,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1379656253288164,"score_gpt":0.5090514009935752,"score_spread":0.3710857756647588,"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."}}