{"id":"W4213310220","doi":"10.1016/j.jbi.2022.104034","title":"Non-negative matrix factorization temporal topic models and clinical text data identify COVID-19 pandemic effects on primary healthcare and community health in Toronto, Canada","year":2022,"lang":"en","type":"article","venue":"Journal of Biomedical Informatics","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":25,"is_retracted":false,"has_abstract":false,"ca_institutions":"North York General Hospital; Institute for Clinical Evaluative Sciences; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Pandemic; Health care; Computer science; Medicine; Artificial intelligence; Psychology; Coronavirus disease 2019 (COVID-19); Disease; Infectious disease (medical specialty); Pathology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008250027,0.00008116043,0.0003762396,0.0001068494,0.0007054157,0.00004466859,0.0003551907,0.00006194109,0.00002172361],"category_scores_gemma":[0.001132525,0.00006876075,0.00003347026,0.0002675152,0.0001506424,0.0004551261,0.0002952649,0.0007822679,8.973559e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001773376,"about_ca_system_score_gemma":0.003910055,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.5491458,"about_ca_topic_score_gemma":0.5819404,"domain_scores_codex":[0.9961269,0.001807573,0.001024686,0.00006902782,0.000803971,0.0001678471],"domain_scores_gemma":[0.9959227,0.002672577,0.0007085741,0.0001360559,0.00007267934,0.0004873826],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0003471769,0.0008178347,0.2744833,0.0015464,0.0003439021,0.00004667877,0.1204805,0.001192136,0.000001801816,0.002359889,0.01757953,0.5808008],"study_design_scores_gemma":[0.008766117,0.004421555,0.4569317,0.0005147171,0.000175083,0.0001433405,0.226297,0.1716876,6.106646e-7,0.04645593,0.08377127,0.000835118],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9221342,0.0009981659,0.05770069,0.01699413,0.001133697,0.0005475688,0.0002004061,0.00001629001,0.0002748076],"genre_scores_gemma":[0.9908535,0.0008213358,0.003946499,0.004109676,0.0001381453,0.000001467521,0.0001076827,0.000003416166,0.00001826638],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5799657,"threshold_uncertainty_score":0.6936269,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1456593808156004,"score_gpt":0.4946154215590821,"score_spread":0.3489560407434817,"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."}}