{"id":"W4403140655","doi":"10.1016/j.gloepi.2024.100168","title":"Comparing AI/ML approaches and classical regression for predictive modeling using large population health databases: Applications to COVID-19 case prediction","year":2024,"lang":"en","type":"article","venue":"Global Epidemiology","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ottawa Hospital; Larus Technologies (Canada); Institut du Savoir Montfort; Institute for Clinical Evaluative Sciences; University of Ottawa","funders":"Ontario Ministry of Health and Long-Term Care; University of Ottawa","keywords":"Coronavirus disease 2019 (COVID-19); Regression; Population; Computer science; Predictive modelling; Database; Artificial intelligence; Statistics; Machine learning; Medicine; Mathematics; Environmental health; Internal medicine","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0364736,0.001644039,0.001395335,0.003395804,0.0006518877,0.002286506,0.002137428,0.00134212,0.0008803907],"category_scores_gemma":[0.07749812,0.0005908,0.001502022,0.002555837,0.0008376185,0.002115794,0.002089255,0.002508735,0.0002578104],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002133338,"about_ca_system_score_gemma":0.002530101,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03064415,"about_ca_topic_score_gemma":0.01982936,"domain_scores_codex":[0.9883101,0.008705758,0.0006879256,0.001092033,0.001007894,0.0001962949],"domain_scores_gemma":[0.9071896,0.08327615,0.002295656,0.002771061,0.003766997,0.000700617],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001376649,0.0008274781,0.1350819,0.0006080529,0.002019204,0.0002866284,0.0004832901,0.6293391,0.0007743516,0.007350719,0.003182568,0.2186701],"study_design_scores_gemma":[0.00005136864,0.000101518,0.003758544,0.00003589794,0.0000549659,0.00003194763,0.00008584435,0.992102,0.0001735328,0.003264685,0.000324308,0.00001544296],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4421962,0.004498903,0.5419835,0.004439625,0.0002528944,0.0008747744,0.001540786,0.001641931,0.002571274],"genre_scores_gemma":[0.7885621,0.001541035,0.2068518,0.0005819642,0.0002368177,0.0004623471,0.001242331,0.00009119335,0.0004303967],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0364736,"threshold_uncertainty_score":0.1928931,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3795098186871582,"score_gpt":0.5039864135553538,"score_spread":0.1244765948681956,"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."}}