{"id":"W4410447735","doi":"10.3233/shti250479","title":"Applying AI to Support Categorization of Heterogeneous Epidemiological Datasets","year":2025,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University Health Centre","funders":"Deutsche Forschungsgemeinschaft","keywords":"Computer science; Metadata; Annotation; Interoperability; World Wide Web; Information retrieval; Controlled vocabulary; Categorization; Data curation; Context (archaeology); Data science; Artificial intelligence","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":[],"consensus_categories":[],"category_scores_codex":[0.00495179,0.00008829195,0.0004648936,0.0008926299,0.000151526,0.00001212703,0.0004140207,0.00009403489,0.000006059907],"category_scores_gemma":[0.006259824,0.00006336493,0.0000158054,0.001358029,0.0003087678,0.0001713472,0.001009687,0.0001474424,0.00001435244],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000417553,"about_ca_system_score_gemma":0.00004781693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001417926,"about_ca_topic_score_gemma":0.00006143888,"domain_scores_codex":[0.9977895,0.00009614781,0.001546275,0.0001491849,0.0001888293,0.0002300543],"domain_scores_gemma":[0.9985619,0.0005869365,0.0003024694,0.0004273276,0.0000897099,0.00003162566],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000028844,0.00005454784,0.02022055,0.000732389,0.00004612027,0.000002444139,0.002139195,0.0007273177,9.049622e-7,0.4082775,0.0792206,0.4885495],"study_design_scores_gemma":[0.0004491606,0.0005987816,0.002022443,0.0001745644,0.000008711968,0.000007563006,0.02714107,0.002174553,0.00009794726,0.3109235,0.656243,0.0001587038],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1931841,0.008638027,0.6205641,0.1568304,0.003545571,0.00886306,0.001256138,0.0004994714,0.006619124],"genre_scores_gemma":[0.9677377,0.002352984,0.009479021,0.02005439,0.000006485492,0.0002108678,0.00006881823,0.000002314654,0.00008743507],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7745536,"threshold_uncertainty_score":0.7494046,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2480369898054427,"score_gpt":0.5283460737041448,"score_spread":0.2803090838987021,"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."}}