{"id":"W4409258708","doi":"10.1016/j.jbi.2025.104795","title":"Low-cost algorithms for clinical notes phenotype classification to enhance epidemiological surveillance: A case study","year":2025,"lang":"en","type":"article","venue":"Journal of Biomedical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Fondo para la Investigación Científica y Tecnológica; Agencia Nacional de Promoción de la Investigación, el Desarrollo Tecnológico y la Innovación; Styrelsen för Internationellt Utvecklingssamarbete; Universidad Nacional de Quilmes; Consejo Nacional de Investigaciones Científicas y Técnicas; International Development Research Centre","keywords":"Computer science; Epidemiology; Phenotype; Algorithm; Medicine; Data mining; Artificial intelligence; Pathology; Biology; Genetics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008996924,0.0001731419,0.0006563291,0.0003124601,0.0001741218,0.0001070952,0.001023445,0.000214722,0.000007619877],"category_scores_gemma":[0.01345592,0.0001211757,0.0001850446,0.000828694,0.0001122599,0.0002955182,0.0002681063,0.0007763118,0.00001607078],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001156026,"about_ca_system_score_gemma":0.0004402272,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002372681,"about_ca_topic_score_gemma":0.00001266681,"domain_scores_codex":[0.9956586,0.000474164,0.002803729,0.0001848232,0.0005165066,0.0003621767],"domain_scores_gemma":[0.9923084,0.005024804,0.001027647,0.0004864007,0.0007243459,0.0004283661],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008823239,0.0007697965,0.02884906,0.000233272,0.00008740961,0.0001689467,0.002440455,0.0001671116,0.000006209366,0.0008409695,0.01020134,0.9561472],"study_design_scores_gemma":[0.002411175,0.004971547,0.06129819,0.0003930831,0.00005044886,0.001066238,0.003511349,0.8683515,0.00003226472,0.001559265,0.05586147,0.0004934921],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1311333,0.0000503125,0.8576322,0.008925304,0.001517313,0.0006595157,0.000007838017,0.00003854878,0.00003562621],"genre_scores_gemma":[0.739284,0.00005175149,0.2569803,0.003241274,0.0003832189,0.00002863499,0.000004705354,0.000005892166,0.00002024594],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9556537,"threshold_uncertainty_score":0.9948542,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1203890973362984,"score_gpt":0.490809706567575,"score_spread":0.3704206092312766,"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."}}