{"id":"W4407340781","doi":"10.1016/j.jaci.2024.12.984","title":"Development of an Algorithm to Identify Patients With Hypereosinophilic Syndrome (HES) in Claims Data and Electronic Health Records","year":2025,"lang":"en","type":"article","venue":"Journal of Allergy and Clinical Immunology","topic":"Eosinophilic Disorders and Syndromes","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"GlaxoSmithKline (Canada)","funders":"","keywords":"Health records; Hypereosinophilic syndrome; Electronic health record; Medicine; Algorithm; Computer science; Data mining; Internal medicine; Eosinophilia; Political science; Health care","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":[0.0009913155,0.0001292475,0.0007816717,0.0002656438,0.00005335968,0.000009990001,0.0002293464,0.0001459166,0.00001870254],"category_scores_gemma":[0.000105937,0.00009598801,0.00003560511,0.0002040722,0.0001494421,0.0001350009,0.0001721951,0.0004749851,8.31473e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000497769,"about_ca_system_score_gemma":0.000684306,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003343422,"about_ca_topic_score_gemma":0.0004490336,"domain_scores_codex":[0.9979745,0.0001422623,0.001197361,0.0002673402,0.0001535331,0.0002650736],"domain_scores_gemma":[0.9989772,0.0001183426,0.0003348069,0.000312725,0.0001253755,0.0001315197],"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":[0.001988832,0.00273476,0.1237151,0.00006769473,0.002190859,0.0000814099,0.0004673039,8.407567e-7,0.00005724453,0.0001977923,0.0001821938,0.8683159],"study_design_scores_gemma":[0.004533295,0.006024131,0.9818876,0.0003721241,0.0000450609,0.0002215201,0.0003643776,0.0000285342,0.000005072371,0.0004335039,0.005997045,0.00008768617],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9943102,0.002880314,0.0001847358,0.002239669,0.0001729274,0.000168355,0.000004036347,0.000003716801,0.00003603284],"genre_scores_gemma":[0.9844884,0.004684852,0.009901972,0.0007805427,0.00001715782,0.000002012498,0.00002797096,0.00001155256,0.00008548691],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8682283,"threshold_uncertainty_score":0.3914278,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02539431806861426,"score_gpt":0.361784238490215,"score_spread":0.3363899204216007,"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."}}