{"id":"W4415126726","doi":"10.1093/jamia/ocaf165","title":"FHIR-Former: enhancing clinical predictions through Fast Healthcare Interoperability Resources and large language models","year":2025,"lang":"en","type":"article","venue":"Journal of the American Medical Informatics Association","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Universität Duisburg-Essen; Universitätsklinikum Essen","keywords":"Interoperability; Standardization; Bridging (networking); Health care; Resource (disambiguation); Semantic interoperability","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":[0.005008977,0.0001130658,0.0004278318,0.00009600479,0.0002843548,0.000116446,0.0008654604,0.0001148565,0.000004401739],"category_scores_gemma":[0.003742542,0.00007451601,0.0001587058,0.0005605496,0.0001167329,0.000687711,0.0004700664,0.001364453,0.000001810827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003977328,"about_ca_system_score_gemma":0.0004483527,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002487761,"about_ca_topic_score_gemma":0.0001664808,"domain_scores_codex":[0.9963598,0.0007170227,0.001506827,0.0001016633,0.001028841,0.0002858845],"domain_scores_gemma":[0.9961458,0.0008391575,0.002124586,0.0003441019,0.000370519,0.0001757838],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009034477,0.0003919081,0.4974743,0.0006097384,0.0005105333,0.000007784037,0.1597538,0.0007826745,0.000009039685,0.01257948,0.01277143,0.3150189],"study_design_scores_gemma":[0.001398013,0.0007178721,0.123747,0.001080841,0.00007880645,0.00006789147,0.02131937,0.8343834,0.00002826742,0.005134128,0.01178537,0.0002590079],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6128856,0.0001821415,0.3540519,0.03122807,0.0008601145,0.0001352162,0.000007152205,0.00004184879,0.0006079878],"genre_scores_gemma":[0.9804442,0.0003169237,0.01022609,0.008742359,0.0001719108,0.000002771231,0.000001052698,0.000004921314,0.0000897898],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8336007,"threshold_uncertainty_score":0.5927944,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01394723324373387,"score_gpt":0.3554960264741158,"score_spread":0.3415487932303819,"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."}}