{"id":"W4413864914","doi":"10.1186/s13326-025-00335-4","title":"A prototype ETL pipeline that uses HL7 FHIR RDF resources when deploying pure functions to enrich knowledge graph patient data","year":2025,"lang":"en","type":"article","venue":"Journal of Biomedical Semantics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre for Addiction and Mental Health","funders":"","keywords":"Computer science; RDF; Graph; Pipeline (software); Knowledge graph; Information retrieval; Database; Linked data; Data science; Data mining; Programming language; Theoretical computer science; Semantic Web","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":[0.001354613,0.0002196255,0.0004226733,0.0008018431,0.0002991869,0.0002255681,0.002390405,0.0001749955,0.00003374415],"category_scores_gemma":[0.001600846,0.0001646734,0.0001151223,0.001521696,0.0001029096,0.0003574804,0.001491304,0.0009392111,0.000036574],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008922189,"about_ca_system_score_gemma":0.0004354766,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005001948,"about_ca_topic_score_gemma":0.00007159411,"domain_scores_codex":[0.9969247,0.0003500505,0.0008839639,0.0004422515,0.0009565165,0.0004424996],"domain_scores_gemma":[0.9970681,0.0005018741,0.0004428268,0.001036121,0.0004730881,0.0004780102],"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":[0.0002219334,0.001615779,0.06950366,0.001193043,0.0003547431,0.0003847296,0.01059664,0.0003193749,0.0004120057,0.001519835,0.4248575,0.4890208],"study_design_scores_gemma":[0.0006588047,0.001151275,0.006965632,0.001271302,0.00009188591,0.0001959065,0.0004340579,0.05013699,0.00006895709,0.001514113,0.9372219,0.0002891826],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05979155,0.002485747,0.8744599,0.0588344,0.003183942,0.0007278484,0.00002871296,0.0001600418,0.0003279297],"genre_scores_gemma":[0.8882808,0.0002223955,0.1061065,0.003448882,0.001120586,0.00002555267,0.00002858137,0.00004434925,0.0007223487],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8284892,"threshold_uncertainty_score":0.6715185,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04196971663979097,"score_gpt":0.3312414859543117,"score_spread":0.2892717693145208,"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."}}