{"id":"W3139761694","doi":"10.2196/23983","title":"A Framework (SOCRATex) for Hierarchical Annotation of Unstructured Electronic Health Records and Integration Into a Standardized Medical Database: Development and Usability Study","year":2021,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Electronic Health Records Systems","field":"Health Professions","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Korea Health Industry Development Institute; Ministry of Trade, Industry and Energy","keywords":"Computer science; Information retrieval; Annotation; Usability; SNOMED CT; Schema (genetic algorithms); Data curation; Medicine; Data mining; Terminology; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02487654,0.001643708,0.0009956135,0.002936786,0.0009842062,0.002735218,0.00292739,0.001163565,0.00242901],"category_scores_gemma":[0.02564483,0.001060952,0.002608925,0.001460329,0.0009971776,0.003587078,0.004166508,0.001462158,0.0007526898],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001748878,"about_ca_system_score_gemma":0.004904666,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008086968,"about_ca_topic_score_gemma":0.008962316,"domain_scores_codex":[0.9883711,0.005460192,0.001561353,0.001733908,0.002535351,0.000338126],"domain_scores_gemma":[0.9802082,0.01031132,0.001415546,0.002889338,0.004442107,0.0007336068],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002941794,0.002384298,0.02093944,0.00745331,0.0008660218,0.002117154,0.01521875,0.03282673,0.1006382,0.02909116,0.02793181,0.7575913],"study_design_scores_gemma":[0.001153285,0.0052022,0.02946972,0.003074201,0.0009186262,0.003865812,0.006253843,0.6353627,0.08665232,0.01554326,0.2115723,0.000931683],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05228145,0.0004816337,0.9115782,0.0005022037,0.00009549894,0.004696297,0.002365614,0.02648329,0.001515861],"genre_scores_gemma":[0.04464018,0.0001688296,0.9480569,0.0001327668,0.00001338517,0.001281735,0.004089306,0.0009091091,0.0007077023],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02487654,"threshold_uncertainty_score":0.1315613,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03660782378064367,"score_gpt":0.4528535013384867,"score_spread":0.416245677557843,"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."}}