{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008357354,0.0002485613,0.000883682,0.0001317779,0.0006019222,0.00001964244,0.0001956504,0.000490052,0.0002116963],"category_scores_gemma":[0.006628552,0.0001988439,0.00003963871,0.00044009,0.000211769,0.0002220296,0.0002157396,0.002034324,0.00000320459],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007956556,"about_ca_system_score_gemma":0.01758166,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001946338,"about_ca_topic_score_gemma":0.00469005,"domain_scores_codex":[0.9930819,0.001358562,0.002849696,0.0003038959,0.001538602,0.0008673999],"domain_scores_gemma":[0.9951085,0.002456259,0.0007199697,0.000382924,0.0004878054,0.0008445671],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.001221818,0.0008458499,0.02083564,0.0143387,0.000237326,0.000006918922,0.227079,4.745433e-7,0.00002325471,0.01932178,0.003226893,0.7128624],"study_design_scores_gemma":[0.06474442,0.02326173,0.07426222,0.02811121,0.0002778615,0.0003454533,0.4393456,0.09838723,0.0006986372,0.0738565,0.1934324,0.003276732],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8583599,0.0004377396,0.1332495,0.00376179,0.0003986836,0.003621853,0.00004049098,0.00006680537,0.00006328616],"genre_scores_gemma":[0.9408993,0.000550944,0.05355619,0.002932526,0.0002689964,0.001316731,0.0003863421,0.0000344982,0.00005452654],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7095857,"threshold_uncertainty_score":0.9879878,"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."}}