{"id":"W7117364293","doi":"10.2196/77409","title":"A Sentence Classification–Based Medical Status Extraction Pipeline for Electronic Health Records: Institutional Case Study","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Information extraction; Sentence; Medical record; Medical information; Electronic health record; Health records; Electronic medical record; Health informatics","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":[0.003991818,0.0005594453,0.0002854578,0.001329797,0.0007684309,0.0009991456,0.001001997,0.0008785538,0.001840676],"category_scores_gemma":[0.01156853,0.0002216437,0.0005053896,0.001239421,0.0005474263,0.001084631,0.00120452,0.0006818076,0.0007615414],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001191198,"about_ca_system_score_gemma":0.001527356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007432667,"about_ca_topic_score_gemma":0.01136611,"domain_scores_codex":[0.9979814,0.0009616489,0.0002974777,0.0003869715,0.0002778551,0.0000945515],"domain_scores_gemma":[0.9903324,0.006795982,0.0005631934,0.0007212771,0.00128764,0.0002993561],"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":[0.001720357,0.001438007,0.2195233,0.003338879,0.0003595443,0.028576,0.01863137,0.02555305,0.05930386,0.004161397,0.04668292,0.5907114],"study_design_scores_gemma":[0.0006742887,0.002155422,0.2267387,0.0008656834,0.001013737,0.02076025,0.02319983,0.3345495,0.2152683,0.008878254,0.1654301,0.000466009],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8430003,0.0007154336,0.1320491,0.00310938,0.0001153476,0.001461751,0.01012658,0.005214955,0.004207158],"genre_scores_gemma":[0.7486438,0.0003452723,0.2380545,0.0004546766,0.00007213298,0.0005196448,0.01006307,0.0002332668,0.001613723],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007432667,"threshold_uncertainty_score":0.02111095,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03488286215087998,"score_gpt":0.4077768561638938,"score_spread":0.3728939940130138,"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."}}