{"id":"W7000503561","doi":"","title":"Extracting Cognitive Impairment Assessment Information From Unstructured Notes in Electronic Health Records Using Natural Language Processing Tools: Validation with Clinical Assessment Data","year":2025,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Minimum Data Set; Montreal Cognitive Assessment; Cohort; Medical record; Cognition; Cognitive impairment; Medicaid; Electronic health record; Hebrew","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.005268188,0.00032418,0.0007591103,0.00080747,0.0004115805,0.003151322,0.003197968,0.0001160588,0.0001331771],"category_scores_gemma":[0.0008660993,0.0002842215,0.00006742031,0.001581392,0.00005783117,0.01189323,0.001743347,0.001653928,7.668266e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009476196,"about_ca_system_score_gemma":0.00368666,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007519652,"about_ca_topic_score_gemma":0.0007653034,"domain_scores_codex":[0.9946609,0.001397908,0.001743952,0.0007119112,0.0009043366,0.0005810454],"domain_scores_gemma":[0.994837,0.001454018,0.002357313,0.0007749115,0.0004243494,0.0001523975],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00008875617,0.0001055247,0.5154874,0.0001579587,0.00007154889,0.000007664719,0.0005115363,0.0009847464,0.000177833,0.00004872224,0.00007169724,0.4822867],"study_design_scores_gemma":[0.0009053046,0.00003909682,0.7679564,0.00192367,0.00003236175,0.000009375582,0.0004426918,0.2274703,0.0002370594,0.0006360866,0.00008536384,0.0002622165],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6686037,0.004142347,0.3245724,0.0007972489,0.0005880946,0.001024695,0.00004770878,0.0000690676,0.0001548163],"genre_scores_gemma":[0.9464074,0.0006753972,0.05178628,0.0006749852,0.00009625925,0.00002625346,0.0003120353,0.00001816454,0.000003184557],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4820244,"threshold_uncertainty_score":0.999961,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2702322639910404,"score_gpt":0.6372681409762044,"score_spread":0.367035876985164,"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."}}