{"id":"W4409413640","doi":"10.2147/clep.s504259","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":"Clinical Epidemiology","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"U.S. National Library of Medicine; National Institutes of Health","keywords":"Health records; Medicine; Cognitive impairment; Cognition; Unstructured data; Natural language processing; Electronic health record; Data science; Information retrieval; Data mining; Computer science; Artificial intelligence; Psychiatry; Big data; Health care","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02579949,0.0007765574,0.0004758557,0.002865667,0.0005211326,0.001884354,0.001248454,0.0007537887,0.0006494707],"category_scores_gemma":[0.1004975,0.0002287768,0.001057718,0.001414466,0.0008696052,0.001403108,0.001471901,0.0009543748,0.0004576936],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008799495,"about_ca_system_score_gemma":0.002651973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004073252,"about_ca_topic_score_gemma":0.004674103,"domain_scores_codex":[0.9813809,0.0105881,0.00305825,0.002541699,0.002187483,0.0002436887],"domain_scores_gemma":[0.9255888,0.05366356,0.006570449,0.004600768,0.009169906,0.0004064651],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002231766,0.003622038,0.661817,0.002657812,0.001128163,0.001374961,0.003946912,0.02213652,0.01101124,0.00126598,0.006461767,0.2823458],"study_design_scores_gemma":[0.001674394,0.003100965,0.5398893,0.001678395,0.0007675044,0.003199827,0.00399239,0.3972344,0.02790774,0.007284922,0.01304282,0.0002273607],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.862487,0.0005556922,0.1166939,0.00082274,0.0001123836,0.006165077,0.0106799,0.001066788,0.001416645],"genre_scores_gemma":[0.7084817,0.0002851552,0.2676306,0.0006357275,0.00008695835,0.00413891,0.01844305,0.00005002916,0.0002478276],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02579949,"threshold_uncertainty_score":0.1364424,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1923096115347233,"score_gpt":0.5624915034290198,"score_spread":0.3701818918942965,"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."}}