{"doi":"10.1016/j.jamda.2025.105949","title":"An Electronic Health Record Algorithm's Performance to Identify Cognitive Impairment in Primary Care","abstract":"OBJECTIVES: Most people with dementia are diagnosed and cared for in primary care. We examined the performance of an electronic health record (EHR) algorithm to identify older adults with dementia or mild cognitive impairment in primary care. DESIGN: Retrospective cohort study. SETTING AND PARTICIPANTS: We identified all adults aged 65+ seen for a routine visit from December 2021 to December 2022 in 59 primary care clinics. We used representative sampling to create a cohort of 525 older adults. METHODS: Revision (ICD-10) codes and prescribed dementia medications to the cohort and evaluated the algorithm's performance characteristics. RESULTS: Of the representative cohort (n = 525), 59% were women and 81% were White, with an average age of 74.5 ± 6.9 years. Dementia or mild cognitive impairment was present on EHR review in 8.6% (n = 45) of the cohort. The algorithm had a specificity of 98.1%, a sensitivity of 60.0%, a positive predictive value of 0.75, and a negative predictive value of 0.96. The overall predictive performance (F-1 score) was 0.667. Nonspecific ICD-10 was the most common, with \"unspecified dementia\" representing 17 of 34 ICD-10 codes found by the algorithm. CONCLUSIONS AND IMPLICATIONS: Optimization of an EHR algorithm to detect cognitive impairment by combining cognitive impairment-related ICD-10 codes and dementia medications identified people with dementia or mild cognitive impairment in primary care with high specificity and acceptable sensitivity, although ICD-10 codes remained nonspecific.","journal":"Journal of the American Medical Directors Association","year":2025,"id":579135,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":0,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.8882,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2025-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1489780,"name":"Molly E. Lynch","orcid":null,"position":1,"is_corresponding":false},{"id":381755,"name":"Feng‐Chang Lin","orcid":"0000-0002-2638-1775","position":2,"is_corresponding":false},{"id":1489380,"name":"Yumei Yang","orcid":"0000-0002-7554-1050","position":3,"is_corresponding":false},{"id":850887,"name":"Winfred Frazier","orcid":"0000-0003-3373-0918","position":4,"is_corresponding":false},{"id":396956,"name":"Laura C. Hanson","orcid":"0000-0001-5120-6058","position":5,"is_corresponding":false},{"id":282008,"name":"Christine E. Kistler","orcid":"0000-0003-0566-5741","position":0,"is_corresponding":true}],"reference_count":25,"raw_metadata":null,"created_at":"2026-07-19T02:58:30.282164Z","pmid":"41135594","pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}