{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T13:11:32Z","timestamp":1776085892705,"version":"3.50.1"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>This systematic review evaluated natural language processing (NLP) approaches for detecting cognitive impairment in electronic health record clinical notes. Following PRISMA guidelines, we analyzed 18 studies (<jats:italic>n<\/jats:italic>\u2009=\u20091,064,530) that employed rule-based algorithms (67%), traditional machine learning (28%), and deep learning (17%). NLP models demonstrated robust performance in identifying cognitive decline, with median sensitivity 0.88 (IQR 0.74\u20130.91) and specificity 0.96 (IQR 0.81\u20130.99). Deep learning architectures achieved superior results, with area under the receiver operating characteristic curves up to 0.997. Major implementation challenges included incomplete electronic health record data capture, inconsistent clinical documentation practices, and limited external validation. While NLP demonstrates promise, successful clinical translation requires establishing standardized approaches, improving access to annotated datasets, and developing equitable deployment frameworks.<\/jats:p>","DOI":"10.1038\/s41746-025-01527-z","type":"journal-article","created":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T07:16:33Z","timestamp":1740813393000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Natural language processing of electronic health records for early detection of cognitive decline: a systematic review"],"prefix":"10.1038","volume":"8","author":[{"given":"Ravi","family":"Shankar","sequence":"first","affiliation":[]},{"given":"Anjali","family":"Bundele","sequence":"additional","affiliation":[]},{"given":"Amartya","family":"Mukhopadhyay","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,3,1]]},"reference":[{"key":"1527_CR1","first-page":"30","volume":"2022","author":"S Gauthier","year":"2021","unstructured":"Gauthier, S., Rosa-Neto, P., Morais, J. A. & Webster, C. World Alzheimer report 2021: journey through the diagnosis of dementia. Alzheimer\u2019s. Dis. Int. 2022, 30 (2021).","journal-title":"Alzheimer\u2019s. Dis. Int."},{"key":"1527_CR2","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1212\/con.0000000000000313","volume":"22","author":"RC Petersen","year":"2016","unstructured":"Petersen, R. C Mild cognitive impairment. Continuum 22, 404\u2013418, https:\/\/doi.org\/10.1212\/con.0000000000000313 (2016).","journal-title":"Continuum"},{"key":"1527_CR3","doi-asserted-by":"publisher","unstructured":"Bai, W. et al. Worldwide prevalence of mild cognitive impairment among community dwellers aged 50 years and older: a meta-analysis and systematic review of epidemiology studies. Age Ageing 51, https:\/\/doi.org\/10.1093\/ageing\/afac173 (2022).","DOI":"10.1093\/ageing\/afac173"},{"key":"1527_CR4","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1016\/j.jalz.2017.12.006","volume":"14","author":"J Jia","year":"2018","unstructured":"Jia, J. et al. The cost of Alzheimer\u2019s disease in China and re-estimation of costs worldwide. Alzheimers Dement. 14, 483\u2013491 (2018).","journal-title":"Alzheimers Dement."},{"key":"1527_CR5","first-page":"101580","volume":"51","author":"A Nandi","year":"2022","unstructured":"Nandi, A. et al. Global and regional projections of the economic burden of Alzheimer\u2019s disease andrelated dementias from 2019 to 2050: a value of statistical life approach. E. Clin. Med. 51, 101580 (2022).","journal-title":"E. Clin. Med."},{"key":"1527_CR6","doi-asserted-by":"publisher","first-page":"2255","DOI":"10.1016\/S0140-6736(15)60461-5","volume":"385","author":"T Ngandu","year":"2015","unstructured":"Ngandu, T. et al. A 2 year multidomain intervention of diet, exercise, cognitive training, and vascular risk monitoring versus control to prevent cognitive decline in at-risk elderly people (FINGER): a randomised controlled trial. Lancet 385, 2255\u20132263 (2015).","journal-title":"Lancet"},{"key":"1527_CR7","doi-asserted-by":"publisher","first-page":"1036","DOI":"10.15585\/mmwr.mm6737a4","volume":"67","author":"BS Olivari","year":"2018","unstructured":"Olivari, B. S. et al. CDC grand rounds: promoting well-being and independence in older adults. MMWR Morb. Mortal. Wkly Rep. 67, 1036\u20131039 (2018).","journal-title":"MMWR Morb. Mortal. Wkly Rep."},{"key":"1527_CR8","unstructured":"Kane, R. L. et al. Interventions to Prevent Age-Related Cognitive Decline, Mild Cognitive Impairment, and Clinical Alzheimer\u2019s-Type Dementia (Agency for Healthcare Research and Quality, USA, 2017)."},{"key":"1527_CR9","doi-asserted-by":"publisher","first-page":"30","DOI":"10.7326\/M17-1528","volume":"168","author":"M Brasure","year":"2018","unstructured":"Brasure, M. et al. Physical activity interventions in preventing cognitive decline and Alzheimer-type dementia: a systematic review. Ann. Intern. Med. 168, 30\u201338 (2018).","journal-title":"Ann. Intern. Med."},{"key":"1527_CR10","doi-asserted-by":"publisher","first-page":"764","DOI":"10.1001\/jama.2019.22258","volume":"323","author":"CD Patnode","year":"2020","unstructured":"Patnode, C. D. et al. Screening for cognitive impairment in older adults: updated evidence report and systematic review for the US Preventive Services Task Force. JAMA 323, 764\u2013785 (2020).","journal-title":"JAMA"},{"key":"1527_CR11","doi-asserted-by":"publisher","first-page":"e011146","DOI":"10.1136\/bmjopen-2016-011146","volume":"7","author":"L Lang","year":"2017","unstructured":"Lang, L. et al. Prevalence and determinants of undetected dementia in the community: a systematic literature review and a meta-analysis. BMJ Open 7, e011146 (2017).","journal-title":"BMJ Open"},{"key":"1527_CR12","doi-asserted-by":"publisher","first-page":"1131","DOI":"10.1007\/s11606-018-4377-y","volume":"33","author":"H Amjad","year":"2018","unstructured":"Amjad, H. et al. Underdiagnosis of dementia: an observational study of patterns in diagnosis and awareness in US older adults. J. Gen. Intern. Med. 33, 1131\u20131138 (2018).","journal-title":"J. Gen. Intern. Med."},{"key":"1527_CR13","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1055\/s-0038-1634210","volume":"42","author":"CR Weir","year":"2003","unstructured":"Weir, C. R. et al. Direct text entry in electronic progress notes. An evaluation of input errors. Methods Inf. Med. 42, 61\u201367 (2003).","journal-title":"Methods Inf. Med."},{"key":"1527_CR14","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-019-0894-9","volume":"19","author":"JS Obeid","year":"2019","unstructured":"Obeid, J. S. et al. Automated detection of altered mental status in emergency department clinical notes: a deep learning approach. BMC Med. Inf. Decis. Mak. 19, 164 (2019).","journal-title":"BMC Med. Inf. Decis. Mak."},{"key":"1527_CR15","doi-asserted-by":"publisher","first-page":"544","DOI":"10.1136\/amiajnl-2011-000464","volume":"18","author":"PM Nadkarni","year":"2011","unstructured":"Nadkarni, P. M., Ohno-Machado, L. & Chapman, W. W. Natural language processing: an introduction. J. Am. Med Inf. Assoc. 18, 544\u2013551 (2011).","journal-title":"J. Am. Med Inf. Assoc."},{"key":"1527_CR16","doi-asserted-by":"publisher","first-page":"e12239","DOI":"10.2196\/12239","volume":"7","author":"S Sheikhalishahi","year":"2019","unstructured":"Sheikhalishahi, S. et al. Natural language processing of clinical notes on chronic diseases: systematic review. JMIR Med. Inf. 7, e12239 (2019).","journal-title":"JMIR Med. Inf."},{"key":"1527_CR17","doi-asserted-by":"publisher","first-page":"e17984","DOI":"10.2196\/17984","volume":"8","author":"I Spasic","year":"2020","unstructured":"Spasic, I. & Nenadic, G. Clinical text data in machine learning: systematic review. JMIR Med. Inf. 8, e17984 (2020).","journal-title":"JMIR Med. Inf."},{"key":"1527_CR18","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.jbi.2017.07.012","volume":"73","author":"K Kreimeyer","year":"2017","unstructured":"Kreimeyer, K. et al. Natural language processing systems for capturing and standardizing unstructured clinical information: a systematic review. J. Biomed. Inf. 73, 14\u201329 (2017).","journal-title":"J. Biomed. Inf."},{"key":"1527_CR19","doi-asserted-by":"publisher","first-page":"e57926","DOI":"10.2196\/57926","volume":"7","author":"R Prakash","year":"2024","unstructured":"Prakash, R., Dupre, M. E., \u00d8stbye, T. & Xu, H. Extracting critical information from unstructured clinicians\u2019 notes data to identify dementia severity using a rule-based approach: feasibility study. JMIR Aging 7, e57926 (2024).","journal-title":"JMIR Aging"},{"key":"1527_CR20","doi-asserted-by":"publisher","first-page":"ooad014","DOI":"10.1093\/jamiaopen\/ooad014","volume":"6","author":"IY Oh","year":"2023","unstructured":"Oh, I. Y. et al. Extraction of clinical phenotypes for Alzheimer\u2019s disease dementia from clinical notes using natural language processing. JAMIA Open 6, ooad014 (2023).","journal-title":"JAMIA Open"},{"key":"1527_CR21","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-022-01864-z","volume":"22","author":"RB Penfold","year":"2022","unstructured":"Penfold, R. B. et al. Development of a machine learning model to predict mild cognitive impairment using natural language processing in the absence of screening. BMC Med. Inf. Decis. Mak. 22, 129 (2022).","journal-title":"BMC Med. Inf. Decis. Mak."},{"key":"1527_CR22","doi-asserted-by":"publisher","unstructured":"Tyagi, T. et al. Using deep learning to identify patients with cognitive impairment in electronic health records. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2111.09115 (2021).","DOI":"10.48550\/arXiv.2111.09115"},{"key":"1527_CR23","doi-asserted-by":"publisher","first-page":"e2135174","DOI":"10.1001\/jamanetworkopen.2021.35174","volume":"4","author":"L Wang","year":"2021","unstructured":"Wang, L. et al. Development and validation of a deep learning model for earlier detection of cognitive decline from clinical notes in electronic health records. JAMA Netw. Open 4, e2135174 (2021).","journal-title":"JAMA Netw. Open"},{"key":"1527_CR24","doi-asserted-by":"publisher","unstructured":"Du, X. et al. Enhancing early detection of cognitive decline in the elderly: a comparative study utilizing large language models in clinical notes. eBioMedicine 109 https:\/\/doi.org\/10.1016\/j.ebiom.2024.105401 (2024).","DOI":"10.1016\/j.ebiom.2024.105401"},{"key":"1527_CR25","doi-asserted-by":"publisher","first-page":"105146","DOI":"10.1016\/j.ijmedinf.2023.105146","volume":"177","author":"M Zolnoori","year":"2023","unstructured":"Zolnoori, M. et al. HomeADScreen: developing Alzheimer\u2019s disease and related dementia risk identification model in home healthcare. Int. J. Med. Inform. 177, 105146 (2023).","journal-title":"Int. J. Med. Inform."},{"key":"1527_CR26","doi-asserted-by":"publisher","first-page":"1270688","DOI":"10.3389\/fneur.2024.1270688","volume":"15","author":"S Panahi","year":"2024","unstructured":"Panahi, S. et al. Identifying clinical phenotypes of frontotemporal dementia in post-9\/11 era veterans using natural language processing. Front. Neurol. 15, 1270688 (2024).","journal-title":"Front. Neurol."},{"key":"1527_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1017\/S0033291724001922","volume":"54","author":"LL Gibson","year":"2024","unstructured":"Gibson, L. L., Mueller, C., Stewart, R. & Aarsland, D. Characteristics associated with progression to probable dementia with Lewy bodies in a cohort with very late-onset psychosis. Psychol. Med. 54, 1\u201310 (2024).","journal-title":"Psychol. Med."},{"key":"1527_CR28","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1007\/s41666-023-00125-6","volume":"7","author":"LC Maclagan","year":"2023","unstructured":"Maclagan, L. C. et al. Can patients with dementia be identified in primary care electronic medical records using natural language processing? J. Health. Inf. Res. 7, 42\u201358 (2023).","journal-title":"J. Health. Inf. Res."},{"key":"1527_CR29","doi-asserted-by":"publisher","first-page":"e40384","DOI":"10.2196\/40384","volume":"24","author":"A Noori","year":"2022","unstructured":"Noori, A. et al. Development and evaluation of a natural language processing annotation tool to facilitate phenotyping of cognitive status in electronic health records: diagnostic study. J. Med. Internet Res. 24, e40384 (2022).","journal-title":"J. Med. Internet Res."},{"key":"1527_CR30","doi-asserted-by":"publisher","first-page":"e027672","DOI":"10.1161\/JAHA.122.027672","volume":"12","author":"DM Kent","year":"2023","unstructured":"Kent, D. M. et al. Association of incidentally discovered covert cerebrovascular disease identified using natural language processing and future dementia. J. Am. Heart Assoc. 12, e027672 (2023).","journal-title":"J. Am. Heart Assoc."},{"key":"1527_CR31","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1016\/j.jalz.2019.09.084","volume":"16","author":"TH McCoy Jr.","year":"2020","unstructured":"McCoy, T. H. Jr. et al. Stratifying risk for dementia onset using large-scale electronic health record data: a retrospective cohort study. Alzheimers Dement. 16, 531\u2013540 (2020).","journal-title":"Alzheimers Dement."},{"key":"1527_CR32","doi-asserted-by":"publisher","first-page":"529","DOI":"10.7326\/0003-4819-155-8-201110180-00009","volume":"155","author":"PF Whiting","year":"2011","unstructured":"Whiting, P. F. et al. QUADAS-2: a revised tool for the quality assessment of diagnostic accuracy studies. Ann. Intern. Med. 155, 529\u2013536 (2011).","journal-title":"Ann. Intern. Med."},{"key":"1527_CR33","doi-asserted-by":"publisher","unstructured":"Hussein, K. I. et al. Natural language processing to identify patients with cognitive impairment. Preprint at medRxiv https:\/\/doi.org\/10.1101\/2022.02.16.22271085 (2022).","DOI":"10.1101\/2022.02.16.22271085"},{"key":"1527_CR34","doi-asserted-by":"publisher","first-page":"1069","DOI":"10.1002\/gps.5330","volume":"35","author":"D Bishara","year":"2020","unstructured":"Bishara, D. et al. The anticholinergic effect on cognition (AEC) scale-associations with mortality, hospitalisation and cognitive decline following dementia diagnosis. Int. J. Geriatr. Psychiatry 35, 1069\u20131077 (2020).","journal-title":"Int. J. Geriatr. Psychiatry"},{"key":"1527_CR35","doi-asserted-by":"publisher","first-page":"e200334","DOI":"10.1212\/CPJ.0000000000200334","volume":"14","author":"JL Purks","year":"2024","unstructured":"Purks, J. L. et al. Cognitive symptoms in cross-sectional Parkinson disease cohort evaluated by human-in-the-loop machine learning and natural language processing. Neurol. Clin. Pract. 14, e200334 (2024).","journal-title":"Neurol. Clin. Pract."},{"key":"1527_CR36","doi-asserted-by":"publisher","first-page":"111223","DOI":"10.1016\/j.exger.2020.111223","volume":"146","author":"AM Al-Harrasi","year":"2021","unstructured":"Al-Harrasi, A. M. et al. Motor signs in Alzheimer\u2019s disease and vascular dementia: detection through natural language processing, co-morbid features and relationship to adverse outcomes. Exp. Gerontol. 146, 111223 (2021).","journal-title":"Exp. Gerontol."},{"key":"1527_CR37","doi-asserted-by":"publisher","DOI":"10.1186\/s13643-020-01542-z","volume":"10","author":"ML Rethlefsen","year":"2021","unstructured":"Rethlefsen, M. L. et al. PRISMA-S: an extension to the PRISMA Statement for Reporting Literature Searches in Systematic Reviews. Syst. Rev. 10, 39 (2021).","journal-title":"Syst. Rev."},{"key":"1527_CR38","doi-asserted-by":"publisher","unstructured":"Wang, L. et al. Evaluating depressive symptoms and risk of cognitive decline using longitudinal electronic health records. Alzheimers Dement. 19 https:\/\/doi.org\/10.1002\/alz.078877 (2023).","DOI":"10.1002\/alz.078877"}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01527-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01527-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01527-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T07:16:36Z","timestamp":1740813396000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01527-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,1]]},"references-count":38,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1527"],"URL":"https:\/\/doi.org\/10.1038\/s41746-025-01527-z","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,1]]},"assertion":[{"value":"11 November 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 February 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 March 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"133"}}