{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T21:30:56Z","timestamp":1791840656957,"version":"4.3.4"},"reference-count":43,"publisher":"Wiley","issue":"2","license":[{"start":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T00:00:00Z","timestamp":1745452800000},"content-version":"am","delay-in-days":23,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T00:00:00Z","timestamp":1745452800000},"content-version":"vor","delay-in-days":23,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100006108","name":"National Center for Advancing Translational Sciences","doi-asserted-by":"publisher","award":["UL1\u2010TR001450"],"award-info":[{"award-number":["UL1\u2010TR001450"]}],"id":[{"id":"10.13039\/100006108","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000049","name":"National Institute on Aging","doi-asserted-by":"publisher","award":["1K01AG073538\u20100 to SK"],"award-info":[{"award-number":["1K01AG073538\u20100 to SK"]}],"id":[{"id":"10.13039\/100000049","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2242812"],"award-info":[{"award-number":["2242812"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["alz-journals.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["A&D Transl Res & Clin Interv"],"published-print":{"date-parts":[[2025,4]]},"abstract":"Abstract<\/jats:title>\n \n INTRODUCTION<\/jats:title>\n The current standard electronic (e\u2010)phenotype for identifying patients with Alzheimer's disease and related dementias (ADRD) from medical claims data yields suboptimal diagnostic accuracy. This study leveraged artificial intelligence (AI)\u2013based text\u2010classification methods to improve the identification of patients with dementia due to ADRD using clinical notes from electronic health records (EHRs).<\/jats:p>\n <\/jats:sec>\n \n METHODS<\/jats:title>\n \n EHR data for patients aged \u2265 64 (\n N<\/jats:italic>\n = 4000) from an academic medical center were used. The cohort included 1000 patients with ADRD per the Chronic Conditions Warehouse (CCW) algorithm for ADRD (i.e., at least one ADRD International Classification of Diseases, Tenth Revision codes [ICD\u201010 code]) and 3000 matched controls without ADRD (i.e., no CCW codes). We trained several AI\u2010based text\u2010classification models, including bag\u2010of\u2010words models, deep learning, and large language models (LLMs), to make ADRD determinations from clinical notes. The performance of each model was evaluated against \u201cgold standard\u201d manual chart review.\n <\/jats:p>\n <\/jats:sec>\n \n RESULTS<\/jats:title>\n \n A foundational LLM derived from Llama 2 demonstrated superior performance in identifying patients with ADRD (area under the curve [AUC] = 0.9534,\n F<\/jats:italic>\n 1<\/jats:sub>\n score 0.8571) compared to both the current standard CCW algorithm (AUC = 0.8482,\n F<\/jats:italic>\n 1<\/jats:sub>\n score 0.8323, although only the AUC was statistically significantly different) and other AI\u2010based models. Several of the AI\u2010based models, including convolutional neural networks, also outperformed the CCW algorithm.\n <\/jats:p>\n <\/jats:sec>\n \n DISCUSSION<\/jats:title>\n These findings highlight the potential of AI\u2010based text\u2010classification methods to optimize the automated identification of patients with ADRD using rich EHR data. However, the success of this approach depends on the quality of clinical notes, and more work is needed to refine and validate these methods across more diverse data sets.<\/jats:p>\n <\/jats:sec>\n \n Highlights<\/jats:title>\n \n \n \n The current e\u2010phenotype for patients with Alzheimer's disease and related dementias (ADRD) in electronic health records has suboptimal diagnostic accuracy.<\/jats:p>\n <\/jats:list-item>\n \n The study used artificial intelligence (AI)\u2013based text classification methods to improve the detection of patients with ADRD.<\/jats:p>\n <\/jats:list-item>\n \n AI\u2010based models, including convolutional neural networks, outperformed the Chronic Conditions Warehouse algorithm.<\/jats:p>\n <\/jats:list-item>\n <\/jats:list>\n <\/jats:p>\n <\/jats:sec>","DOI":"10.1002\/trc2.70089","type":"journal-article","created":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T02:53:44Z","timestamp":1745549624000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["AI approaches for phenotyping Alzheimer's disease and related dementias using electronic health records"],"prefix":"10.1002","volume":"11","author":[{"given":"Sara","family":"Knox","sequence":"first","affiliation":[{"name":"Department of Health Sciences and Research College of Health Professions Medical University of South Carolina Charleston South Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stephanie","family":"Aghamoosa","sequence":"additional","affiliation":[{"name":"Department of Health Sciences and Research College of Health Professions Medical University of South Carolina Charleston South Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul M.","family":"Heider","sequence":"additional","affiliation":[{"name":"Biomedical Informatics Center Department of Public Health Sciences College of Medicine Medical University of South Carolina Charleston South Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maxwell","family":"Cutty","sequence":"additional","affiliation":[{"name":"Department of Health Sciences and Research College of Health Professions Medical University of South Carolina Charleston South Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Wright","sequence":"additional","affiliation":[{"name":"Biomedical Informatics Center Department of Public Health Sciences College of Medicine Medical University of South Carolina Charleston South Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dmitry","family":"Scherbakov","sequence":"additional","affiliation":[{"name":"Biomedical Informatics Center Department of Public Health Sciences College of Medicine Medical University of South Carolina Charleston South Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gabriel","family":"Hood","sequence":"additional","affiliation":[{"name":"Biomedical Informatics Center Department of Public Health Sciences College of Medicine Medical University of South Carolina Charleston South Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sara A.","family":"Nolin","sequence":"additional","affiliation":[{"name":"Department of Neurology College of Medicine Medical University of South Carolina Charleston South Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jihad S.","family":"Obeid","sequence":"additional","affiliation":[{"name":"Biomedical Informatics Center Department of Public Health Sciences College of Medicine Medical University of South Carolina Charleston South Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,4,24]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jalz.2018.02.016"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jalz.2017.07.714"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1093\/geronb\/gbaa083"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1046\/j.1532\u20105415.2002.50519.x"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.lana.2021.100179"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trci.2019.04.003"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1111\/jgs.17183"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1111\/jgs.15638"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.hjdsi.2020.100430"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1002\/alz.12199"},{"key":"e_1_2_8_12_1","volume-title":"30 CCW Chronic conditions algorithms: Alzheimer's disease","author":"Chronic Conditions Data Warehouse"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1038\/srep46226"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1126\/scitranslmed.3001807"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.2196\/17819"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1532\u20105415.1999.tb04580.x"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1093\/jamiaopen\/ooad014"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.2196\/17784"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1097\/mcg.0000000000001586"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1056\/AIoa2400181"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12911\u2010017\u20100518\u20101"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010018\u201024389\u2010w"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12889\u2010024\u201021123\u20102"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1093\/jamiaopen\/ooae075"},{"key":"e_1_2_8_25_1","doi-asserted-by":"publisher","DOI":"10.1002\/(sici)1097\u20100258(19970715)16:13<1529::aid\u2010sim565>3.0.co;2\u2010h"},{"key":"e_1_2_8_26_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12911\u2010018\u20100723\u20106"},{"key":"e_1_2_8_27_1","volume-title":"1999 Joint SIGDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora","author":"Collins M","year":"1999"},{"key":"e_1_2_8_28_1","volume-title":"Learning with noisy labels","author":"Natarajan N","year":"2013"},{"key":"e_1_2_8_29_1","doi-asserted-by":"publisher","DOI":"10.1093\/pan\/mpl013"},{"key":"e_1_2_8_30_1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511809071"},{"key":"e_1_2_8_31_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"e_1_2_8_32_1","article-title":"Multi\u2010class support vector machines","author":"Weston J","year":"1999","journal-title":"Citeseer"},{"key":"e_1_2_8_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0026683"},{"key":"e_1_2_8_34_1","unstructured":"AbadiM AgarwalA BarhamP et\u00a0al.TensorFlow: Large\u2010Scale Machine Learning on Heterogeneous Systems.2016:arXiv:1603.04467. Accessed July 12 2024. doi:10.48550\/arXiv.1603.04467"},{"key":"e_1_2_8_35_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1412.6980"},{"key":"e_1_2_8_36_1","unstructured":"MikolovT ChenK CorradoG DeanJ.Efficient Estimation of Word Representations in Vector Space. Proceedings of Workshop at ICLR.2013. doi:10.48550\/arXiv.1301.3781"},{"key":"e_1_2_8_37_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2310.06825"},{"key":"e_1_2_8_38_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2106.09685"},{"key":"e_1_2_8_39_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2402.12749"},{"key":"e_1_2_8_40_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2307.09288"},{"key":"e_1_2_8_41_1","article-title":"An Empirical Investigation of Statistical Significance in NLP","author":"Berg\u2010Kirkpatrick T","year":"2012","journal-title":"Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning"},{"key":"e_1_2_8_42_1","doi-asserted-by":"publisher","DOI":"10.2307\/2531595"},{"key":"e_1_2_8_43_1","unstructured":"ZhaoZ WallaceE FengS KleinD SinghS.Calibrate before use: improving few\u2010shot performance of language models. Paper presented at: International Conference on Machine Learning.2021:12697\u201012706."},{"key":"e_1_2_8_44_1","doi-asserted-by":"publisher","DOI":"10.1002\/alz.13859"}],"container-title":["Alzheimer's & Dementia: Translational Research & Clinical Interventions"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/alz-journals.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/trc2.70089","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/alz-journals.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/trc2.70089","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T09:24:41Z","timestamp":1761470681000},"score":1,"resource":{"primary":{"URL":"https:\/\/alz-journals.onlinelibrary.wiley.com\/doi\/10.1002\/trc2.70089"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":43,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["10.1002\/trc2.70089"],"URL":"https:\/\/doi.org\/10.1002\/trc2.70089","archive":["Portico"],"relation":{},"ISSN":["2352-8737","2352-8737"],"issn-type":[{"value":"2352-8737","type":"print"},{"value":"2352-8737","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]},"assertion":[{"value":"2024-11-25","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-22","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-04-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70089"}}