{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T18:01:15Z","timestamp":1782756075378,"version":"3.54.5"},"reference-count":29,"publisher":"Wiley","issue":"4","license":[{"start":{"date-parts":[[2020,9,10]],"date-time":"2020-09-10T00:00:00Z","timestamp":1599696000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000057","name":"National Institute of General Medical Sciences","doi-asserted-by":"publisher","award":["R01GM105688"],"award-info":[{"award-number":["R01GM105688"]}],"id":[{"id":"10.13039\/100000057","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000025","name":"National Institute of Mental Health","doi-asserted-by":"publisher","award":["R01 MH119177"],"award-info":[{"award-number":["R01 MH119177"]}],"id":[{"id":"10.13039\/100000025","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000025","name":"National Institute of Mental Health","doi-asserted-by":"publisher","award":["R01MH105384"],"award-info":[{"award-number":["R01MH105384"]}],"id":[{"id":"10.13039\/100000025","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Learning Health Systems"],"published-print":{"date-parts":[[2020,10]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Introduction<\/jats:title><jats:p>We sought to assess longitudinal electronic health records (EHRs) using machine learning (ML) methods to computationally derive probable Alzheimer's Disease (AD) and related dementia subphenotypes.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>A retrospective analysis of EHR data from a cohort of 7587 patients seen at a large, multi\u2010specialty urban academic medical center in New York was conducted. Subphenotypes were derived using hierarchical clustering from 792 probable AD patients (cases) who had received at least one diagnosis of AD using their clinical data. The other 6795 patients, labeled as controls, were matched on age and gender with the cases and randomly selected in the ratio of 9:1. Prediction models with multiple ML algorithms were trained on this cohort using 5\u2010fold cross\u2010validation. XGBoost was used to rank the variable importance.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Four subphenotypes were computationally derived. Subphenotype A (n = 273; 28.2%) had more patients with cardiovascular diseases; subphenotype B (n = 221; 27.9%) had more patients with mental health illnesses, such as depression and anxiety; patients in subphenotype C (n = 183; 23.1%) were overall older (mean (SD) age, 79.5 (5.4) years) and had the most comorbidities including diabetes, cardiovascular diseases, and mental health disorders; and subphenotype D (n = 115; 14.5%) included patients who took anti\u2010dementia drugs and had sensory problems, such as deafness and hearing impairment.<\/jats:p><jats:p>The 0\u2010year prediction model for AD risk achieved an area under the receiver operating curve (AUC) of 0.764 (SD: 0.02); the 6\u2010month model, 0.751 (SD: 0.02); the 1\u2010year model, 0.752 (SD: 0.02); the 2\u2010year model, 0.749 (SD: 0.03); and the 3\u2010year model, 0.735 (SD: 0.03), respectively. Based on variable importance, the top\u2010ranked comorbidities included depression, stroke\/transient ischemic attack, hypertension, anxiety, mobility impairments, and atrial fibrillation. The top\u2010ranked medications included anti\u2010dementia drugs, antipsychotics, antiepileptics, and antidepressants.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>Four subphenotypes were computationally derived that correlated with cardiovascular diseases and mental health illnesses. ML algorithms based on patient demographics, diagnosis, and treatment demonstrated promising results in predicting the risk of developing AD at different time points across an individual's lifespan.<\/jats:p><\/jats:sec>","DOI":"10.1002\/lrh2.10246","type":"journal-article","created":{"date-parts":[[2020,9,24]],"date-time":"2020-09-24T12:51:53Z","timestamp":1600951913000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":33,"title":["<scp>Data\u2010driven<\/scp> discovery of probable Alzheimer's disease and related dementia subphenotypes using electronic health records"],"prefix":"10.1002","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5291-5198","authenticated-orcid":false,"given":"Jie","family":"Xu","sequence":"first","affiliation":[{"name":"Department of Population Health Sciences Information Technologies and Services, Weill Cornell Medicine  New York New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Population Health Sciences Information Technologies and Services, Weill Cornell Medicine  New York New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenxing","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Population Health Sciences Information Technologies and Services, Weill Cornell Medicine  New York New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Prakash","family":"Adekkanattu","sequence":"additional","affiliation":[{"name":"Information Technologies and Services, Weill Cornell Medicine  New York New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5116-0555","authenticated-orcid":false,"given":"Pascal","family":"Brandt","sequence":"additional","affiliation":[{"name":"Biomedical Informatics and Medical Education University of Washington  Seattle Washington USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoqian","family":"Jiang","sequence":"additional","affiliation":[{"name":"Department of Health Sciences Research Mayo Clinic  Rochester Minnesota USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Richard C.","family":"Kiefer","sequence":"additional","affiliation":[{"name":"Department of Health Sciences Research Mayo Clinic  Rochester Minnesota USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Luo","sequence":"additional","affiliation":[{"name":"Feinberg School of Medicine Northwestern University  Chicago Illinois USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengsheng","family":"Mao","sequence":"additional","affiliation":[{"name":"Feinberg School of Medicine Northwestern University  Chicago Illinois USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jennifer A.","family":"Pacheco","sequence":"additional","affiliation":[{"name":"Feinberg School of Medicine Northwestern University  Chicago Illinois USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luke V.","family":"Rasmussen","sequence":"additional","affiliation":[{"name":"Feinberg School of Medicine Northwestern University  Chicago Illinois USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiye","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Population Health Sciences Information Technologies and Services, Weill Cornell Medicine  New York New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Richard","family":"Isaacson","sequence":"additional","affiliation":[{"name":"Department of Population Health Sciences Information Technologies and Services, Weill Cornell Medicine  New York New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jyotishman","family":"Pathak","sequence":"additional","affiliation":[{"name":"Department of Population Health Sciences Information Technologies and Services, Weill Cornell Medicine  New York New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2020,9,10]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jalz.2019.01.010"},{"key":"e_1_2_8_3_1","volume-title":"Genes, Environment and Alzheimer's Disease","author":"Lazarov O","year":"2016"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2017.07.002"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0199026"},{"key":"e_1_2_8_6_1","doi-asserted-by":"crossref","first-page":"151225","DOI":"10.1016\/j.apnr.2019.151225","article-title":"Identity and perceptions of quality of life in Alzheimer's disease","volume":"52","author":"Manson A","year":"2019","journal-title":"Appl Nurs Res"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1002\/gps.5262"},{"key":"e_1_2_8_8_1","volume-title":"Alzheimer's Disease Treatment and Family Stress: Directions for Research","author":"Light E","year":"1990"},{"issue":"1","key":"e_1_2_8_9_1","first-page":"1","article-title":"Data\u2010driven identification of endophenotypes of Alzheimer's disease progression: implications for clinical trials and therapeutic interventions","volume":"10","author":"Geifman Nophar","year":"2018","journal-title":"Alzheimer's research & therapy"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1093\/brain\/awy050"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2004.05.006"},{"key":"e_1_2_8_12_1","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1186\/1471-2458-4-12","article-title":"Attrition and bias in the MRC cognitive function and ageing study: an epidemiological investigation","volume":"4","author":"Matthews FE","year":"2004","journal-title":"BMC Public Health"},{"issue":"7","key":"e_1_2_8_13_1","first-page":"423","article-title":"Cognitive and other neuropsychological assessments documented in electronic health records prior to or at Alzheimer's disease diagnosis","volume":"14","author":"Maserejian Nancy Nairi","year":"2018","journal-title":"Alzheimer's Dement"},{"issue":"7","key":"e_1_2_8_14_1","doi-asserted-by":"crossref","first-page":"342","DOI":"10.1016\/j.jalz.2019.06.825","article-title":"Machine learning prediction of future incidence of Alzheimer's disease using population\u2010wide electronic health records","volume":"15","author":"Park J\u2010H","year":"2019","journal-title":"Alzheimer's Dement"},{"issue":"7","key":"e_1_2_8_15_1","doi-asserted-by":"crossref","first-page":"1530","DOI":"10.1016\/j.jalz.2019.08.101","article-title":"An EHR\u2010based cohort Discovery tool for identifying probable AD","volume":"15","author":"Tjandra Donna","year":"2019","journal-title":"Alzheimer's Dement"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00357-014-9161-z"},{"key":"e_1_2_8_17_1","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1016\/j.ins.2016.06.012","article-title":"Mathematical properties of soft cardinality: enhancing Jaccard, Dice and cosine similarity measures with element\u2010wise distance","volume":"367","author":"Jimenez S","year":"2016","journal-title":"Inf Sci"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-020-0256-0"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jalz.2017.10.009"},{"issue":"15","key":"e_1_2_8_20_1","doi-asserted-by":"crossref","first-page":"1695","DOI":"10.2174\/1381612823666170317165350","article-title":"Diabetes\u2010related neurological implications and pharmacogenomics","volume":"24","author":"Rojas\u2010Carranza CA","year":"2018","journal-title":"Curr Pharm Des"},{"key":"e_1_2_8_21_1","doi-asserted-by":"crossref","first-page":"384","DOI":"10.3389\/fncel.2018.00384","article-title":"A novel perspective linkage between kidney function and Alzheimer's disease","volume":"12","author":"Shi Yan","year":"2018","journal-title":"Front Cell Neurosci"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.3233\/JAD-2012-120064"},{"issue":"4","key":"e_1_2_8_23_1","doi-asserted-by":"crossref","first-page":"414","DOI":"10.1080\/00221309.2019.1697637","article-title":"Personality disorders characterized by anxiety predict Alzheimer's disease in women: a case\u2010control studies","volume":"147","author":"Henriques\u2010Calado J","year":"2019","journal-title":"J Gen Psychol"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.3233\/JAD-148004"},{"key":"e_1_2_8_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.nrl.2012.04.001"},{"key":"e_1_2_8_26_1","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1016\/j.ijmedinf.2017.07.002","article-title":"Advancing Alzheimer's research: a review of big data promises","volume":"106","author":"Rui Z","year":"2017","journal-title":"International journal of medical informatics"},{"key":"e_1_2_8_27_1","doi-asserted-by":"publisher","DOI":"10.1002\/gps.381"},{"key":"e_1_2_8_28_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1749-6632.2002.tb04807.x"},{"key":"e_1_2_8_29_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-019-0786-z"},{"issue":"3","key":"e_1_2_8_30_1","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1186\/s12911-019-0781-4","article-title":"Clinical text classification with rule\u2010based features and knowledge\u2010guided convolutional neural networks","volume":"19","author":"Yao L","year":"2019","journal-title":"BMC Med Inform Decis Mak"}],"container-title":["Learning Health Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/lrh2.10246","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/lrh2.10246","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/lrh2.10246","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T18:25:55Z","timestamp":1693851955000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/lrh2.10246"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,10]]},"references-count":29,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2020,10]]}},"alternative-id":["10.1002\/lrh2.10246"],"URL":"https:\/\/doi.org\/10.1002\/lrh2.10246","archive":["Portico"],"relation":{},"ISSN":["2379-6146","2379-6146"],"issn-type":[{"value":"2379-6146","type":"print"},{"value":"2379-6146","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,9,10]]},"assertion":[{"value":"2020-02-18","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-08-06","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-09-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e10246"}}