{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T13:40:40Z","timestamp":1787319640435,"version":"build-2736575974"},"posted":{"date-parts":[[2025,11,6]]},"group-title":"Health Informatics","reference-count":33,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T00:00:00Z","timestamp":1762387200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,11,10]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:sec>\n                  <jats:title>INTRODUCTION<\/jats:title>\n                  <jats:p>There is need to detect and intervene in pre-clinical phases of Alzheimer\u2019s disease (AD). Electronic health records (EHRs) may help predict AD using machine learning methods.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>METHODS<\/jats:title>\n                  <jats:p>We identified EHRs for 19,473 cases with AD and 111,922 controls. Records spanned 10 or more years prior to AD diagnosis. We trained a random forest model (employing 5-fold cross-validation with 2,499 features) to predict AD 10 years prior to its onset using a 75\/25% train\/test split and then computed permuted feature importance.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>RESULTS<\/jats:title>\n                  <jats:p>We achieved an area under the ROC curve of 0.80. Feature importance identified factors associated with AD, including age, sex, race, ethnicity, BMI, cardiovascular diseases, inflammation, pain, sleep and mood disorders, trauma, other neurodegenerative disorders, diuretics, colon-related disorders and procedures, seizures, and vitamin B12.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>DISCUSSION<\/jats:title>\n                  <jats:p>This is the first EHR-based model to predict AD 10 years prior to onset, which could help predict AD and inform prevention\/early intervention.<\/jats:p>\n                <\/jats:sec>","DOI":"10.1101\/2025.11.04.25338396","type":"posted-content","created":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T20:30:18Z","timestamp":1762461018000},"source":"Crossref","is-referenced-by-count":1,"title":["Predicting Alzheimer\u2019s Disease Diagnosis, a Decade or more Years before Onset using the Electronic Health Record and Random Forest Machine Learning Models"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1707-1617","authenticated-orcid":false,"given":"Sanya B.","family":"Taneja","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2993-2085","authenticated-orcid":false,"given":"Richard D.","family":"Boyce","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1696-1781","authenticated-orcid":false,"given":"Scott A.","family":"Malec","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6786-9956","authenticated-orcid":false,"given":"Steven M.","family":"Albert","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3016-1951","authenticated-orcid":false,"given":"C. Elizabeth","family":"Shaaban","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arthur S.","family":"Levine","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul","family":"Munro","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2238-5429","authenticated-orcid":false,"given":"Jiang","family":"Bian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5291-5198","authenticated-orcid":false,"given":"Jie","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5351-3983","authenticated-orcid":false,"given":"Demetrius","family":"Maraganore","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1771-3157","authenticated-orcid":false,"given":"Karen","family":"Schliep","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9252-6039","authenticated-orcid":false,"given":"Jonathan C.","family":"Silverstein","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9793-494X","authenticated-orcid":false,"given":"Michelle","family":"Kienholz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9286-0694","authenticated-orcid":false,"given":"Helmet T.","family":"Karim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2025111200504772000_2025.11.04.25338396v2.1","doi-asserted-by":"crossref","unstructured":"2025 Alzheimer\u2019s disease facts and figures. Alzheimers & Dementia 2025; 21:","DOI":"10.1002\/alz.70235"},{"key":"2025111200504772000_2025.11.04.25338396v2.2","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.o2094"},{"key":"2025111200504772000_2025.11.04.25338396v2.3","doi-asserted-by":"crossref","first-page":"197","DOI":"10.14283\/jpad.2022.30","article-title":"Two Randomized Phase 3 Studies of Aducanumab in Early Alzheimer\u2019s Disease","volume":"9","year":"2022","journal-title":"J Prev Alzheimers Dis"},{"key":"2025111200504772000_2025.11.04.25338396v2.4","doi-asserted-by":"publisher","DOI":"10.1056\/NEJ-Moa2212948"},{"key":"2025111200504772000_2025.11.04.25338396v2.5","doi-asserted-by":"crossref","first-page":"506","DOI":"10.1038\/s43587-023-00403-3","article-title":"Blood biomarkers for Alzheimer\u2019s disease in clinical practice and trials","volume":"3","year":"2023","journal-title":"Nat Aging"},{"key":"2025111200504772000_2025.11.04.25338396v2.6","doi-asserted-by":"publisher","DOI":"10.1126\/scitranslmed.adg4122"},{"key":"2025111200504772000_2025.11.04.25338396v2.7","doi-asserted-by":"crossref","first-page":"520","DOI":"10.1038\/s43587-023-00410-4","article-title":"Detection and treatment of Alzheimer\u2019s disease in its preclinical stage","volume":"3","year":"2023","journal-title":"Nat Aging"},{"key":"2025111200504772000_2025.11.04.25338396v2.8","doi-asserted-by":"publisher","DOI":"10.1126\/scitranslmed.adf5681"},{"key":"2025111200504772000_2025.11.04.25338396v2.9","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1202753"},{"key":"2025111200504772000_2025.11.04.25338396v2.10","doi-asserted-by":"publisher","DOI":"10.1002\/msj.20157"},{"key":"2025111200504772000_2025.11.04.25338396v2.11","first-page":"157","article-title":"From Brain Disease to Brain Health: Primary Prevention of Alzheimer\u2019s Disease and Related Disorders in a Health System Using an Electronic Medical Record-Based Approach","volume":"4","year":"2017","journal-title":"J Prev Alzheimers Dis"},{"key":"2025111200504772000_2025.11.04.25338396v2.12","doi-asserted-by":"crossref","first-page":"968","DOI":"10.1001\/jamaneurol.2022.2967","article-title":"The ATN framework\u2014moving preclinical Alzheimer disease to clinical relevance","volume":"79","year":"2022","journal-title":"JAMA neurology"},{"key":"2025111200504772000_2025.11.04.25338396v2.13","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(24)00064-X"},{"key":"2025111200504772000_2025.11.04.25338396v2.14","first-page":"799","article-title":"Deep Learning Prediction of Mild Cognitive Impairment using Electronic Health Records","volume":"2019","year":"2019","journal-title":"Proceedings (IEEE Int Conf Bioinformatics Biomed)"},{"key":"2025111200504772000_2025.11.04.25338396v2.15","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1038\/s41746-020-0256-0","article-title":"Machine learning prediction of incidence of Alzheimer\u2019s disease using large-scale administrative health data","volume":"3","year":"2020","journal-title":"NPJ Digit Med"},{"key":"2025111200504772000_2025.11.04.25338396v2.16","doi-asserted-by":"crossref","unstructured":"Zhu W , Razavian N : Variationally regularized graph-based representation learning for electronic health records, 2021","DOI":"10.1145\/3450439.3451855"},{"key":"2025111200504772000_2025.11.04.25338396v2.17","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0203246"},{"key":"2025111200504772000_2025.11.04.25338396v2.18","unstructured":"Li Q , Yang X , Xu J , et al: Early prediction of Alzheimer\u2019s disease and related dementias using real-world electronic health records. Alzheimers Dement 2023;"},{"key":"2025111200504772000_2025.11.04.25338396v2.19","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1038\/s43587-024-00573-8","article-title":"Leveraging electronic health records and knowledge networks for Alzheimer\u2019s disease prediction and sex-specific biological insights","volume":"4","year":"2024","journal-title":"Nat Aging"},{"key":"2025111200504772000_2025.11.04.25338396v2.20","doi-asserted-by":"crossref","first-page":"601","DOI":"10.1093\/jamia\/ocab204","article-title":"An atomic approach to the design and implementation of a research data warehouse","volume":"29","year":"2022","journal-title":"J Am Med Inform Assoc"},{"key":"2025111200504772000_2025.11.04.25338396v2.21","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocy032"},{"key":"2025111200504772000_2025.11.04.25338396v2.22","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1016\/j.inffus.2021.11.011","article-title":"Tabular data: Deep learning is not all you need","volume":"81","year":"2022","journal-title":"Information Fusion"},{"key":"2025111200504772000_2025.11.04.25338396v2.23","doi-asserted-by":"publisher","DOI":"10.2147\/CLEP.S206770"},{"key":"2025111200504772000_2025.11.04.25338396v2.24","doi-asserted-by":"crossref","first-page":"S165","DOI":"10.3233\/JAD-190181","article-title":"A Systematic Review of Meta-Analyses that Evaluate Risk Factors for Dementia to Evaluate the Quantity, Quality, and Global Representativeness of Evidence","volume":"70","year":"2019","journal-title":"J Alzheimers Dis"},{"key":"2025111200504772000_2025.11.04.25338396v2.25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuro.2017.03.006"},{"key":"2025111200504772000_2025.11.04.25338396v2.26","doi-asserted-by":"crossref","first-page":"104916","DOI":"10.1016\/j.archger.2022.104916","article-title":"Height loss as an indicator of ageing through its association with frailty and sarcopenia: An observational cohort study","volume":"110","year":"2023","journal-title":"Arch Gerontol Geriatr"},{"key":"2025111200504772000_2025.11.04.25338396v2.27","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-28273-0"},{"key":"2025111200504772000_2025.11.04.25338396v2.28","doi-asserted-by":"crossref","first-page":"104368","DOI":"10.1016\/j.jbi.2023.104368","article-title":"Causal feature selection using a knowledge graph combining structured knowledge from the biomedical literature and ontologies: A use case studying depression as a risk factor for Alzheimer\u2019s disease","volume":"142","year":"2023","journal-title":"J Biomed Inform"},{"key":"2025111200504772000_2025.11.04.25338396v2.29","doi-asserted-by":"publisher","DOI":"10.1186\/s13195-021-00875-8"},{"key":"2025111200504772000_2025.11.04.25338396v2.30","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1186\/s13195-021-00827-2","article-title":"Brain Health Services: organization, structure, and challenges for implementation. A user manual for Brain Health Services-part 1 of 6","volume":"13","year":"2021","journal-title":"Alzheimers Res Ther"},{"key":"2025111200504772000_2025.11.04.25338396v2.31","doi-asserted-by":"crossref","unstructured":"Li Y , Yen D , Hendrix RD , et al: Timing of Biomarker Changes in Sporadic Alzheimer\u2019s Disease in Estimated Years from Symptom Onset. Ann Neurol 2024;","DOI":"10.1002\/ana.26891"},{"key":"2025111200504772000_2025.11.04.25338396v2.32","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa2310168"},{"key":"2025111200504772000_2025.11.04.25338396v2.33","doi-asserted-by":"publisher","DOI":"10.1056\/NEJ-Moa2212948"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.11.04.25338396","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T20:50:30Z","timestamp":1768510230000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.1101\/2025.11.04.25338396"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,6]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1101\/2025.11.04.25338396","relation":{},"subject":[],"published":{"date-parts":[[2025,11,6]]},"subtype":"preprint"}}