{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T10:21:05Z","timestamp":1789381265510,"version":"build-2803163510"},"reference-count":36,"publisher":"JMIR Publications Inc.","issue":"6","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Inform"],"abstract":"\n Background<\/jats:title>\n Clinical trials need efficient tools to assist in recruiting patients at risk of Alzheimer disease and related dementias (ADRD). Early detection can also assist patients with financial planning for long-term care. Clinical notes are an important, underutilized source of information in machine learning models because of the cost of collection and complexity of analysis.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aimed to investigate the use of deidentified clinical notes from multiple hospital systems collected over 10 years to augment retrospective machine learning models of the risk of developing ADRD.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n We used 2 years of data to predict the future outcome of ADRD onset. Clinical notes are provided in a deidentified format with specific terms and sentiments. Terms in clinical notes are embedded into a 100-dimensional vector space to identify clusters of related terms and abbreviations that differ across hospital systems and individual clinicians.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n When using clinical notes, the area under the curve (AUC) improved from 0.85 to 0.94, and positive predictive value (PPV) increased from 45.07% (25,245\/56,018) to 68.32% (14,153\/20,717) in the model at disease onset. Models with clinical notes improved in both AUC and PPV in years 3-6 when notes\u2019 volume was largest; results are mixed in years 7 and 8 with the smallest cohorts.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n Although clinical notes helped in the short term, the presence of ADRD symptomatic terms years earlier than onset adds evidence to other studies that clinicians undercode diagnoses of ADRD. De-identified clinical notes increase the accuracy of risk models. Clinical notes collected across multiple hospital systems via natural language processing can be merged using postprocessing techniques to aid model accuracy.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/17819","type":"journal-article","created":{"date-parts":[[2020,3,25]],"date-time":"2020-03-25T02:01:48Z","timestamp":1585101708000},"page":"e17819","source":"Crossref","is-referenced-by-count":29,"title":["Predicting Onset of Dementia Using Clinical Notes and Machine Learning: Case-Control Study"],"prefix":"10.2196","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2480-4236","authenticated-orcid":false,"given":"Christopher A","family":"Hane","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3979-7577","authenticated-orcid":false,"given":"Vijay S","family":"Nori","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8822-2737","authenticated-orcid":false,"given":"William H","family":"Crown","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3713-171X","authenticated-orcid":false,"given":"Darshak M","family":"Sanghavi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3005-0864","authenticated-orcid":false,"given":"Paul","family":"Bleicher","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2020,6,3]]},"reference":[{"key":"ref1","unstructured":"Alzheimer's Disease International2019-06-15World Alzheimer Report 2011: The Benefits of Early Diagnosis and Interventionhttps:\/\/www.alz.co.uk.\/research\/world-report-2011,"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1377\/hlthaff.2013.1314"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.jalz.2013.11.006"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.14569\/ijacsa.2015.061202"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0b013e3181a81636"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/S2213-8587(13)70048-2"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.jalz.2013.05.1772"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-4422(06)70537-3"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1001\/archneurol.2010.136"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18553\/jmcp.2018.24.11.1138"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0203246"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.trci.2019.10.006"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-018-0029-1"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1377\/hlthaff.2014.0038"},{"key":"ref15","unstructured":"Optum20192019-07-15Clinformatics Data Marthttps:\/\/www.optum.com\/content\/dam\/optum\/resources\/productSheets\/Clinformatics_for_Data_Mart.pdf"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.surg.2018.02.002"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11135-006-9018-6"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1111\/j.1600-0587.2012.07348.x"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2012.00044"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1198\/106186008x344522"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-9-307"},{"key":"ref22","unstructured":"FastText2019-07-15What is FastText?https:\/\/fasttext.cc\/index.html"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/e17-2068"},{"key":"ref24","unstructured":"The R Project for Statistical Computing20172017-01-06R: A Language and Environment for Statistical Computinghttps:\/\/www.R-project.org\/"},{"key":"ref25","unstructured":"LightGBM's Documentation!-Read the Docs2019-07-15Welcome to LightGBM\u2019s Documentation!https:\/\/lightgbm.readthedocs.io\/en\/latest\/"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1013203451"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/089976699300016106"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1111\/j.1532-5415.2004.52301.x"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1111\/j.1532-5415.1999.tb04580.x"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3233\/JAD-131622"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1002\/ejhf.631"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3233\/jad-132363"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/ncpneuro0124"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1111\/j.1525-1497.2005.0126.x"},{"key":"ref35","unstructured":"CruzJSToday's Geriatric Medicine20162020-01-14Amyloid PET Imaging for Alzheimer's Disease Diagnosishttps:\/\/www.todaysgeriatricmedicine.com\/news\/ex_112116.shtml"},{"key":"ref36","author":"Xie, Q","year":"2019","journal-title":"ArXiv"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/medinform.jmir.org\/2020\/6\/e17819","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:21:51Z","timestamp":1782840111000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2020\/6\/e17819"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,3]]},"references-count":36,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2020]]}},"URL":"https:\/\/doi.org\/10.2196\/17819","relation":{"has-preprint":[{"id-type":"doi","id":"10.2196\/preprints.17819","asserted-by":"object"}]},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,6,3]]}}}