{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T23:57:52Z","timestamp":1775001472205,"version":"3.50.1"},"reference-count":59,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T00:00:00Z","timestamp":1731110400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"name":"National Institute of Aging","award":["AG066462"],"award-info":[{"award-number":["AG066462"]}]},{"DOI":"10.13039\/100000092","name":"National Library of Medicine","doi-asserted-by":"publisher","award":["R01LM009886"],"award-info":[{"award-number":["R01LM009886"]}],"id":[{"id":"10.13039\/100000092","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000092","name":"National Library of Medicine","doi-asserted-by":"publisher","award":["T15LM007079"],"award-info":[{"award-number":["T15LM007079"]}],"id":[{"id":"10.13039\/100000092","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Center for Advancing Clinical and Translational Science","award":["UL1TR001873"],"award-info":[{"award-number":["UL1TR001873"]}]},{"name":"National Center for Advancing Clinical and Translational Science","award":["OT2TR003434"],"award-info":[{"award-number":["OT2TR003434"]}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,1,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>This study aims to automate the prediction of Mini-Mental State Examination (MMSE) scores, a widely adopted standard for cognitive assessment in patients with Alzheimer\u2019s disease, using natural language processing (NLP) and machine learning (ML) on structured and unstructured EHR data.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Materials and Methods<\/jats:title>\n                  <jats:p>We extracted demographic data, diagnoses, medications, and unstructured clinical visit notes from the EHRs. We used Latent Dirichlet Allocation (LDA) for topic modeling and Term-Frequency Inverse Document Frequency (TF-IDF) for n-grams. In addition, we extracted meta-features such as age, ethnicity, and race. Model training and evaluation employed eXtreme Gradient Boosting (XGBoost), Stochastic Gradient Descent Regressor (SGDRegressor), and Multi-Layer Perceptron (MLP).<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We analyzed 1654 clinical visit notes collected between September 2019 and June 2023 for 1000 Alzheimer\u2019s disease patients. The average MMSE score was 20, with patients averaging 76.4 years old, 54.7% female, and 54.7% identifying as White. The best-performing model (ie, lowest root mean squared error (RMSE)) is MLP, which achieved an RMSE of 5.53 on the validation set using n-grams, indicating superior prediction performance over other models and feature sets. The RMSE on the test set was 5.85.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Discussion<\/jats:title>\n                  <jats:p>This study developed a ML method to predict MMSE scores from unstructured clinical notes, demonstrating the feasibility of utilizing NLP to support cognitive assessment. Future work should focus on refining the model and evaluating its clinical relevance across diverse settings.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>We contributed a model for automating MMSE estimation using EHR features, potentially transforming cognitive assessment for Alzheimer\u2019s patients and paving the way for more informed clinical decisions and cohort identification.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/jamia\/ocae274","type":"journal-article","created":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T20:08:33Z","timestamp":1731182913000},"page":"119-128","source":"Crossref","is-referenced-by-count":4,"title":["Mini-mental status examination phenotyping for Alzheimer\u2019s disease patients using both structured and narrative electronic health record features"],"prefix":"10.1093","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4318-5987","authenticated-orcid":false,"given":"Betina","family":"Idnay","sequence":"first","affiliation":[{"name":"Department of Biomedical Informatics, Columbia University Irving Medical Center , New York, NY 10032,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0077-3615","authenticated-orcid":false,"given":"Gongbo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Columbia University Irving Medical Center , New York, NY 10032,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2926-1063","authenticated-orcid":false,"given":"Fangyi","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Columbia University Irving Medical Center , New York, NY 10032,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4679-805X","authenticated-orcid":false,"given":"Casey N","family":"Ta","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Columbia University Irving Medical Center , New York, NY 10032,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthew W","family":"Schelke","sequence":"additional","affiliation":[{"name":"Department of Neurology, Columbia University Irving Medical Center , New York, NY 10032,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Karen","family":"Marder","sequence":"additional","affiliation":[{"name":"Department of Neurology, Columbia University Irving Medical Center , New York, NY 10032,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9624-0214","authenticated-orcid":false,"given":"Chunhua","family":"Weng","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Columbia University Irving Medical Center , New York, NY 10032,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2024,11,9]]},"reference":[{"key":"2024121616122642400_ocae274-B1","doi-asserted-by":"crossref","first-page":"700","DOI":"10.1002\/alz.12638","article-title":"2022 Alzheimer\u2019s disease facts and figures","volume":"18","author":"Alzheimer\u2019s Association","year":"2022","journal-title":"Alzheimers Dement"},{"key":"2024121616122642400_ocae274-B2","doi-asserted-by":"crossref","first-page":"1598","DOI":"10.1002\/alz.13016","article-title":"2023 Alzheimer\u2019s disease facts and figures","volume":"19","author":"Alzheimer\u2019s Association","year":"2023","journal-title":"Alzheimers Dement"},{"key":"2024121616122642400_ocae274-B3","author":"Centers for Disease Control and Prevention","year":"2024"},{"key":"2024121616122642400_ocae274-B4","first-page":"1","article-title":"Deaths: leading causes for 2017","volume":"68","author":"Heron","year":"2019","journal-title":"Natl Vital Stat Rep"},{"key":"2024121616122642400_ocae274-B5","author":"Secretary for Planning and Evaluation [ASPE], A","year":"2021"},{"key":"2024121616122642400_ocae274-B6","author":"World Health Organization"},{"key":"2024121616122642400_ocae274-B7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.12688\/f1000research.14506.1","article-title":"Current understanding of Alzheimer\u2019s disease diagnosis and treatment","volume":"7","author":"Weller","year":"2018","journal-title":"F1000Res"},{"key":"2024121616122642400_ocae274-B8","doi-asserted-by":"crossref","first-page":"102247","DOI":"10.1016\/j.eclinm.2023.102247","article-title":"Identifying underlying patterns in Alzheimer\u2019s disease trajectory: a deep learning approach and Mendelian randomization analysis","volume":"64","author":"Yi","year":"2023","journal-title":"EClinicalMedicine"},{"key":"2024121616122642400_ocae274-B9","first-page":"221","article-title":"Aducanumab: appropriate use recommendations update","volume":"9","author":"Cummings","year":"2022","journal-title":"J Prev Alzheimers Dis."},{"key":"2024121616122642400_ocae274-B10","first-page":"362","article-title":"Lecanemab: appropriate use recommendations","volume":"10","author":"Cummings","year":"2023","journal-title":"J Prev Alzheimers Dis"},{"key":"2024121616122642400_ocae274-B11","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1016\/0022-3956(75)90026-6","article-title":"\u201cMini-mental state\u201d. A practical method for grading the cognitive state of patients for the clinician","volume":"12","author":"Folstein","year":"1975","journal-title":"J Psychiatr Res"},{"key":"2024121616122642400_ocae274-B12","first-page":"CD010783","article-title":"Mini-mental state examination (MMSE) for the detection of Alzheimer\u2019s disease and other dementias in people with mild cognitive impairment (MCI)","volume":"2015","author":"Arevalo-Rodriguez","year":"2015","journal-title":"Cochrane Database Syst Rev"},{"key":"2024121616122642400_ocae274-B13","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1097\/WNN.0b013e318190cf75","article-title":"Clinical trial design issues in mild to moderate Alzheimer disease","volume":"21","author":"Knopman","year":"2008","journal-title":"Cogn Behav Neurol"},{"key":"2024121616122642400_ocae274-B14","first-page":"320","article-title":"The data gap in the EHR for clinical research eligibility screening","volume":"2017","author":"Butler","year":"2018","journal-title":"AMIA Jt Summits Transl Sci Proc"},{"key":"2024121616122642400_ocae274-B15","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1016\/j.ijmedinf.2011.02.003","article-title":"Comparing semi-automatic systems for recruitment of patients to clinical trials","volume":"80","author":"Cuggia","year":"2011","journal-title":"Int J Med Inform"},{"key":"2024121616122642400_ocae274-B16","doi-asserted-by":"crossref","first-page":"e31","DOI":"10.2196\/mental.8097","article-title":"Cognitive assessment of patients with Alzheimer\u2019s disease by telemedicine: pilot study","volume":"5","author":"Carotenuto","year":"2018","journal-title":"JMIR Ment Health."},{"key":"2024121616122642400_ocae274-B17","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1177\/1357633X15615049","article-title":"The effect of telemedicine on cognitive decline in patients with dementia","volume":"23","author":"Kim","year":"2017","journal-title":"J Telemed Telecare."},{"key":"2024121616122642400_ocae274-B18","doi-asserted-by":"crossref","first-page":"339","DOI":"10.3390\/bs12090339","article-title":"Predicting scores on the mini-mental state examination (MMSE) from spontaneous speech","volume":"12","author":"Bueno-Cayo","year":"2022","journal-title":"Behav Sci"},{"key":"2024121616122642400_ocae274-B19","first-page":"761","author":"Morar","year":"2020"},{"key":"2024121616122642400_ocae274-B20","doi-asserted-by":"crossref","first-page":"34567","DOI":"10.1038\/srep34567","article-title":"COMPASS: a computational model to predict changes in MMSE scores 24-months after initial assessment of Alzheimer\u2019s disease","volume":"6","author":"Zhu","year":"2016","journal-title":"Sci Rep"},{"key":"2024121616122642400_ocae274-B21","doi-asserted-by":"crossref","DOI":"10.1002\/alz.043541","article-title":"Prediction of the MMSE up to 6 years ahead with cross-cohort replications","volume":"16","author":"Maheux","year":"2020","journal-title":"Alzheimers Dement"},{"key":"2024121616122642400_ocae274-B22","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1590\/1809-2950\/17030126012019","article-title":"Prediction equation for the mini-mental state examination: influence of education, age, and sex","volume":"26","author":"Mendes","year":"2019","journal-title":"Fisioter Pesqui"},{"key":"2024121616122642400_ocae274-B23","first-page":"8055","article-title":"Calibrating mini-mental state examination scores to predict misdiagnosed dementia patients","volume":"11","author":"Vyas","year":"2021","journal-title":"NATO Adv Sci Inst Ser E Appl Sci"},{"key":"2024121616122642400_ocae274-B24","doi-asserted-by":"crossref","first-page":"364","DOI":"10.1093\/jamia\/ocy173","article-title":"Natural language processing of symptoms documented in free-text narratives of electronic health records: a systematic review","volume":"26","author":"Koleck","year":"2019","journal-title":"J Am Med Inform Assoc"},{"key":"2024121616122642400_ocae274-B25","doi-asserted-by":"crossref","first-page":"1206","DOI":"10.1093\/jamia\/ocy070","article-title":"Unstructured clinical documentation reflecting cognitive and behavioral dysfunction: toward an EHR-based phenotype for cognitive impairment","volume":"25","author":"Gilmore-Bykovskyi","year":"2018","journal-title":"J Am Med Inform Assoc"},{"key":"2024121616122642400_ocae274-B26","doi-asserted-by":"crossref","first-page":"658","DOI":"10.1111\/jgs.14744","article-title":"An automated approach to identifying patients with dementia using electronic medical records","volume":"65","author":"Reuben","year":"2017","journal-title":"J Am Geriatr Soc"},{"key":"2024121616122642400_ocae274-B27","doi-asserted-by":"crossref","DOI":"10.1002\/alz.065899","article-title":"Developing a universal phenotyping algorithm to identify patients with clinically diagnosed and probable Alzheimer\u2019s disease using electronic health record data","volume":"18","author":"Thakkar","year":"2022","journal-title":"Alzheimers Dement"},{"key":"2024121616122642400_ocae274-B28","doi-asserted-by":"crossref","first-page":"110263","DOI":"10.1016\/j.isci.2024.110263","article-title":"Machine learning on longitudinal multi-modal data enables the understanding and prognosis of Alzheimer\u2019s disease progression","volume":"27","author":"Zhang","year":"2024","journal-title":"iScience"},{"key":"2024121616122642400_ocae274-B29","first-page":"2825","author":"Pedregosa","year":"2011"},{"key":"2024121616122642400_ocae274-B30","doi-asserted-by":"crossref","DOI":"10.1201\/9781315108230","volume-title":"Feature Engineering and Selection: A Practical Approach for Predictive Models","author":"Kuhn","year":"2019"},{"key":"2024121616122642400_ocae274-B31","volume-title":"Applied Text Analysis with Python: Enabling Language-Aware Data Products with Machine Learning","author":"Bengfort","year":"2018"},{"key":"2024121616122642400_ocae274-B32","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1162\/coli.08-012-R1-06-90","article-title":"Recognizing contextual polarity: an exploration of features for phrase-level sentiment analysis","volume":"35","author":"Wilson","year":"2009","journal-title":"Comput Linguist Assoc Comput Linguist"},{"key":"2024121616122642400_ocae274-B33","author":"Friedl","year":"2006"},{"key":"2024121616122642400_ocae274-B34","volume-title":"Mastering SpaCy: An End-to-End Practical Guide to Implementing NLP Applications Using the Python Ecosystem","author":"Altinok","year":"2021"},{"key":"2024121616122642400_ocae274-B35","author":"Bird","year":"2009"},{"key":"2024121616122642400_ocae274-B36","doi-asserted-by":"crossref","DOI":"10.1201\/9780429298899","volume-title":"Sampling: Design and Analysis","author":"Lohr","year":"2021"},{"key":"2024121616122642400_ocae274-B37","first-page":"993","article-title":"Latent Dirichlet allocation","volume":"3","author":"Blei","year":"2003","journal-title":"J Mach Learn Res"},{"key":"2024121616122642400_ocae274-B38","volume-title":"The Handbook of NLP with Gensim: Leverage Topic Modeling to Uncover Hidden Patterns, Themes, and Valuable Insights within Textual Data","author":"Kuo","year":"2023"},{"key":"2024121616122642400_ocae274-B39","author":"Manning","year":"2009"},{"key":"2024121616122642400_ocae274-B40","first-page":"414","author":"Zhang","year":"2018"},{"key":"2024121616122642400_ocae274-B41","first-page":"19","article-title":"Comparative study on feature selection in Uighur text categorization","volume":"4","author":"Yong","year":"2012","journal-title":"Int J Adv Inf Sci Serv Sci"},{"key":"2024121616122642400_ocae274-B42","doi-asserted-by":"crossref","first-page":"107134","DOI":"10.1016\/j.knosys.2021.107134","article-title":"A comprehensive survey on sentiment analysis: approaches, challenges and trends","volume":"226","author":"Birjali","year":"2021","journal-title":"Knowledge-Based Syst"},{"key":"2024121616122642400_ocae274-B43","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1016\/j.jpsychires.2008.04.014","article-title":"A meta-analysis of the accuracy of the mini-mental state examination in the detection of dementia and mild cognitive impairment","volume":"43","author":"Mitchell","year":"2009","journal-title":"J Psychiatr Res"},{"key":"2024121616122642400_ocae274-B44","first-page":"CD013786","article-title":"Diagnostic test accuracy of telehealth assessment for dementia and mild cognitive impairment","volume":"7","author":"McCleery","year":"2021","journal-title":"Cochrane Database Syst Rev"},{"key":"2024121616122642400_ocae274-B45","doi-asserted-by":"crossref","first-page":"1248","DOI":"10.1002\/gps.3769","article-title":"The association of psychotropic medication use with the cognitive, functional, and neuropsychiatric trajectory of Alzheimer\u2019s disease","volume":"27","author":"Rosenberg","year":"2012","journal-title":"Int J Geriatr Psychiatry."},{"key":"2024121616122642400_ocae274-B46","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1186\/s13195-021-00934-0","article-title":"The association of antidiabetic medications and Mini-Mental State Examination scores in patients with diabetes and dementia","volume":"13","author":"Secnik","year":"2021","journal-title":"Alzheimers Res Ther"},{"key":"2024121616122642400_ocae274-B47","author":"Hofmann","year":"2013"},{"key":"2024121616122642400_ocae274-B48","first-page":"399","author":"R\u00f6der","year":"2015"},{"key":"2024121616122642400_ocae274-B49","first-page":"288","article-title":"Reading tea leaves: how humans interpret topic models","author":"Chang"},{"key":"2024121616122642400_ocae274-B50","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learn"},{"key":"2024121616122642400_ocae274-B51","first-page":"785","author":"Chen","year":"2016"},{"key":"2024121616122642400_ocae274-B52","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1016\/0925-2312(93)90006-O","article-title":"Backpropagation and stochastic gradient descent method","volume":"5","author":"Amari","year":"1993","journal-title":"Neurocomputing"},{"key":"2024121616122642400_ocae274-B53","first-page":"1","author":"Rana","year":"2018"},{"key":"2024121616122642400_ocae274-B54","doi-asserted-by":"crossref","first-page":"2386","DOI":"10.1001\/jama.1993.03500180078038","article-title":"Population-based norms for the Mini-Mental State Examination by age and educational level","volume":"269","author":"Crum","year":"1993","journal-title":"JAMA"},{"key":"2024121616122642400_ocae274-B55","first-page":"1137","article-title":"A study of cross-validation and bootstrap for accuracy estimation and model selection","volume":"14","author":"Kohavi","year":"1995","journal-title":"IJCAI"},{"key":"2024121616122642400_ocae274-B56","doi-asserted-by":"crossref","first-page":"857","DOI":"10.1001\/archneur.56.7.857","article-title":"Variability in annual Mini-Mental State Examination score in patients with probable Alzheimer disease: a clinical perspective of data from the Consortium to Establish a Registry for Alzheimer\u2019s Disease","volume":"56","author":"Clark","year":"1999","journal-title":"Arch Neurol"},{"key":"2024121616122642400_ocae274-B57","doi-asserted-by":"publisher","author":"Jethani","year":"2024","DOI":"10.1101\/2023.07.10.23292373"},{"key":"2024121616122642400_ocae274-B58","doi-asserted-by":"crossref","first-page":"420","DOI":"10.1002\/gps.5030","article-title":"Using electronic health records to estimate the prevalence of agitation in Alzheimer disease\/dementia","volume":"34","author":"Halpern","year":"2019","journal-title":"Int J Geriatr Psychiatry."},{"key":"2024121616122642400_ocae274-B59","doi-asserted-by":"crossref","DOI":"10.1093\/med\/9780199685219.001.0001","volume-title":"Health Measurement Scales: A Practical Guide to Their Development and Use","author":"Streiner","year":"2015"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/32\/1\/119\/61202032\/ocae274.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/32\/1\/119\/61202032\/ocae274.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T16:13:04Z","timestamp":1734365584000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/32\/1\/119\/7888957"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,9]]},"references-count":59,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,11,9]]},"published-print":{"date-parts":[[2025,1,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocae274","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,1]]},"published":{"date-parts":[[2024,11,9]]}}}