{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T02:59:56Z","timestamp":1793501996225,"version":"4.5.0"},"posted":{"date-parts":[[2025,12,4]]},"group-title":"Neurology","reference-count":45,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T00:00:00Z","timestamp":1764806400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,12,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:sec>\n                  <jats:title>INTRODUCTION<\/jats:title>\n                  <jats:p>Accurate antemortem differentiation among dementia etiologies remains challenging, particularly for atypical or mixed clinical presentations. Multiplexed plasma proteomics paired with supervised machine-learning offers a minimally invasive and accessible approach for differential diagnosis.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>METHODS<\/jats:title>\n                  <jats:p>Plasma from 194 participants was analyzed using the NULISA CNS 120+ plasma biomarker panel. Differentially abundant protein patterns associated with AD, frontotemporal lobar degeneration, Lewy body disease, and vascular disease were identified. These features were used to train supervised XGBoost classifier models. Models were then applied to participants with mild cognitive impairment to generate data-driven predictions of etiology.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>RESULTS<\/jats:title>\n                  <jats:p>NULISA plasma biomarkers revealed disease-specific protein patterns. XGBoost classifiers differentiated disease etiologies with high specificity. Application of the models to participants with mild cognitive impairment yielded robust etiologic predictions.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>DISCUSSION<\/jats:title>\n                  <jats:p>These results support the feasibility of using multiplexed NULISA plasma proteomics, combined with machine learning, for differential diagnosis of complex neurodegenerative dementia etiologies.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Highlights<\/jats:title>\n                  <jats:list list-type=\"bullet\">\n                    <jats:list-item>\n                      <jats:p>Multiplex plasma proteomics revealed distinct protein markers of dementia subtypes<\/jats:p>\n                    <\/jats:list-item>\n                    <jats:list-item>\n                      <jats:p>Supervised XGBoost classifiers accurately distinguished each dementia etiology<\/jats:p>\n                    <\/jats:list-item>\n                    <jats:list-item>\n                      <jats:p>Model application to unknown etiologies produced interpretable probability profiles<\/jats:p>\n                    <\/jats:list-item>\n                    <jats:list-item>\n                      <jats:p>The combined NULISA-machine learning framework demonstrates diagnostic feasibility<\/jats:p>\n                    <\/jats:list-item>\n                  <\/jats:list>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Research in Context<\/jats:title>\n                  <jats:list list-type=\"order\">\n                    <jats:list-item>\n                      <jats:p>Systematic review: The authors reviewed the literature using traditional sources (e.g. PubMed), meeting abstracts and presentations. NULISA technology has been utilized to analyze blood biomarkers in people with neurological diseases and differential protein expression based on clinical diagnosis and presumed etiologies has been observed. These citations are appropriately cited.<\/jats:p>\n                    <\/jats:list-item>\n                    <jats:list-item>\n                      <jats:p>Interpretation: Our findings indicate that machine learning can be used in combination with NULISA technology to improve etiology prediction in people with dementia.<\/jats:p>\n                    <\/jats:list-item>\n                    <jats:list-item>\n                      <jats:p>Future directions: Future studies using larger, more well-balanced participant cohorts will enable better understanding of the plasma biomarkers and demographic factors that best discriminate between dementia etiologies.<\/jats:p>\n                    <\/jats:list-item>\n                  <\/jats:list>\n                <\/jats:sec>","DOI":"10.64898\/2025.12.02.25340706","type":"posted-content","created":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T11:07:49Z","timestamp":1765278469000},"source":"Crossref","is-referenced-by-count":3,"title":["Dementia etiology classification using NULISA plasma biomarkers and machine learning"],"prefix":"10.64898","author":[{"given":"Kelly N.","family":"DuBois","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Subhamoy","family":"Pal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amanda Cook","family":"Maher","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Judith","family":"Heidebrink","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carol","family":"Persad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bruno M.","family":"Giordani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benjamin M.","family":"Hampstead","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9605-6337","authenticated-orcid":false,"given":"Kelly M.","family":"Bakulski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David G.","family":"Morgan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicholas M.","family":"Kanaan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2025120903053497000_2025.12.02.25340706v1.1","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2018.00181"},{"key":"2025120903053497000_2025.12.02.25340706v1.2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1440-1789.2005.00605.x"},{"key":"2025120903053497000_2025.12.02.25340706v1.3","doi-asserted-by":"publisher","DOI":"10.1002\/alz.13809"},{"key":"2025120903053497000_2025.12.02.25340706v1.4","doi-asserted-by":"crossref","unstructured":"Barker WW , Luis CA , Kashuba A , Luis M , Harwood DG , Loewenstein D , et al. Relative Frequencies of Alzheimer Disease, Lewy Body, Vascular and Frontotemporal Dementia, and Hippocampal Sclerosis in the State of Florida Brain Bank. Alzheimer Disease & Associated Disorders 2002;16:203.","DOI":"10.1097\/00002093-200210000-00001"},{"key":"2025120903053497000_2025.12.02.25340706v1.5","doi-asserted-by":"publisher","DOI":"10.1038\/s41392-024-01911-3"},{"key":"2025120903053497000_2025.12.02.25340706v1.6","doi-asserted-by":"publisher","DOI":"10.1186\/s13024-025-00872-7"},{"key":"2025120903053497000_2025.12.02.25340706v1.7","doi-asserted-by":"publisher","DOI":"10.1038\/nrneurol.2017.96"},{"key":"2025120903053497000_2025.12.02.25340706v1.8","doi-asserted-by":"publisher","DOI":"10.1016\/j.jalz.2018.02.018"},{"key":"2025120903053497000_2025.12.02.25340706v1.9","doi-asserted-by":"publisher","DOI":"10.1002\/alz.13859"},{"key":"2025120903053497000_2025.12.02.25340706v1.10","doi-asserted-by":"publisher","DOI":"10.1093\/brain\/awaa286"},{"key":"2025120903053497000_2025.12.02.25340706v1.11","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0000000000013211"},{"key":"2025120903053497000_2025.12.02.25340706v1.12","doi-asserted-by":"publisher","DOI":"10.1002\/alz.14442"},{"key":"2025120903053497000_2025.12.02.25340706v1.13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ebiom.2024.105322"},{"key":"2025120903053497000_2025.12.02.25340706v1.14","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-42834-x"},{"key":"2025120903053497000_2025.12.02.25340706v1.15","unstructured":"NULISAseq | CNS Disease Panel. Alamar Biosciences n.d. https:\/\/alamarbio.com\/nulisaseq-cns-disease-panel\/ (accessed October 16, 2025)."},{"key":"2025120903053497000_2025.12.02.25340706v1.16","doi-asserted-by":"publisher","DOI":"10.1002\/alz.70166"},{"key":"2025120903053497000_2025.12.02.25340706v1.17","doi-asserted-by":"publisher","DOI":"10.1186\/s13024-024-00753-5"},{"key":"2025120903053497000_2025.12.02.25340706v1.18","doi-asserted-by":"publisher","DOI":"10.1002\/alz.14621"},{"key":"2025120903053497000_2025.12.02.25340706v1.19","doi-asserted-by":"publisher","DOI":"10.1093\/braincomms\/fcaf004"},{"key":"2025120903053497000_2025.12.02.25340706v1.20","doi-asserted-by":"publisher","DOI":"10.1186\/s13024-025-00909-x"},{"key":"2025120903053497000_2025.12.02.25340706v1.21","doi-asserted-by":"publisher","DOI":"10.1002\/alz.70116"},{"key":"2025120903053497000_2025.12.02.25340706v1.22","doi-asserted-by":"publisher","DOI":"10.1002\/alz.70162"},{"key":"2025120903053497000_2025.12.02.25340706v1.23","unstructured":"U-M Memory and Aging Project | University of Michigan Medical School n.d. https:\/\/medresearch.umich.edu\/labs-departments\/centers\/madc\/research\/u-m-memory-and-aging-project (accessed October 16, 2025)."},{"key":"2025120903053497000_2025.12.02.25340706v1.24","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"2025120903053497000_2025.12.02.25340706v1.25","unstructured":"Uniform Data Set version 3 | National Alzheimer\u2019s Coordinating Center n.d. https:\/\/naccdata.org\/data-collection\/forms-documentation\/uds-3 (accessed October 30, 2025)."},{"key":"2025120903053497000_2025.12.02.25340706v1.26","doi-asserted-by":"publisher","DOI":"10.1002\/alz.70778"},{"key":"2025120903053497000_2025.12.02.25340706v1.27","doi-asserted-by":"publisher","DOI":"10.1017\/S1041610297004870"},{"key":"2025120903053497000_2025.12.02.25340706v1.28","doi-asserted-by":"publisher","DOI":"10.1111\/j.1532-5415.2005.53221.x"},{"key":"2025120903053497000_2025.12.02.25340706v1.29","doi-asserted-by":"publisher","DOI":"10.1002\/14651858.CD010775.pub3"},{"key":"2025120903053497000_2025.12.02.25340706v1.30","doi-asserted-by":"publisher","DOI":"10.1111\/j.1532-5415.2005.53221.x"},{"key":"2025120903053497000_2025.12.02.25340706v1.31","doi-asserted-by":"publisher","DOI":"10.1192\/bjp.140.6.566"},{"key":"2025120903053497000_2025.12.02.25340706v1.32","doi-asserted-by":"publisher","DOI":"10.1159\/000089218"},{"key":"2025120903053497000_2025.12.02.25340706v1.33","doi-asserted-by":"publisher","DOI":"10.1001\/archneurol.2010.115"},{"key":"2025120903053497000_2025.12.02.25340706v1.34","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0073377"},{"key":"2025120903053497000_2025.12.02.25340706v1.35","doi-asserted-by":"publisher","DOI":"10.1016\/j.nicl.2018.04.022"},{"key":"2025120903053497000_2025.12.02.25340706v1.36","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkv007"},{"key":"2025120903053497000_2025.12.02.25340706v1.37","doi-asserted-by":"publisher","DOI":"10.5555\/3122009.3122048"},{"key":"2025120903053497000_2025.12.02.25340706v1.38","first-page":"321","article-title":"SMOTE: synthetic minority over-sampling technique","volume":"16","year":"2002","journal-title":"J Artif Int Res"},{"key":"2025120903053497000_2025.12.02.25340706v1.39","unstructured":"Berta E , Bach F , Jordan M . Classifier Calibration with ROC-Regularized Isotonic Regression. Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, PMLR; 2024, p. 1972\u201380."},{"key":"2025120903053497000_2025.12.02.25340706v1.40","unstructured":"Platt J . Probabilistic Outputs for Support vector Machines and Comparisons to Regularized Likelihood Methods, 1999."},{"key":"2025120903053497000_2025.12.02.25340706v1.41","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"2025120903053497000_2025.12.02.25340706v1.42","unstructured":"CalibratedClassifierCV. Scikit-Learn n.d. https:\/\/scikit-learn\/stable\/modules\/generated\/sklearn.calibration.CalibratedClassifierCV.html (accessed October 30, 2025)."},{"key":"2025120903053497000_2025.12.02.25340706v1.43","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0138-9"},{"key":"2025120903053497000_2025.12.02.25340706v1.44","doi-asserted-by":"publisher","DOI":"10.1136\/jnnp.74.9.1206"},{"key":"2025120903053497000_2025.12.02.25340706v1.45","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.58.11.1615"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2025.12.02.25340706","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T11:07:54Z","timestamp":1765278474000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.64898\/2025.12.02.25340706"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,4]]},"references-count":45,"URL":"https:\/\/doi.org\/10.64898\/2025.12.02.25340706","relation":{},"subject":[],"published":{"date-parts":[[2025,12,4]]},"subtype":"preprint"}}