{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T13:10:27Z","timestamp":1768569027422,"version":"3.49.0"},"posted":{"date-parts":[[2025,7,16]]},"group-title":"Health Informatics","reference-count":11,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T00:00:00Z","timestamp":1752624000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,7,16]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                <jats:p>\n                  Dementia, one of the most prevalent neurodegenerative diseases, affects millions worldwide. Understanding linguistic markers of dementia is crucial for elucidating how cognitive decline manifests in speech patterns. Current non-invasive assessments like the Montreal Cognitive Assessment (MoCA) and Saint Louis University Mental Status (SLUMS) tests rely on manual interpretation and often lack detailed linguistic insight. This paper introduces a first-of-its-kind interpretable artificial intelligence (IAI) framework,\n                  <jats:italic>CharMark<\/jats:italic>\n                  , which leverages first-order Markov Chain models to characterize language production at the character level. By computing steadystate probabilities of character transitions in speech transcripts from individuals with dementia and healthy controls, we uncover distinctive character-usage patterns. The space character \u201c\u201c, representing pauses, and letters such as \u201c\n                  <jats:monospace>n<\/jats:monospace>\n                  \u201d and \u201c\n                  <jats:monospace>i<\/jats:monospace>\n                  \u201d showed statistically significant differences between groups. Principal Component Analysis (PCA) revealed natural clustering aligned with cognitive status, while Kolmogorov-Smirnov tests confirmed distributional shifts. A Lasso Logistic Regression model further demonstrated that these character-level features possess strong discriminative potential. Our primary contribution is the identification and characterization of candidate linguistic biomarkers of cognitive decline; features that are both interpretable and easily computable. These findings highlight the potential of character-level modeling as a lightweight, scalable strategy for early-stage dementia screening, particularly in settings where more complex or audio-dependent models may be impractical.\n                <\/jats:p>","DOI":"10.1101\/2025.07.14.25331543","type":"posted-content","created":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T23:10:13Z","timestamp":1752707413000},"source":"Crossref","is-referenced-by-count":0,"title":["CharMark: A Markov Approach to Linguistic Biomarkers in Dementia"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-8584-6693","authenticated-orcid":false,"given":"Kevin","family":"Mekulu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Faisal","family":"Aqlan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"54368","reference":[{"key":"2025071813451229000_2025.07.14.25331543v1.1","unstructured":"Alzheimer\u2019s Disease International (2021). World Alzheimer Report 2021: Journey through the diagnosis of dementia. Tech. rep., Alzheimer\u2019s Disease International, London. World Alzheimer Report"},{"key":"2025071813451229000_2025.07.14.25331543v1.2","doi-asserted-by":"crossref","unstructured":"De Roeck, E. E. , De Deyn, P. P. , Dierckx, E. , and Engelborghs, S. (2019). Brief cognitive screening instruments for early detection of alzheimer\u2019s disease: a systematic review. Alzheimers. Res. Ther. 11, 21","DOI":"10.1186\/s13195-019-0474-3"},{"key":"2025071813451229000_2025.07.14.25331543v1.3","unstructured":"Goodglass, H. , Kaplan, E. , and Barresi, B. (2001). The assessment of aphasia and related disorders (Philadelphia: Lippincott Williams & Wilkins), 3 edn."},{"key":"2025071813451229000_2025.07.14.25331543v1.4","doi-asserted-by":"publisher","DOI":"10.1511\/2013.101.92"},{"key":"2025071813451229000_2025.07.14.25331543v1.5","doi-asserted-by":"crossref","unstructured":"Karimi, L. , Mahboub-Ahari, A. , Jahangiry, L. , Sadeghi-Bazargani, H. , and Farahbakhsh, M. (2022). A systematic review and meta-analysis of studies on screening for mild cognitive impairment in primary healthcare. BMC Psychiatry 22, 97","DOI":"10.1186\/s12888-022-03730-8"},{"key":"2025071813451229000_2025.07.14.25331543v1.6","doi-asserted-by":"publisher","DOI":"10.2307\/2280095"},{"key":"2025071813451229000_2025.07.14.25331543v1.7","doi-asserted-by":"publisher","DOI":"10.1101\/2025.06.12.25329529"},{"key":"2025071813451229000_2025.07.14.25331543v1.8","doi-asserted-by":"publisher","DOI":"10.21203\/rs.3.rs-6391300\/v1"},{"key":"2025071813451229000_2025.07.14.25331543v1.9","doi-asserted-by":"crossref","unstructured":"Ross, S. M. (2014). Introduction to probability models (Academic press), 11 edn.","DOI":"10.1016\/B978-0-12-407948-9.00001-3"},{"key":"2025071813451229000_2025.07.14.25331543v1.10","doi-asserted-by":"crossref","first-page":"1450","DOI":"10.1001\/jamainternmed.2015.2152","article-title":"Cognitive tests to detect dementia: A systematic review and meta-analysis","volume":"175","year":"2015","journal-title":"JAMA Intern. Med"},{"key":"2025071813451229000_2025.07.14.25331543v1.11","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1590\/s1980-5764-2016dn1004013","article-title":"Some aspects of the validity of the montreal cognitive assessment (MoCA)for evaluating cognitive impairment in brazilian patients with parkinson\u2019s disease","volume":"10","year":"2016","journal-title":"Dement. Neuropsychol"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.07.14.25331543","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T20:40:48Z","timestamp":1768509648000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.1101\/2025.07.14.25331543"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,16]]},"references-count":11,"URL":"https:\/\/doi.org\/10.1101\/2025.07.14.25331543","relation":{},"subject":[],"published":{"date-parts":[[2025,7,16]]},"subtype":"preprint"}}