{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T13:21:19Z","timestamp":1768569679341,"version":"3.49.0"},"posted":{"date-parts":[[2025,8,8]]},"group-title":"Neurology","reference-count":50,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,8,8]],"date-time":"2025-08-08T00:00:00Z","timestamp":1754611200000},"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":[[2025,10,28]]},"abstract":"<jats:p>Early detection of cognitive impairment (CI) is critical for timely intervention in Alzheimer\u2019s disease and AD-related dementias. To address this, we propose the Warning Assessment and Alerting Tool for Cognitive Health from Spontaneous Speech (WATCH-SS), a modular and explainable three-stage framework for detecting CI from a patient\u2019s speech sample. The framework uses detectors for five linguistic and acoustic indicators of CI, aggregates their outputs into a set of clinically interpretable summary features, and uses a predictive model for CI classification. We consider multiple approaches to implementing these detectors that range from simple, computationally efficient methods suitable for real-time analysis to strong, resource-intensive methods, better for high accuracy offine analysis. On the DementiaBank ADReSS dataset, WATCH-SS achieved strong predictive performance (AUC = 80% on the test set). This work demonstrates that a modular, feature-based approach can achieve strong performance while providing a transparent diagnostic profile, representing a significant step towards a trustworthy and clinically-usable screening tool for primary care.<\/jats:p>","DOI":"10.1101\/2025.08.06.25333047","type":"posted-content","created":{"date-parts":[[2025,8,9]],"date-time":"2025-08-09T01:25:12Z","timestamp":1754702712000},"source":"Crossref","is-referenced-by-count":0,"title":["WATCH-SS: Developing a Trustworthy and Explainable Modular Framework for Detecting Cognitive Impairment from Spontaneous Speech*"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1465-983X","authenticated-orcid":false,"given":"Sydney","family":"Pugh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0272-5716","authenticated-orcid":false,"given":"Matthew","family":"Hill","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3851-9521","authenticated-orcid":false,"given":"Sy","family":"Hwang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8533-8976","authenticated-orcid":false,"given":"Rachel","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3134-3220","authenticated-orcid":false,"given":"Kuk","family":"Jang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2247-9626","authenticated-orcid":false,"given":"Stacy","family":"Iannone","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7709-3813","authenticated-orcid":false,"given":"Karen","family":"O\u2019Connor","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8461-0492","authenticated-orcid":false,"given":"Kyra","family":"O\u2019Brien","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eric","family":"Eaton","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1016-9363","authenticated-orcid":false,"given":"Kevin","family":"Johnson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"54368","reference":[{"key":"2025103004401471000_2025.08.06.25333047v2.1","unstructured":"Alzheimer\u2019s Association , 2025 Alzheimer\u2019s Disease Facts and Figures, Alzheimer\u2019s & Dementia: The Journal of the Alzheimer\u2019s Association 21 (apr 2025)."},{"key":"2025103004401471000_2025.08.06.25333047v2.2","doi-asserted-by":"publisher","DOI":"10.1007\/s11606-018-4377-y"},{"key":"2025103004401471000_2025.08.06.25333047v2.3","doi-asserted-by":"crossref","first-page":"101113","DOI":"10.1016\/j.csl.2020.101113","article-title":"Linguistic features and automatic classifiers for identifying mild cognitive impairment and dementia","volume":"65","year":"2021","journal-title":"Computer Speech Language"},{"key":"2025103004401471000_2025.08.06.25333047v2.4","doi-asserted-by":"crossref","unstructured":"E. Eyigoz , S. Mathur , M. Santamaria , G. Cecchi and M. Naylor , Linguistic markers predict onset of alzheimer\u2019s disease, EClinicalMedicine 28 (2020).","DOI":"10.1016\/j.eclinm.2020.100583"},{"key":"2025103004401471000_2025.08.06.25333047v2.5","unstructured":"R. H. Brookshire and M. R. McNeil , Introduction to neurogenic communication disorders (Elsevier Health Sciences, 2014)."},{"key":"2025103004401471000_2025.08.06.25333047v2.6","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1186\/s43058-025-00693-1","article-title":"Designing an intervention to improve cognitive evaluations in primary care","volume":"6","year":"2025","journal-title":"Implementation Science Communications"},{"key":"2025103004401471000_2025.08.06.25333047v2.7","doi-asserted-by":"crossref","unstructured":"C.-J. Chou , C.-T. Chang , Y.-N. Chang , C.-Y. Lee , Y.-F. Chuang , Y.-L. Chiu , W.-L. Liang , Y.-M. Fan and Y.-C. Liu , Screening for early alzheimer\u2019s disease: enhancing diagnosis with linguistic features and biomarkers, Frontiers in Aging Neuroscience Volume 16 - 2024 (2024).","DOI":"10.3389\/fnagi.2024.1451326"},{"key":"2025103004401471000_2025.08.06.25333047v2.8","first-page":"e12516","article-title":"An explainable machine learning model of cognitive decline derived from speech","volume":"15","year":"2023","journal-title":"Alzheimer\u2019s & Dementia: Diagnosis, Assessment & Disease Monitoring"},{"key":"2025103004401471000_2025.08.06.25333047v2.9","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1016\/j.laheal.2023.09.002","article-title":"Natural language processing-driven framework for the early detection of language and cognitive decline","volume":"1","year":"2023","journal-title":"Language and Health"},{"key":"2025103004401471000_2025.08.06.25333047v2.10","doi-asserted-by":"crossref","unstructured":"L. Huang , H. Yang , Y. Che and J. Yang , Automatic speech analysis for detecting cognitive decline of older adults, Frontiers in Public Health Volume 12 - 2024 (2024).","DOI":"10.3389\/fpubh.2024.1417966"},{"key":"2025103004401471000_2025.08.06.25333047v2.11","first-page":"e12393","article-title":"Development of digital voice biomarkers and associations with cognition, cerebrospinal biomarkers, and neural representation in early alzheimer\u2019s disease","volume":"15","year":"2023","journal-title":"Alzheimer\u2019s & Dementia: Diagnosis, Assessment & Disease Monitoring"},{"key":"2025103004401471000_2025.08.06.25333047v2.12","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1177\/0891988720933358","article-title":"Using automatic assessment of speech production to predict current and future cognitive function in older adults","volume":"34","year":"2021","journal-title":"Journal of Geriatric Psychiatry and Neurology"},{"key":"2025103004401471000_2025.08.06.25333047v2.13","article-title":"Tackling cognitive impairment detection from speech: A submission to the process challenge","year":"2024","journal-title":"arXiv preprint"},{"key":"2025103004401471000_2025.08.06.25333047v2.14","doi-asserted-by":"publisher","DOI":"10.1080\/02687039608248419"},{"key":"2025103004401471000_2025.08.06.25333047v2.15","doi-asserted-by":"crossref","unstructured":"I. Arevalo-Rodriguez , N. Smailagic , M. Roqu\u00e9-Figuls , A. Ciapponi , E. Sanchez-Perez , A. Giannakou , O. L. Pedraza , X. B. Cosp and S. Cullum , Mini-Mental State Examination (MMSE) for the early detection of dementia in people with mild cognitive impairment (MCI) - Arevalo-Rodriguez, I - 2021 | Cochrane Library.","DOI":"10.1002\/14651858.CD010783.pub3"},{"key":"2025103004401471000_2025.08.06.25333047v2.16","doi-asserted-by":"publisher","DOI":"10.1097\/WAD.0b013e3182420bfe"},{"key":"2025103004401471000_2025.08.06.25333047v2.17","doi-asserted-by":"publisher","DOI":"10.1080\/07317115.2022.2120446"},{"key":"2025103004401471000_2025.08.06.25333047v2.18","doi-asserted-by":"crossref","first-page":"130","DOI":"10.2174\/1567205014666171121114930","article-title":"A Speech Recognition-based Solution for the Automatic Detection of Mild Cognitive Impairment from Spontaneous Speech","volume":"15","year":"2018","journal-title":"Current Alzheimer Research"},{"key":"2025103004401471000_2025.08.06.25333047v2.19","first-page":"63","article-title":"Topic-Based Measures of Conversation for Detecting Mild Cognitive Impairment","volume":"2020","year":"2020","journal-title":"Proceedings of the conference. Association for Computational Linguistics. Meeting"},{"key":"2025103004401471000_2025.08.06.25333047v2.20","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1186\/s13195-022-01131-3","article-title":"Deep learning-based speech analysis for Alzheimer\u2019s disease detection: a literature review","volume":"14","year":"2022","journal-title":"Alzheimer\u2019s Research & Therapy"},{"key":"2025103004401471000_2025.08.06.25333047v2.21","doi-asserted-by":"crossref","unstructured":"L. Gauder , L. Pepino , L. Ferrer and P. Riera , Alzheimer Disease Recognition Using Speech-Based Embeddings From Pre-Trained Models, in Interspeech 2021, (ISCA, ISCA, August 2021).","DOI":"10.21437\/Interspeech.2021-753"},{"key":"2025103004401471000_2025.08.06.25333047v2.22","doi-asserted-by":"crossref","unstructured":"P. Mahajan and V. Baths , Acoustic and Language Based Deep Learning Approaches for Alzheimer\u2019s Dementia Detection From Spontaneous Speech, Frontiers in Aging Neuroscience 13 (February 2021), Publisher: Frontiers.","DOI":"10.3389\/fnagi.2021.623607"},{"key":"2025103004401471000_2025.08.06.25333047v2.23","doi-asserted-by":"crossref","unstructured":"M. R. Makiuchi , T. Warnita , N. Inoue , K. Shinoda , M. Yoshimura , M. Kitazawa , K. Funaki , Y. Eguchi and T. Kishimoto , Speech Paralinguistic Approach for Detecting Dementia Using Gated Convolutional Neural Network, IEICE Transactions on Information E104-D, 1930 (November 2021), Publisher: The Institute of Electronics, Information and Communication Engineers.","DOI":"10.1587\/transinf.2020EDP7196"},{"key":"2025103004401471000_2025.08.06.25333047v2.24","doi-asserted-by":"crossref","unstructured":"Z. Liu , L. Proctor , P. N. Collier and X. Zhao , Automatic Diagnosis and Prediction of Cognitive Decline Associated with Alzheimer\u2019s Dementia through Spontaneous Speech, in 2021 IEEE International Conference on Signal and Image Processing Applications (ICSIPA), September 2021. ISSN: 2642-6471.","DOI":"10.1109\/ICSIPA52582.2021.9576784"},{"key":"2025103004401471000_2025.08.06.25333047v2.25","doi-asserted-by":"crossref","first-page":"e0000168","DOI":"10.1371\/journal.pdig.0000168","article-title":"Predicting dementia from spontaneous speech using large language models","volume":"1","year":"2022","journal-title":"PLOS Digital Health"},{"key":"2025103004401471000_2025.08.06.25333047v2.26","unstructured":"M. Zusag and L. Wagner , Providing interpretable insights for neurological speech and cognitive disorders from interactive serious games, PLOS Digital Health 1 (2022)."},{"key":"2025103004401471000_2025.08.06.25333047v2.27","doi-asserted-by":"crossref","first-page":"88377","DOI":"10.1109\/ACCESS.2021.3090321","article-title":"Automated Recognition of Alzheimer\u2019s Dementia Using Bag-of-Deep-Features and Model Ensembling","volume":"9","year":"2021","journal-title":"IEEE Access"},{"key":"2025103004401471000_2025.08.06.25333047v2.28","first-page":"315","volume-title":"Journal of Alzheimer\u2019s Disease","volume":"84","year":"2021"},{"key":"2025103004401471000_2025.08.06.25333047v2.29","doi-asserted-by":"crossref","first-page":"642033","DOI":"10.3389\/fnagi.2021.642033","article-title":"Language impairment in alzheimer\u2019s disease\u2014robust and explainable evidence for ad-related deterioration of spontaneous speech through multilingual machine learning","volume":"13","year":"2021","journal-title":"Frontiers in aging neuroscience"},{"key":"2025103004401471000_2025.08.06.25333047v2.30","doi-asserted-by":"crossref","first-page":"12613","DOI":"10.1007\/s10489-024-05808-0","article-title":"Explainable cognitive decline detection in free dialogues with a machine learning approach based on pre-trained large language models","volume":"54","year":"2024","journal-title":"Applied Intelligence"},{"key":"2025103004401471000_2025.08.06.25333047v2.31","doi-asserted-by":"crossref","unstructured":"S. Luz , F. Haider , S. de la Fuente Garcia , D. Fromm and B. MacWhinney , Alzheimer\u2019s dementia recognition through spontaneous speech: The adress challenge, Frontiers in Computer Science Volume 3 - 2021 (2021).","DOI":"10.3389\/fcomp.2021.780169"},{"key":"2025103004401471000_2025.08.06.25333047v2.32","doi-asserted-by":"publisher","DOI":"10.1001\/archneur.1994.00540180063015"},{"key":"2025103004401471000_2025.08.06.25333047v2.33","unstructured":"H. Goodglass , E. Kaplan and S. Weintraub , BDAE: The Boston diagnostic aphasia examination (Lippincott Williams & Wilkins Philadelphia, PA, 2001)."},{"key":"2025103004401471000_2025.08.06.25333047v2.34","unstructured":"B. MacWhinney , The CHILDES project: Tools for analyzing talk, Volume I: Transcription format and programs (Psychology Press, 2014)."},{"key":"2025103004401471000_2025.08.06.25333047v2.35","unstructured":"K. B. Johnson , B. Alasaly , K. J. Jang , E. Eaton , S. Mopidevi and R. Koppel , The observer repository: Advancing ambulatory care innovation through video-based clinical ethnography, medRxiv (2025)."},{"key":"2025103004401471000_2025.08.06.25333047v2.36","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2024.108013"},{"key":"2025103004401471000_2025.08.06.25333047v2.37","unstructured":"J. Heitz , G. Schneider and N. Langer , Linguistic features extracted by GPT-4 improve Alzheimer\u2019s disease detection based on spontaneous speech, in Proceedings of the 31st International Conference on Computational Linguistics, eds. O. Rambow , L. Wanner , M. Apidianaki , H. Al-Khalifa , B. D. Eugenio and S. Schockaert (Association for Computational Linguistics, Abu Dhabi, UAE, January 2025)."},{"key":"2025103004401471000_2025.08.06.25333047v2.38","doi-asserted-by":"publisher","DOI":"10.2196\/51501"},{"key":"2025103004401471000_2025.08.06.25333047v2.39","unstructured":"M. Honnibal , I. Montani , S. Van Landeghem , A. Boyd et al., spacy: Industrial-strength natural language processing in python (2020)."},{"key":"2025103004401471000_2025.08.06.25333047v2.40","doi-asserted-by":"publisher","DOI":"10.2190\/2QDA-YAL3-2E69-PYJW"},{"key":"2025103004401471000_2025.08.06.25333047v2.41","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1044\/2017_AJSLP-16-0210","article-title":"Describing phonological paraphasias in three variants of primary progressive aphasia","volume":"27","year":"2018","journal-title":"American Journal of Speech-Language Pathology"},{"key":"2025103004401471000_2025.08.06.25333047v2.42","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1093\/brain\/awm251","article-title":"Word-finding difficulty: a clinical analysis of the progressive aphasias","volume":"131","year":"2007","journal-title":"Brain"},{"key":"2025103004401471000_2025.08.06.25333047v2.43","doi-asserted-by":"crossref","unstructured":"L. K. Obler , Chapter 12 - language and brain dysfunction in dementia, in Language Functions and Brain Organization, ed. S. J. Segalowitz (Academic Press, Boston, 1983) pp. 267\u2013282.","DOI":"10.1016\/B978-0-12-635640-3.50020-5"},{"key":"2025103004401471000_2025.08.06.25333047v2.44","doi-asserted-by":"publisher","DOI":"10.1016\/0093-934X(85)90124-5"},{"key":"2025103004401471000_2025.08.06.25333047v2.45","unstructured":"J. Devlin , M.-W. Chang , K. Lee and K. Toutanova , BERT: Pre-training of deep bidirectional transformers for language understanding, in Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), eds. J. Burstein , C. Doran and T. Solorio (Association for Computational Linguistics, Minneapolis, Minnesota, June 2019)."},{"key":"2025103004401471000_2025.08.06.25333047v2.46","unstructured":"J. Robert , M. Webbie et al., Pydub (2018)."},{"key":"2025103004401471000_2025.08.06.25333047v2.47","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"2025103004401471000_2025.08.06.25333047v2.48","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"2025103004401471000_2025.08.06.25333047v2.49","unstructured":"A. Radford , J. W. Kim , T. Xu , G. Brockman , C. McLeavey and I. Sutskever , Robust speech recognition via large-scale weak supervision, in International conference on machine learning, 2023."},{"key":"2025103004401471000_2025.08.06.25333047v2.50","doi-asserted-by":"crossref","unstructured":"M. Zusag , L. Wagner and T. Bloder , Careful whisper-leveraging advances in automatic speech recognition for robust and interpretable aphasia subtype classification, in Proc. Interspeech 2023, 2023.","DOI":"10.21437\/Interspeech.2023-1653"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.08.06.25333047","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T20:42:42Z","timestamp":1768509762000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.1101\/2025.08.06.25333047"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,8]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1101\/2025.08.06.25333047","relation":{},"subject":[],"published":{"date-parts":[[2025,8,8]]},"subtype":"preprint"}}