{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T20:00:36Z","timestamp":1790193636471,"version":"4.1.0"},"reference-count":56,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR AI"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Over half of US adults with Alzheimer disease and related dementias (ADRD) remain undiagnosed. Speech-based screening algorithms offer a scalable approach, but the relative value of large language model (LLM) adaptation strategies is unclear.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n The study aimed to compare LLM adaptation strategies for cognitive impairment detection across DementiaBank speech datasets using both text-only and multimodal models.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n \n We analyzed audio-recorded speech from 237 participants in the ADReSSo subset of DementiaBank (ADRD vs cognitive normal [CN]) and report performance on a held-out test set (n=71). Nine text-only LLMs (3B-405B; open-weight and commercial) and 3 multimodal audio-text models were evaluated. Adaptations included (1) in-context learning (ICL) with 4 demonstration selection strategies (most similar, least similar, average similar or prototype, and random), (2) reasoning-augmented prompting (self- or teacher-generated rationales, self-consistency, tree-of-thought with domain experts), (3) parameter-efficient fine-tuning (token-level vs added classification head), and (4) multimodal audio-text integration. Generalizability of the adaptation strategies was evaluated on the DementiaBank Delaware dataset (n=205; mild cognitive impairment vs CN) using the first 3 strategies. The primary outcome was the\n F<\/jats:italic>\n 1<\/jats:sub>\n -score for the cognitive impaired class; the area under the receiver operating characteristic curve was reported when available.\n <\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n On the ADReSSo dataset, average similar (prototype) demonstrations achieved the highest ICL performance across model sizes (\n F<\/jats:italic>\n 1<\/jats:sub>\n -score up to 0.81). Reasoning primarily benefited smaller models: teacher-generated rationales increased LLaMA 8B from\n F<\/jats:italic>\n 1<\/jats:sub>\n -score 0.72 to 0.76; expert-role tree-of-thought improved its zero-shot score from 0.65 to 0.71. Token-level fine-tuning produced the highest scores (LLaMA 3B:\n F<\/jats:italic>\n 1<\/jats:sub>\n =0.83, 95% CI 0.01, area under the curve [AUC]=0.91; LLaMA 70B:\n F<\/jats:italic>\n 1<\/jats:sub>\n =0.82, 95% CI 0.02, AUC=0.86; GPT-4o:\n F<\/jats:italic>\n 1<\/jats:sub>\n =0.79, 95% CI 0.01, AUC=0.87). A classification head markedly improved MedAlpaca 7B (\n F<\/jats:italic>\n 1<\/jats:sub>\n =0.06, 95% CI 0.02 to\n F<\/jats:italic>\n 1<\/jats:sub>\n =0.81, 95% CI 0.04), indicating model-dependent benefits of this approach. Among multimodal models, fine-tuned Phi-4 Multimodal reached an\n F<\/jats:italic>\n 1<\/jats:sub>\n -score of 0.80 (cognitive impaired) and 0.75 (CN) but did not exceed the top text-only systems. On the Delaware dataset, ICL achieved a high performance (LLaMA 8B:\n F<\/jats:italic>\n 1<\/jats:sub>\n =0.74; GPT-4o:\n F<\/jats:italic>\n 1<\/jats:sub>\n =0.80). Reasoning-augmented ICL improved LLaMA 8B to an\n F<\/jats:italic>\n 1<\/jats:sub>\n -score of 0.75. Token-level fine-tuning produced the highest scores (LLaMA 8B:\n F<\/jats:italic>\n 1<\/jats:sub>\n =0.76, 95% CI 0.02; GPT-4o:\n F<\/jats:italic>\n 1<\/jats:sub>\n =0.82, 95% CI 0.03).\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n Detection accuracy is influenced by demonstration selection, reasoning design, and tuning method. Token-level fine-tuning is generally most effective, while a classification head benefits models that perform poorly under token-based supervision. Properly adapted open-weight models can match or exceed commercial LLMs, supporting their use in scalable speech-based ADRD and mild cognitive impairment screening. Current multimodal models may require improved audio-text alignment and\/or larger training corpora.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/82608","type":"journal-article","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T13:45:07Z","timestamp":1771249507000},"page":"e82608-e82608","source":"Crossref","is-referenced-by-count":4,"title":["Large Language Model Adaptation Strategies in Speech-Based Cognitive Screening: Systematic Evaluation"],"prefix":"10.2196","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-5650-6374","authenticated-orcid":false,"given":"Fatemeh","family":"Taherinezhad","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9662-6133","authenticated-orcid":false,"given":"Mohamad Javad","family":"Momeni Nezhad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8078-8955","authenticated-orcid":false,"given":"Sepehr","family":"Karimi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1937-3396","authenticated-orcid":false,"given":"Sina","family":"Rashidi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0668-5169","authenticated-orcid":false,"given":"Ali","family":"Zolnour","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9769-5979","authenticated-orcid":false,"given":"Maryam","family":"Dadkhah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0160-6113","authenticated-orcid":false,"given":"Yasaman","family":"Haghbin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4284-9869","authenticated-orcid":false,"given":"Hossein","family":"Azadmaleki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4484-2990","authenticated-orcid":false,"given":"Maryam","family":"Zolnoori","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,3,26]]},"reference":[{"issue":"2","key":"R1","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1016\/j.jalz.2013.02.003","article-title":"2013 Alzheimer\u2019s disease facts and figures","volume":"9","author":"Thies","journal-title":"Alzheimers Dement"},{"key":"R2","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2023.102624","article-title":"ADscreen: a speech processing-based screening system for automatic identification of patients with Alzheimer\u2019s disease and related dementia","volume":"143","author":"Zolnoori","journal-title":"Artif Intell Med"},{"key":"R3","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2023.105146","article-title":"HomeADScreen: developing Alzheimer\u2019s disease and related dementia risk identification model in home healthcare","volume":"177","author":"Zolnoori","journal-title":"Int J Med Inform"},{"issue":"5","key":"R4","doi-asserted-by":"publisher","first-page":"931","DOI":"10.1111\/jgs.14716","article-title":"Impact of the REACH II and REACH VA dementia caregiver interventions on healthcare costs","volume":"65","author":"Nichols","journal-title":"J Am Geriatr Soc"},{"issue":"6","key":"R5","doi-asserted-by":"publisher","first-page":"M621","DOI":"10.1093\/gerona\/59.6.m621","article-title":"Dementia assessment in primary care: results from a study in three managed care systems","volume":"59","author":"Boise","journal-title":"J Gerontol A Biol Sci Med Sci"},{"issue":"2","key":"R6","doi-asserted-by":"publisher","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","author":"Toth","journal-title":"Curr Alzheimer Res"},{"key":"R7","unstructured":"Assessing cognitive impairment in older patients. National Institute on Aging. URL: https:\/\/www.nia.nih.gov\/health\/assessing-cognitive-impairment-older-patients [Accessed 01-03-2021]"},{"issue":"8","key":"R8","doi-asserted-by":"publisher","first-page":"105019","DOI":"10.1016\/j.jamda.2024.105019","article-title":"Natural language processing to identify home health care patients at risk for becoming incapacitated with no evident advance directives or surrogates","volume":"25","author":"Song","journal-title":"J Am Med Dir Assoc"},{"issue":"2","key":"R9","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1093\/jamia\/ocae300","article-title":"Beyond electronic health record data: leveraging natural language processing and machine learning to uncover cognitive insights from patient-nurse verbal communications","volume":"32","author":"Zolnoori","journal-title":"J Am Med Inform Assoc"},{"issue":"2","key":"R10","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1075\/ps.17011.cum","article-title":"Describing the Cookie Theft picture: sources of breakdown in Alzheimer\u2019s dementia","volume":"10","author":"Cummings","journal-title":"Pragmat. Soc"},{"key":"R11","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/4683573","article-title":"Changes in the rhythm of speech difference between people with nondegenerative mild cognitive impairment and with preclinical dementia","volume":"2020","author":"Meil\u00e1n","journal-title":"Behav Neurol"},{"issue":"5","key":"R12","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0155195","article-title":"Vocabulary size in speech may be an early indicator of cognitive impairment","volume":"11","author":"Aramaki","journal-title":"PLoS ONE"},{"issue":"1","key":"R13","doi-asserted-by":"publisher","first-page":"8","DOI":"10.3928\/00989134-20251208-03","article-title":"Detecting mild cognitive impairment using follow-up call speech and electronic health record data in home health care settings","volume":"52","author":"Zolnoori","journal-title":"J Gerontol Nurs"},{"key":"R14","doi-asserted-by":"crossref","unstructured":"Devlin J Chang MW Lee K Toutanova K . BERT: pre-training of deep bidirectional transformers for language understanding. Presented at: 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); Jun 2-7, 2019; Minneapolis, MN. URL: https:\/\/aclanthology.org\/N19-1423\/ [Accessed 27-02-2026] [doi: 10.18653\/v1\/N19-1423]","DOI":"10.18653\/v1\/N19-1423"},{"key":"R15","unstructured":"Mikolov T Chen K Corrado G Dean J . Efficient estimation of word representations in vector space. Presented at: 1st International Conference on Learning Representations, ICLR 2013; May 2-4, 2013; Scottsdale, AZ. URL: https:\/\/dblp.org\/db\/conf\/iclr\/iclr2013w.html#conf\/iclr\/abs-1301-3781 [Accessed 27-02-2026]"},{"key":"R16","doi-asserted-by":"publisher","DOI":"10.3233\/SHTI251249","article-title":"SpeechCARE: harnessing multimodal innovation to transform cognitive impairment detection - insights from the National Institute on Aging Alzheimer\u2019s Speech Challenge","volume":"329","author":"Azadmaleki","journal-title":"Stud Health Technol Inform"},{"issue":"1","key":"R17","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-025-02026-x","article-title":"SpeechCARE: dynamic multimodal modeling for cognitive screening in diverse linguistic and speech task contexts","volume":"8","author":"Azadmaleki","journal-title":"NPJ Digit Med"},{"key":"R18","unstructured":"Zolnoor M Azadmaleki H Haghbin Y et al. National institute on aging PREPARE challenge: early detection of cognitive impairment using speech: the SpeechCARE solution. arXiv. Preprint posted online on Nov 11, 2025. URL: https:\/\/arxiv.org\/pdf\/2511.08132 [Accessed 08-01-2026] [doi: 10.48550\/arXiv.2511.08132]"},{"key":"R19","doi-asserted-by":"publisher","DOI":"10.3233\/SHTI251250","article-title":"SpeechCura: a novel speech augmentation framework to tackle data scarcity in healthcare","volume":"329","author":"Rashidi","journal-title":"Stud Health Technol Inform"},{"key":"R20","unstructured":"Brow TB Mann B Ryder N et al. Language models are few-shot learners. Presented at: NIPS\u201920: Proceedings of the 34th International Conference on Neural Information Processing Systems; Dec 6-12, 2020; Vancouver, BC. URL: https:\/\/dl.acm.org\/doi\/abs\/10.5555\/3495724.3495883?download=true [Accessed 27-02-2026]"},{"issue":"6","key":"R21","doi-asserted-by":"publisher","first-page":"1003","DOI":"10.1111\/jnu.70039","article-title":"From conversation to standardized terminology: an LLM-RAG approach for automated health problem identification in home healthcare","volume":"57","author":"Zhang","journal-title":"J Nurs Scholarsh"},{"key":"R22","doi-asserted-by":"publisher","DOI":"10.3233\/SHTI250947","article-title":"Optimizing entity recognition in psychiatric treatment data with large language models","volume":"329","author":"Hosseini","journal-title":"Stud Health Technol Inform"},{"key":"R23","doi-asserted-by":"publisher","DOI":"10.3233\/SHTI251302","article-title":"A scoping review of large language model applications in healthcare","volume":"329","author":"Zhang","journal-title":"Stud Health Technol Inform"},{"key":"R24","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2025.1669896","article-title":"LLMCARE: early detection of cognitive impairment via transformer models enhanced by LLM-generated synthetic data","volume":"8","author":"Zolnour","journal-title":"Front Artif Intell"},{"key":"R25","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2025.106231","article-title":"Advancing healthcare with large language models: a scoping review of applications and future directions","volume":"208","author":"Zhang","journal-title":"Int J Med Inform"},{"key":"R26","doi-asserted-by":"crossref","unstructured":"Chen Z Deng J Zhou J Wu J Qian T Huang M . Depression detection in clinical interviews with LLM-empowered structural element graph. Presented at: Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies; Jun 16-21, 2024; Mexico City, Mexico. URL: https:\/\/aclanthology.org\/2024.naacl-long.452\/ [Accessed 27-02-2026] [doi: 10.18653\/v1\/2024.naacl-long.452]","DOI":"10.18653\/v1\/2024.naacl-long.452"},{"issue":"1","key":"R27","doi-asserted-by":"publisher","DOI":"10.1038\/s43856-025-01158-1","article-title":"Enhanced large language models for effective screening of depression and anxiety","volume":"5","author":"Liu","journal-title":"Commun Med (Lond)"},{"key":"R28","doi-asserted-by":"crossref","unstructured":"Koushik L Vishruth M Anand Kumar M . Detecting suicide risk patterns using hierarchical attention networks with large language models. Presented at: Proceedings of the 9th Workshop on Computational Linguistics and Clinical Psychology (CLPsych 2024); Mar 21, 2024; St Julians, Malta. URL: https:\/\/aclanthology.org\/2024.clpsych-1.21\/ [Accessed 27-02-2026] [doi: 10.18653\/v1\/2024.clpsych-1.21]","DOI":"10.18653\/v1\/2024.clpsych-1.21"},{"issue":"1","key":"R29","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-025-01565-7","article-title":"A scoping review on generative AI and large language models in mitigating medication related harm","volume":"8","author":"Ong","journal-title":"NPJ Digit Med"},{"key":"R30","unstructured":"Pichai S . Google AI updates: Bard and new AI features in search. Google Blog. Feb 6, 2023. URL: https:\/\/blog.google\/technology\/ai\/bard-google-ai-search-updates\/ [Accessed 21-07-2025]"},{"issue":"2","key":"R31","doi-asserted-by":"publisher","first-page":"426","DOI":"10.1044\/2022_AJSLP-22-00281","article-title":"DementiaBank: theoretical rationale, protocol, and illustrative analyses","volume":"32","author":"Lanzi","journal-title":"Am J Speech Lang Pathol"},{"key":"R32","unstructured":"Grattafiori A Dubey A Jauhri A et al. The LLaMA 3 herd of models. arXiv. Preprint posted online on Jul 31, 2024. [doi: 10.48550\/arXiv.2407.21783]"},{"key":"R33","unstructured":"Mistralai\/ministral-8B-instruct-2410. Hugging Face. URL: https:\/\/huggingface.co\/mistralai\/Ministral-8B-Instruct-2410 [Accessed 21-07-2025]"},{"key":"R34","unstructured":"Ha T Adams LC Papaioannou JM et al. MedAlpaca: an open-source collection of medical conversational AI models and training data. arXiv. Preprint posted online on Apr 14, 2023. [doi: 10.48550\/arXiv.2304.08247]"},{"key":"R35","doi-asserted-by":"crossref","unstructured":"Guo D Yang D Zhang H DeepSeek-AIet al. DeepSeek-R1: incentivizing reasoning capability in LLMs via reinforcement learning. arXiv. Preprint posted online on Jan 22, 2025. [doi: 10.1038\/s41586-025-09422-z]","DOI":"10.1038\/s41586-025-09422-z"},{"key":"R36","unstructured":"GPT-4o system card. OpenAI; Aug 4, 2024. URL: https:\/\/cdn.openai.com\/gpt-4o-system-card.pdf [Accessed 28-02-2026]"},{"key":"R37","unstructured":"Pichai S Hassabis D Kavukcuoglu K . Introducing gemini 2.0: our new AI model for the agentic era. Google Blog. Dec 11, 2024. URL: https:\/\/blog.google\/technology\/google-deepmind\/google-gemini-ai-update-december-2024\/ [Accessed 21-07-2025]"},{"key":"R38","doi-asserted-by":"crossref","unstructured":"Syed ZS Syed MSS Lech M Pirogova E . Tackling the ADReSSo challenge 2021: the MUET-RMIT system for Alzheimer\u2019s dementia recognition from spontaneous speech. Presented at: 22nd Annual Conference of the International Speech Communication Association \u2013 INTERSPEECH 2021; Aug 30 to Sep 3, 2021; Brno, Czechia. URL: https:\/\/www.isca-archive.org\/interspeech_2021 [Accessed 27-02-2026] [doi: 10.21437\/Interspeech.2021-1572]","DOI":"10.21437\/Interspeech.2021-1572"},{"issue":"S19","key":"R39","doi-asserted-by":"publisher","DOI":"10.1002\/alz.073058","article-title":"Establishing the DementiaBank Delaware Corpus: an online multimedia database for the study of language and cognition in dementia","volume":"19","author":"Lanzi","journal-title":"Alzheimers Dement"},{"key":"R40","unstructured":"Amazon Transcribe. Amazon Web Services (AWS). URL: https:\/\/aws.amazon.com\/transcribe [Accessed 29-07-2025]"},{"key":"R41","doi-asserted-by":"crossref","unstructured":"Chen J Xiao S Zhang P Luo K Lian D Liu Z . M3-embedding: multi-linguality, multi-functionality, multi-granularity text embeddings through self-knowledge distillation. Presented at: Findings of the Association for Computational Linguistics: ACL 2024; Aug 11-16, 2024; Bangkok, Thailand. URL: https:\/\/aclanthology.org\/2024.findings-acl.137\/ [Accessed 27-02-2026] [doi: 10.18653\/v1\/2024.findings-acl.137]","DOI":"10.18653\/v1\/2024.findings-acl.137"},{"key":"R42","unstructured":"Wan X Wei J Schuurmans D et al. Self-consistency improves chain of thought reasoning in language models. Presented at: 11th International Conference on Learning Representations (ICLR 2023); May 1-5, 2023; Kigali, Rwanda. URL: https:\/\/openreview.net\/forum?id=1PL1NIMMrw [Accessed 21-07-2025]"},{"key":"R43","unstructured":"Yao S Yu D Zhao J et al. Tree of thoughts: deliberate problem solving with large language models. Presented at: NIPS \u201923: Proceedings of the 37th International Conference on Neural Information Processing Systems; Dec 10-16, 2023; New Orleans, LA. URL: https:\/\/dl.acm.org\/doi\/abs\/10.5555\/3666122.3666639 [Accessed 27-02-2026]"},{"key":"R44","doi-asserted-by":"crossref","unstructured":"Dettmers T Holtzman A Pagnoni A Zettlemoyer L . QLoRA: efficient finetuning of quantized LLMs. Presented at: NIPS \u201923: Proceedings of the 37th International Conference on Neural Information Processing Systems; Dec 10-16, 2023; New Orleans, LA. URL: https:\/\/dl.acm.org\/doi\/10.5555\/3666122.3666563 [Accessed 27-02-2026] [doi: 10.52202\/075280-0441]","DOI":"10.52202\/075280-0441"},{"key":"R45","unstructured":"AutoModels \u2014 transformers 3.0.2 documentation. Hugging Face. URL: https:\/\/huggingface.co\/transformers\/v3.0.2\/model_doc\/auto.html [Accessed 25-07-2025]"},{"key":"R46","unstructured":"Xu J Guo Z He J et al. Qwen2.5-Omni technical report. arXiv. Preprint posted online on Mar 26, 2025. [doi: 10.48550\/arXiv.2503.20215]"},{"key":"R47","unstructured":"MicrosoftAbouelenin A Ashfaq A Atkinson A et al. Phi-4-mini technical report: compact yet powerful multimodal language models via mixture-of-LoRAs. arXiv. Preprint posted online on Mar 3, 2025. [doi: 10.48550\/arXiv.2503.01743]"},{"issue":"1","key":"R48","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1214\/aoms\/1177730491","article-title":"On a test of whether one of two random variables is stochastically larger than the other","volume":"18","author":"Mann","journal-title":"Ann Math Statist"},{"key":"R49","unstructured":"DementiaBank English protocol Delaware Corpus. TalkBank. URL: https:\/\/talkbank.org\/dementia\/access\/English\/Protocol\/Delaware.html [Accessed 15-07-2025]"},{"key":"R50","doi-asserted-by":"crossref","unstructured":"Pan Y Mirheidari B Harris JM et al. Using the outputs of different automatic speech recognition paradigms for acoustic- and BERT-based Alzheimer\u2019s dementia detection through spontaneous speech. Presented at: 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021; Aug 30 to Sep 3, 2021; Brno, Czechia. URL: https:\/\/www.isca-archive.org\/interspeech_2021\/pan21c_interspeech.html [Accessed 28-02-2026] [doi: 10.21437\/INTERSPEECH.2021-1519]","DOI":"10.21437\/Interspeech.2021-1519"},{"key":"R51","doi-asserted-by":"crossref","unstructured":"Qiao Y Yin X Wiechmann D Kerz E . Alzheimer\u2019s disease detection from spontaneous speech through combining linguistic complexity and (dis)fluency features with pretrained language models. Presented at: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH 2021; Aug 30 to Sep 3, 2021; Brno, Czechia. URL: https:\/\/www.isca-archive.org\/interspeech_2021\/qiao21_interspeech.html?utm_source=chatgpt.com# [Accessed 28-02-2026] [doi: 10.21437\/Interspeech.2021-1415]","DOI":"10.21437\/Interspeech.2021-1415"},{"key":"R52","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.110834","article-title":"Context-aware attention layers coupled with optimal transport domain adaptation and multimodal fusion methods for recognizing dementia from spontaneous speech","volume":"277","author":"Ilias","journal-title":"Knowl Based Syst"},{"issue":"1","key":"R53","doi-asserted-by":"publisher","first-page":"96","DOI":"10.4218\/etrij.2023-0356","article-title":"Alzheimer\u2019s disease recognition from spontaneous speech using large language models","volume":"46","author":"Bang","journal-title":"ETRI Journal"},{"key":"R54","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2025.101814","article-title":"Modality fusion using auxiliary tasks for dementia detection","volume":"95","author":"Shao","journal-title":"Comput Speech Lang"},{"key":"R55","unstructured":"FDA clears first blood test used in diagnosing Alzheimer\u2019s disease. US Food and Drug Administration. May 16, 2025. URL: https:\/\/www.fda.gov\/news-events\/press-announcements\/fda-clears-first-blood-test-used-diagnosing-alzheimers-disease [Accessed 29-06-2025]"},{"issue":"2","key":"R56","doi-asserted-by":"publisher","DOI":"10.2196\/35325","article-title":"Audio recording patient-nurse verbal communications in home health care settings: pilot feasibility and usability study","volume":"9","author":"Zolnoori","journal-title":"JMIR Hum Factors"}],"container-title":["JMIR AI"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ai.jmir.org\/2026\/1\/e82608","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:16:36Z","timestamp":1782843396000},"score":1,"resource":{"primary":{"URL":"https:\/\/ai.jmir.org\/2026\/1\/e82608"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,26]]},"references-count":56,"URL":"https:\/\/doi.org\/10.2196\/82608","relation":{},"ISSN":["2817-1705"],"issn-type":[{"value":"2817-1705","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,26]]},"article-number":"v5i2e82608"}}