{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:43:06Z","timestamp":1785544986723,"version":"3.56.0"},"reference-count":77,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Inform"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Alzheimer disease (AD) is a progressive neurodegenerative disorder with rapidly growing global prevalence. Early detection is critical for timely intervention; yet, conventional diagnostic methods remain costly and invasive. Speech-based assessment has emerged as a noninvasive alternative, as AD characteristically impairs linguistic abilities including fluency, coherence, and informational content. Recent advances in large language models (LLMs) offer new opportunities to extract structured linguistic features from transcribed speech for automated AD classification. However, existing LLM-based approaches often lack transparency and clinical interpretability, limiting their adoption in clinical workflows.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aims to investigate the influence of linguistic features extracted from transcribed speech, as analyzed by LLMs, on the accuracy and interpretability of AD prediction.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n We propose a framework that leverages LLMs to analyze linguistic features extracted from transcribed speech for AD classification. Our approach focuses on 4 key aspects, including readability, fluency, richness of detail, and keyword relevance. To enhance classification accuracy, the framework integrates transcript embeddings with feature explanation embeddings, forming a comprehensive linguistic representation. We conducted extensive ablation studies to evaluate the contributions of individual features and benchmarked our framework against existing LLM-driven methodologies through pairwise explainability evaluations. Output stability was assessed across 3 independent pipeline runs. A fully local configuration (Llama 3 8B + nomic-embed-text) was tested to evaluate privacy-preserving deployment feasibility. Explainability was assessed via LLM-based pairwise comparison (Gemini-3.1-flash-lite) against the method of Bang et al across 54 correctly classified cases and by blinded evaluation from 2 neurologists.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n The proposed framework achieved a mean precision of 91.52%, a sensitivity of 91.08%, a specificity of 96.29%, and\n F<\/jats:italic>\n 1<\/jats:sub>\n -score of 91.05% across 3 independent runs on the ADReSSo 2021 dataset, outperforming existing LLM-based approaches. A fully-local configuration (Llama 3 8B+nomic-embed-text, requiring no cloud application programming interface access) achieved an\n F<\/jats:italic>\n 1<\/jats:sub>\n -score of 81.58%, demonstrating framework transferability to privacy-preserving deployment environments. Keyword relevance was the most influential feature (\n F<\/jats:italic>\n 1<\/jats:sub>\n -score drop of 13.22 pp when removed). Explainability evaluations showed our method was preferred in 49 out of 54 cases via Gemini-3.1-flash-lite, with human experts preferring our method in 89 of 108 blinded assessments.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n These findings highlight that a structured linguistic feature analysis using LLMs provides a robust and interpretable framework for preliminary AD detection. Our approach offers a scalable and accessible solution that bridges artificial intelligence\u2013driven text analysis with clinical applications, supporting early detection of cognitive decline through noninvasive assessment methods.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/86965","type":"journal-article","created":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T22:01:41Z","timestamp":1780005701000},"page":"e86965-e86965","source":"Crossref","is-referenced-by-count":0,"title":["Advancing Alzheimer Disease Prediction With Large Language Model\u2013Based Linguistic Feature Analysis: Development and Validation Study"],"prefix":"10.2196","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-3793-3153","authenticated-orcid":false,"given":"Ming-Hsia","family":"Hsu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4044-648X","authenticated-orcid":false,"given":"San-Yih","family":"Hwang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2139-9354","authenticated-orcid":false,"given":"Yi-Hang","family":"Tsai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8936-7419","authenticated-orcid":false,"given":"Yun-Chi","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1604-1600","authenticated-orcid":false,"given":"Chih-Kuang","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5767-9056","authenticated-orcid":false,"given":"Chiung-Yun","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,5,28]]},"reference":[{"key":"R1","unstructured":"Long S Benoist C Weidner W . World alzheimer report 2023. Alzheimer\u2019s Disease International; 2023. URL: https:\/\/www.alzint.org\/u\/World-Alzheimer-Report-2023.pdf [Accessed 06-05-2026]"},{"issue":"4","key":"R2","doi-asserted-by":"publisher","first-page":"700","DOI":"10.1002\/alz.12638","article-title":"2022 Alzheimer\u2019s disease facts and figures","volume":"18","journal-title":"Alzheimers Dement"},{"issue":"5","key":"R3","doi-asserted-by":"publisher","first-page":"3708","DOI":"10.1002\/alz.13809","article-title":"2024 Alzheimer\u2019s disease facts and figures","volume":"20","journal-title":"Alzheimers Dement"},{"issue":"14","key":"R4","doi-asserted-by":"publisher","first-page":"1326","DOI":"10.1056\/NEJMsa1204629","article-title":"Monetary costs of dementia in the United States","volume":"368","author":"Hurd","journal-title":"N Engl J Med"},{"issue":"6","key":"R5","doi-asserted-by":"publisher","DOI":"10.1002\/gps.5733","article-title":"New evidence on the value of timely diagnosis for people with dementia","volume":"37","author":"Banerjee","journal-title":"Int J Geriat Psychiatry"},{"issue":"1","key":"R6","doi-asserted-by":"publisher","DOI":"10.1186\/s12913-024-10957-6","article-title":"A qualitative study of informal caregiver perceptions of the benefits of an early dementia diagnosis","volume":"24","author":"Couch","journal-title":"BMC Health Serv Res"},{"issue":"4","key":"R7","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1080\/21507740.2021.1941404","article-title":"Early detection of Alzheimer\u2019s disease benefits research, quality of life, and end-of-life planning","volume":"12","author":"Incorvaia","journal-title":"AJOB Neurosci"},{"issue":"14","key":"R8","doi-asserted-by":"publisher","first-page":"647","DOI":"10.1212\/WNL.0000000000011739","article-title":"Early detection of incipient Alzheimer pathology","volume":"96","author":"Barkhof","journal-title":"Neurology (ECronicon)"},{"issue":"1","key":"R9","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1007\/s40120-022-00428-7","article-title":"The early diagnosis of Alzheimer\u2019s disease: a patient-centred conversation with the care team","volume":"12","author":"Nasreddine","journal-title":"Neurol Ther"},{"issue":"6","key":"R10","doi-asserted-by":"publisher","first-page":"420","DOI":"10.1136\/jnnp-2022-330619","article-title":"Plasma biomarkers for Alzheimer\u2019s disease: a field-test in a memory clinic","volume":"94","author":"Altomare","journal-title":"J Neurol Neurosurg Psychiatry"},{"issue":"12","key":"R11","doi-asserted-by":"publisher","first-page":"5805","DOI":"10.1002\/alz.13455","article-title":"The potential clinical value of plasma biomarkers in Alzheimer\u2019s disease","volume":"19","author":"Blennow","journal-title":"Alzheimer\u2019s & Dementia"},{"key":"R12","doi-asserted-by":"publisher","DOI":"10.3389\/fneur.2021.765454","article-title":"Dementia risk scores and their role in the implementation of risk reduction guidelines","volume":"12","author":"Anstey","journal-title":"Front Neurol"},{"key":"R13","doi-asserted-by":"publisher","DOI":"10.3389\/fneur.2020.592302","article-title":"Early stages of Alzheimer\u2019s disease: evolving the care team for optimal patient management","volume":"11","author":"Galvin","journal-title":"Front Neurol"},{"issue":"2","key":"R14","doi-asserted-by":"publisher","first-page":"655","DOI":"10.3233\/JAD-215106","article-title":"Lessons from detecting cognitive impairment including dementia (DetectCID) in primary care","volume":"86","author":"Bernstein Sideman","journal-title":"J Alzheimers Dis"},{"issue":"4","key":"R15","doi-asserted-by":"publisher","first-page":"661","DOI":"10.3934\/publichealth.2022047","article-title":"The physician\u2019s Alzheimer\u2019s disease management guide: early detection and diagnosis of cognitive impairment, Alzheimer\u2019s disease and related dementia","volume":"9","author":"Reiss","journal-title":"AIMS Public Health"},{"issue":"3","key":"R16","doi-asserted-by":"publisher","first-page":"808","DOI":"10.3758\/brm.40.3.808","article-title":"Combining computer adaptive testing technology with cognitively diagnostic assessment","volume":"40","author":"McGlohen","journal-title":"Behav Res Methods"},{"issue":"8","key":"R17","doi-asserted-by":"publisher","first-page":"767","DOI":"10.1080\/13803395.2021.2021645","article-title":"Introduction to the special issue - neuropsychology from a distance: psychometric properties and clinical utility of remote neurocognitive tests","volume":"43","author":"Van Patten","journal-title":"J Clin Exp Neuropsychol"},{"issue":"1","key":"R18","doi-asserted-by":"publisher","DOI":"10.1002\/dad2.12217","article-title":"Current advances in digital cognitive assessment for preclinical Alzheimer\u2019s disease","volume":"13","author":"\u00d6hman","journal-title":"Alzheimers Dement (Amst)"},{"issue":"Supplement_1","key":"R19","doi-asserted-by":"publisher","first-page":"380","DOI":"10.1093\/geroni\/igad104.1260","article-title":"Revolutionizing cognitive assessment: the power of digital biomarkers and ecologically valid methods","volume":"7","author":"Roque","journal-title":"Innov Aging"},{"issue":"4","key":"R20","doi-asserted-by":"publisher","DOI":"10.1002\/mpr.1562","article-title":"Applications for self-administered mobile cognitive assessments in clinical research: a systematic review","volume":"26","author":"Moore","journal-title":"Int J Methods Psychiatr Res"},{"key":"R21","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2019.02327","article-title":"Comparing traditional and digitized cognitive tests used in standard clinical evaluation - a study of the digital application minnemera","volume":"10","author":"Bj\u00f6rngrim","journal-title":"Front Psychol"},{"key":"R22","volume":"2020","author":"Staffaroni","journal-title":"Pract Neurol (Fort Wash Pa)"},{"issue":"5","key":"R23","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1016\/j.jalz.2014.06.004","article-title":"Innovative diagnostic tools for early detection of Alzheimer\u2019s disease","volume":"11","author":"Laske","journal-title":"Alzheimers Dement"},{"key":"R24","doi-asserted-by":"publisher","DOI":"10.3389\/fnagi.2024.1451326","article-title":"Screening for early Alzheimer\u2019s disease: enhancing diagnosis with linguistic features and biomarkers","volume":"16","author":"Chou","journal-title":"Front Aging Neurosci"},{"key":"R25","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2023.104442","article-title":"AD-BERT: using pre-trained language model to predict the progression from mild cognitive impairment to Alzheimer\u2019s disease","volume":"144","author":"Mao","journal-title":"J Biomed Inform"},{"issue":"1","key":"R26","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1111\/1460-6984.12870","article-title":"Natural language processing techniques for studying language in pathological ageing: a scoping review","volume":"59","author":"Gagliardi","journal-title":"Int J Lang Commun Disord"},{"key":"R27","doi-asserted-by":"crossref","unstructured":"Balagopalan A Novikova J . Comparing acoustic-based approaches for alzheimer\u2019s disease detection. Interspeech 2021. Preprint posted online on 2021. URL: https:\/\/www.isca-archive.org\/interspeech_2021 [Accessed 06-05-2026] [doi: 10.21437\/Interspeech.2021-759]","DOI":"10.21437\/Interspeech.2021-759"},{"key":"R28","doi-asserted-by":"crossref","unstructured":"Ortiz-Perez D Ruiz-Ponce P Tom\u00e1s D Garcia-Rodriguez J . Deep learning-based dementia prediction using multimodal data. In: Garc\u00eda Bringas P , editor. 17th International Workshop on Soft Computing Models in Industrial and Environmental Applications (SOCO 2022). Vol 531. Springer, Cham; 2023:260-269. Lecture Notes in Networks and Systems. [doi: 10.1007\/978-3-031-18050-7_25]","DOI":"10.1007\/978-3-031-18050-7_25"},{"issue":"3","key":"R29","doi-asserted-by":"publisher","DOI":"10.2196\/33460","article-title":"Evaluating web-based automatic transcription for Alzheimer speech data: transcript comparison and machine learning analysis","volume":"5","author":"Soroski","journal-title":"JMIR Aging"},{"key":"R30","doi-asserted-by":"crossref","unstructured":"Wang Y Wang T Ye Z et al. Exploring linguistic feature and model combination for speech recognition based automatic AD detection. Presented at: Interspeech 2022; Sep 18-22, 2022:3328-3332; Incheon, South Korea. 2022.URL: https:\/\/www.isca-archive.org\/interspeech_2022 [Accessed 06-05-2026] [doi: 10.21437\/Interspeech.2022-723]","DOI":"10.21437\/Interspeech.2022-723"},{"key":"R31","doi-asserted-by":"publisher","DOI":"10.1016\/j.psychres.2023.115538","article-title":"Speech and language processing with deep learning for dementia diagnosis: a systematic review","volume":"329","author":"Shi","journal-title":"Psychiatry Res"},{"key":"R32","doi-asserted-by":"publisher","DOI":"10.1016\/j.psychres.2019.112732","article-title":"Artificial intelligence approaches to predicting and detecting cognitive decline in older adults: a conceptual review","volume":"284","author":"Graham","journal-title":"Psychiatry Res"},{"key":"R33","doi-asserted-by":"crossref","unstructured":"Palliya Guruge C Oviatt S Delir Haghighi P Pritchard E . Advances in multimodal behavioral analytics for early dementia diagnosis: a review. Presented at: ICMI \u201921; Oct 18, 2021:328-340; Montr\u00e9al QC Canada. Oct 18, 2021.URL: https:\/\/dl.acm.org\/doi\/proceedings\/10.1145\/3462244 [Accessed 06-05-2026] [doi: 10.1145\/3462244.3479933]","DOI":"10.1145\/3462244.3479933"},{"key":"R34","doi-asserted-by":"crossref","unstructured":"Pandey SK Shekhawat HS Bhasin S Jasuja R Prasanna S . Alzheimer\u2019s dementia recognition using multimodal fusion of speech and text embeddings. In: Kim JH Singh M Khan J Tiwary US Sur M Singh D , editors. Intelligent Human Computer Interaction (IHCI). Vol 13184. Springer, Cham; 2021:718-728. Lecture Notes in Computer Science. [doi: 10.1007\/978-3-030-98404-5_64]","DOI":"10.1007\/978-3-030-98404-5_64"},{"issue":"12","key":"R35","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000168","article-title":"Predicting dementia from spontaneous speech using large language models","volume":"1","author":"Agbavor","journal-title":"PLOS Digit Health"},{"issue":"1","key":"R36","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":"#cr-split#-R37.1","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:Association for Computational Linguistics. 4171-4186"},{"key":"#cr-split#-R37.2","doi-asserted-by":"crossref","unstructured":"Minneapolis, Minnesota. 2019.URL: https:\/\/aclanthology.org\/N19-1423\/ [Accessed 23-05-2026] [doi: 10.18653\/v1\/N19-1423]","DOI":"10.18653\/v1\/N19-1423"},{"key":"R38","doi-asserted-by":"crossref","unstructured":"Padhee S Illendula A Sadler M et al. Predicting early indicators of cognitive decline from verbal utterances. Presented at: 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM); 2020:477-480; Seoul, Korea (South. URL: https:\/\/ieeexplore.ieee.org\/xpl\/mostRecentIssue.jsp?punumber=9312958 [Accessed 06-05-2026] [doi: 10.1109\/BIBM49941.2020.9313106]","DOI":"10.1109\/BIBM49941.2020.9313106"},{"key":"R39","doi-asserted-by":"crossref","unstructured":"Rohanian M Hough J Purver M . Alzheimer\u2019s dementia recognition using acoustic, lexical, disfluency and speech pause features robust to noisy inputs. Presented at: Interspeech 2021; 2021. URL: https:\/\/www.isca-archive.org\/interspeech_2021 [Accessed 06-05-2026] [doi: 10.21437\/Interspeech.2021-1633]","DOI":"10.21437\/Interspeech.2021-1633"},{"key":"R40","doi-asserted-by":"publisher","DOI":"10.3389\/fnagi.2021.623607","article-title":"Acoustic and language based deep learning approaches for Alzheimer\u2019s dementia detection from spontaneous speech","volume":"13","author":"Mahajan","journal-title":"Front Aging Neurosci"},{"key":"R41","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: Interspeech 2021; 2021. URL: https:\/\/www.isca-archive.org\/interspeech_2021 [Accessed 06-05-2026] [doi: 10.21437\/Interspeech.2021-1415]","DOI":"10.21437\/Interspeech.2021-1415"},{"key":"R42","doi-asserted-by":"crossref","unstructured":"Yuan J Bian Y Cai X Huang J Ye Z Church K . Disfluencies and fine-tuning pre-trained language models for detection of Alzheimer\u2019s disease. Presented at: Interspeech 2020; 2020:2162-2166; URL: https:\/\/www.isca-archive.org\/interspeech_2020 [Accessed 06-05-2026] [doi: 10.21437\/Interspeech.2020-2516]","DOI":"10.21437\/Interspeech.2020-2516"},{"key":"R43","doi-asserted-by":"publisher","DOI":"10.2196\/51501","article-title":"Text dialogue analysis for primary screening of mild cognitive impairment: development and validation study","volume":"25","author":"Wang","journal-title":"J Med Internet Res"},{"issue":"8","key":"R44","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics14080817","article-title":"Performance assessment of ChatGPT versus Bard in detecting Alzheimer\u2019s dementia","volume":"14","author":"Balamurali","journal-title":"Diagnostics (Basel)"},{"key":"R45","doi-asserted-by":"crossref","unstructured":"Luz S Haider F Fuente S de la Fromm D MacWhinney B . Detecting cognitive decline using speech only: the adresso challenge. Presented at: Interspeech 2021; 2021:3780-3784; URL: https:\/\/www.isca-archive.org\/interspeech_2021 [Accessed 06-05-2026] [doi: 10.21437\/Interspeech.2021-1220]","DOI":"10.21437\/Interspeech.2021-1220"},{"issue":"6","key":"R46","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1001\/archneur.1994.00540180063015","article-title":"The natural history of Alzheimer\u2019s disease. Description of study cohort and accuracy of diagnosis","volume":"51","author":"Becker","journal-title":"Arch Neurol"},{"key":"R47","unstructured":"Goodglass H Kaplan E Barresi B . BDAE: The Boston Diagnostic Aphasia Examination. Lippincott Williams & Wilkins; 2001:1-85. ISBN: 9780683305593"},{"key":"R48","unstructured":"Radford A Kim JW Xu T Brockman G McLeavey C Sutskever I . Robust speech recognition via large-scale weak supervision. In: Proceedings of the International Conference on Machine Learning (ICML). Vol 202. Proceedings of Machine Learning Research; :28492-28518. URL: https:\/\/proceedings.mlr.press\/v202\/radford23a.html [Accessed 23-05-2026]"},{"key":"R49","doi-asserted-by":"crossref","unstructured":"Bredin H Laurent A . End-to-end speaker segmentation for overlap-aware resegmentation. Presented at: Interspeech 2021; 2021:3707-3711; URL: https:\/\/www.isca-archive.org\/interspeech_2021 [Accessed 06-05-2026] [doi: 10.21437\/Interspeech.2021-560]","DOI":"10.21437\/Interspeech.2021-560"},{"key":"R50","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2021.835960","article-title":"Improving Alzheimer\u2019s disease detection for speech based on feature purification network","volume":"9","author":"Liu","journal-title":"Front Public Health"},{"key":"R51","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2021.103803","article-title":"Predicting Alzheimer\u2019s disease from spoken and written language using fusion-based stacked generalization","volume":"118","author":"Alkenani","journal-title":"J Biomed Inform"},{"key":"R52","doi-asserted-by":"crossref","unstructured":"Sarawgi U Zulfikar W Soliman N Maes P . Multimodal inductive transfer learning for detection of Alzheimer\u2019s dementia and its severity. Presented at: Interspeech 2020; Oct 25-29, 2020. URL: https:\/\/www.isca-archive.org\/interspeech_2020 [Accessed 06-05-2026] [doi: 10.21437\/Interspeech.2020-3137]","DOI":"10.21437\/Interspeech.2020-3137"},{"issue":"3","key":"R53","doi-asserted-by":"publisher","first-page":"959","DOI":"10.3233\/JAD-142763","article-title":"Tracking discourse complexity preceding Alzheimer\u2019s disease diagnosis: a case study comparing the press conferences of Presidents Ronald Reagan and George Herbert Walker Bush","volume":"45","author":"Berisha","journal-title":"J Alzheimers Dis"},{"key":"R54","doi-asserted-by":"publisher","DOI":"10.3389\/fcomp.2021.640669","article-title":"Alzheimer\u2019s dementia recognition from spontaneous speech using disfluency and interactional features","volume":"3","author":"Nasreen","journal-title":"Front Comput Sci"},{"issue":"2","key":"R55","doi-asserted-by":"publisher","first-page":"407","DOI":"10.3233\/JAD-150520","article-title":"Linguistic features identify Alzheimer\u2019s disease in narrative speech","volume":"49","author":"Fraser","journal-title":"J Alzheimers Dis"},{"issue":"1","key":"R56","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1016\/j.dadm.2017.08.005","article-title":"Analysis of macrolinguistic aspects of narratives from individuals with Alzheimer\u2019s disease, mild cognitive impairment, and no cognitive impairment","volume":"10","author":"Toledo","journal-title":"Alzheimers Dement (Amst)"},{"key":"R57","doi-asserted-by":"publisher","DOI":"10.3389\/fnagi.2021.642033","article-title":"Language impairment in Alzheimer\u2019s disease-robust and explainable evidence for AD-related deterioration of spontaneous speech through multilingual machine learning","volume":"13","author":"Lindsay","journal-title":"Front Aging Neurosci"},{"key":"R58","doi-asserted-by":"crossref","unstructured":"Karlekar S Niu T Bansal M . Detecting linguistic characteristics of alzheimer\u2019s dementia by interpreting neural models. Presented at: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers); Jun 1-6, 2018; New Orleans, Louisiana. URL: http:\/\/aclweb.org\/anthology\/N18-2 [Accessed 06-05-2026] [doi: 10.18653\/v1\/N18-2110]","DOI":"10.18653\/v1\/N18-2110"},{"key":"R59","unstructured":"Kong W . Exploring neural models for predicting dementia from language. University of British Columbia; 2019. URL: https:\/\/open.library.ubc.ca\/soa\/cIRcle\/collections\/ubctheses\/24\/items\/1.0380363 [Accessed 23-05-2026] [doi: 10.14288\/1.0380363]"},{"key":"R60","unstructured":"Wei J Tay Y Bommasani R et al. Emergent abilities of large language models. Transactions on Machine Learning Research. 2022. URL: https:\/\/openreview.net\/forum?id=yzkSU5zdwD [Accessed 06-05-2026]"},{"key":"R61","unstructured":"OpenAI. GPT-4 technical report. arXiv. Preprint posted online on Mar 4, 2024. URL: https:\/\/arxiv.org\/abs\/2303.08774 [Accessed 06-05-2026]"},{"key":"R62","unstructured":"Kingma DP Ba J . Adam: a method for stochastic optimization. arXiv. Preprint posted online on Jan 30, 2017. [doi: 10.48550\/arXiv.1412.6980]"},{"key":"R63","unstructured":"Grattafiori A Dubey A Jauhri A Pandey A Kadian A et al. The llama 3 herd of models. arXiv. Preprint posted online on Nov 23, 2024. URL: https:\/\/arxiv.org\/abs\/2407.21783 [Accessed 25-05-2026]"},{"key":"R64","unstructured":"Nussbaum Z Morris JX Duderstadt B Mulyar A . Nomic embed: training a reproducible long context text embedder. arXiv. Preprint posted online on Feb 3, 2025. URL: https:\/\/arxiv.org\/abs\/2402.01613 [Accessed 06-05-2026]"},{"key":"R65","unstructured":"Gemini Team. Google deepmind, gemini: a family of highly capable multimodal models. arXiv. Preprint posted online on May 5, 2025. URL: https:\/\/arxiv.org\/abs\/2312.11805 [Accessed 06-05-2026]"},{"key":"R66","doi-asserted-by":"crossref","unstructured":"Liu Y Iter D Xu Y Wang S Xu R Zhu C . G-eval: NLG evaluation using gpt-4 with better human alignment. In: Bouamor H Pino J Bali K , editors. Presented at: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing; Dec 6-10, 2023:2511-2522; Singapore. URL: https:\/\/aclanthology.org\/2023.emnlp-main [Accessed 06-05-2026] [doi: 10.18653\/v1\/2023.emnlp-main.153]","DOI":"10.18653\/v1\/2023.emnlp-main.153"},{"key":"R67","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.12.012","article-title":"Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI","volume":"58","author":"Barredo Arrieta","journal-title":"Information Fusion"},{"key":"R68","doi-asserted-by":"crossref","unstructured":"Ribeiro MT Singh S Guestrin C . \u201cWhy should i trust you?\u201d: explaining the predictions of any classifier. Presented at: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics; Aug 13, 2016:1135-1144; San Diego, California. URL: http:\/\/aclweb.org\/anthology\/N16-3 [Accessed 07-05-2026] [doi: 10.18653\/v1\/N16-3020]","DOI":"10.18653\/v1\/N16-3020"},{"key":"R69","unstructured":"Lundberg SM Lee SI et al. A unified approach to interpreting model predictions. In: Guyon I von Luxburg U Bengio S Wallach H Fergus R Vishwanathan SVN , editors. Adv Neural Inf Process Syst. Vol 30. 2017:4765-4774. URL: https:\/\/papers.nips.cc\/paper\/7062-a-unified-approach-to-interpreting-model-predictions [Accessed 25-05-2026]"},{"issue":"4","key":"R70","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1312","article-title":"Causability and explainability of artificial intelligence in medicine","volume":"9","author":"Holzinger","journal-title":"Wiley Interdiscip Rev Data Min Knowl Discov"},{"key":"R71","unstructured":"Tonekaboni S Joshi S McCradden MD Goldenberg A et al. What clinicians want: contextualizing explainable machine learning for clinical end use. In: Doshi-Velez F Fackler J Jung K , editors. Presented at: Proceedings of the 4th Machine Learning for Healthcare Conference; Aug 9-10, 2019:359-380; Ann Arbor, Michigan. URL: https:\/\/proceedings.mlr.press\/v106\/tonekaboni19a.html [Accessed 25-05-2026]"},{"key":"R72","unstructured":"Kahneman D Sibony O Sunstein CR . Noise: A Flaw in Human Judgment. Little, Brown Spark; 2021:1-454. URL: https:\/\/www.hachettebookgroup.com\/titles\/daniel-kahneman\/noise\/9780316451406\/? [Accessed 25-05-2026] ISBN: 9780316451406"},{"key":"R73","doi-asserted-by":"crossref","unstructured":"Bavaresco A Bernardi R Bertolazzi L et al. LLMs instead of human judges? a large scale empirical study across 20 nlp evaluation tasks. Presented at: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2); Jul 27 to Aug 1, 2025; Vienna, Austria. URL: https:\/\/aclanthology.org\/2025.acl-short [Accessed 06-05-2026] [doi: 10.18653\/v1\/2025.acl-short.20]","DOI":"10.18653\/v1\/2025.acl-short.20"},{"key":"R74","doi-asserted-by":"crossref","unstructured":"Van Den Burg G j. Suzuki G Liu W Sensoy M . Aligning black-box language models with human judgments. Presented at: Findings of the Association for Computational Linguistics; Apr 29 to May 4, 2025; Albuquerque, New Mexico. URL: https:\/\/aclanthology.org\/2025.findings-naacl [Accessed 06-05-2026] [doi: 10.18653\/v1\/2025.findings-naacl.376]","DOI":"10.18653\/v1\/2025.findings-naacl.376"},{"key":"R75","unstructured":"R Core Team. R: a language and environment for statistical computing. R foundation for statistical computing. 2024. URL: https:\/\/www.R-project.org\/ [Accessed 07-05-2026]"},{"key":"R76","doi-asserted-by":"crossref","unstructured":"Liu Z Proctor L Collier PN Zhao X . Automatic diagnosis and prediction of cognitive decline associated with Alzheimer\u2019s dementia through spontaneous speech. Presented at: 2021 IEEE International Conference on Signal and Image Processing Applications (ICSIPA); Sep 13-15, 2021:39-43; Kuala Terengganu, Malaysia. [doi: 10.1109\/ICSIPA52582.2021.9576784]","DOI":"10.1109\/ICSIPA52582.2021.9576784"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/medinform.jmir.org\/2026\/1\/e86965","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T22:25:21Z","timestamp":1785536721000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2026\/1\/e86965"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,28]]},"references-count":77,"URL":"https:\/\/doi.org\/10.2196\/86965","relation":{},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,28]]},"article-number":"v14i4e86965"}}