{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T21:30:55Z","timestamp":1791840655699,"version":"4.3.4"},"reference-count":50,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T00:00:00Z","timestamp":1769126400000},"content-version":"vor","delay-in-days":22,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["alz-journals.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Alz &amp; Dem Diag Ass &amp; Dis Mo"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>INTRODUCTION<\/jats:title>\n                    <jats:p>We examine how non\u2010expert humans (young adults unfamiliar with dementia) and large language models (LLMs) perceive dementia in transcribed texts\u2014recognizing signs that may indicate cognitive decline. Human perception is important, as it is often the driver for seeking medical evaluation. LLM perception is equally interesting given their potential as screening tools.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>METHODS<\/jats:title>\n                    <jats:p>Humans and LLMs intuitively judged whether transcribed picture descriptions came from dementia patients or healthy controls. We represented texts using high\u2010level, expert\u2010guided features and used logistic regression to model perceptions and analyze coefficients.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>RESULTS<\/jats:title>\n                    <jats:p>Human judgments are inconsistent, relying on a narrow and sometimes misleading set of cues. LLMs use a richer, more clinically aligned feature set. Both groups show a tendency toward false negatives.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>DISCUSSION<\/jats:title>\n                    <jats:p>This work highlights the need to educate humans and LLMs to recognize a broader range of dementia\u2010related linguistic signals. It also underscores the value of interpretability in dementia research.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Highlights<\/jats:title>\n                    <jats:p>\n                      <jats:list list-type=\"bullet\">\n                        <jats:list-item>\n                          <jats:p>Explainable artificial intelligence (AI) uncovers linguistic cues that humans and large language models (LLMs) associate with dementia.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>LLMs allow scalable extraction of expert\u2010defined features on picture descriptions.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>LLMs use broader cues than humans to detect dementia and better align with diagnoses.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>Humans and LLMs exhibit false negatives; LLMs view fluency as cognitive health.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>Understanding non\u2010expert perceptions can guide education and improve early awareness.<\/jats:p>\n                        <\/jats:list-item>\n                      <\/jats:list>\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/dad2.70248","type":"journal-article","created":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T16:25:18Z","timestamp":1769185518000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Human and large language model judgments of cognitive impairment from language: An explainable artificial intelligence approach"],"prefix":"10.1002","volume":"18","author":[{"given":"Maya","family":"Zadok","sequence":"first","affiliation":[{"name":"Faculty of Data and Decisions Sciences Technion\u2010 Israel Institute for Technology  Haifa Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lotem","family":"Peled\u2010Cohen","sequence":"additional","affiliation":[{"name":"Faculty of Data and Decisions Sciences Technion\u2010 Israel Institute for Technology  Haifa Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nitay","family":"Calderon","sequence":"additional","affiliation":[{"name":"Faculty of Data and Decisions Sciences Technion\u2010 Israel Institute for Technology  Haifa Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hila","family":"Gonen","sequence":"additional","affiliation":[{"name":"Paul G. Allen School of Computer Science &amp; Engineering University of Washington  Seattle Washington USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michal Schnaider","family":"Beeri","sequence":"additional","affiliation":[{"name":"The Krieger Klein Alzheimer's Research Center, Brain Health Institute Rutgers University  Piscataway New Jersey USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roi","family":"Reichart","sequence":"additional","affiliation":[{"name":"Faculty of Data and Decisions Sciences Technion\u2010 Israel Institute for Technology  Haifa Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,1,23]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1002\/gps.3766"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0000000000200581"},{"key":"e_1_2_10_4_1","doi-asserted-by":"crossref","unstructured":"Peled\u2010CohenL ReichartR.A systematic review of NLP for dementia\u2010tasks datasets and opportunities. arXiv preprint arXiv:2409.19737 2024.","DOI":"10.1162\/TACL.a.35"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0000000000005863"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-4422(19)30368-0"},{"issue":"8","key":"e_1_2_10_7_1","article-title":"Worldwide prevalence of mild cognitive impairment among community dwellers aged 50 years and older: a meta\u2010analysis and systematic review of epidemiology studies","volume":"51","author":"Bai W","year":"2022","journal-title":"Age Ageing"},{"key":"e_1_2_10_8_1","unstructured":"SmithJ.The future of senior care may be AI.https:\/\/www.retirementliving.com\/aging\u2010with\u2010ai 2025. [Accessed 2025\u201005\u201008]."},{"key":"e_1_2_10_9_1","doi-asserted-by":"publisher","DOI":"10.2217\/nmt.12.7"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.3233\/JAD-220422"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.1001\/archneur.1994.00540180063015"},{"key":"e_1_2_10_12_1","unstructured":"GrattafioriA DubeyA JauhriA et\u00a0al.The llama 3 herd of models. arXiv preprint arXiv:2407.21783 2024."},{"key":"e_1_2_10_13_1","unstructured":"OpenAI. GPT\u20104 technical report. CoRR abs\/2303.08774 2023. doi:10.48550\/ARXIV.2303.08774"},{"key":"e_1_2_10_14_1","unstructured":"TeamG GeorgievP LeiVI et\u00a0al.Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. arXiv preprint arXiv:2403.05530 2024."},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.4088\/JCP.23m14962"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyt.2024.1328122"},{"key":"e_1_2_10_17_1","volume-title":"BDAE: The Boston Diagnostic Aphasia Examination","author":"Goodglass H","year":"1983"},{"key":"e_1_2_10_18_1","doi-asserted-by":"crossref","unstructured":"RottgerP VidgenB HovyD PierrehumbertJ et\u00a0al.Two contrasting data annotation paradigms for subjective nlp tasks. InProceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.Associa\u2010 tion for Computational Linguistics 2022.","DOI":"10.18653\/v1\/2022.naacl-main.13"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.1044\/jshr.3602.338"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cortex.2021.01.012"},{"key":"e_1_2_10_21_1","doi-asserted-by":"crossref","unstructured":"CroisileB SkaB BrabantM\u2010J et\u00a0al Comparative study of oral and written picture description in patients with Alzheimer's disease. Technical report 1996.","DOI":"10.1006\/brln.1996.0033"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.3233\/JAD\u2010150520"},{"key":"e_1_2_10_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.NEUCOM.2023.126413"},{"key":"e_1_2_10_24_1","first-page":"331","volume-title":"Dementia and Normal Aging","author":"Kempler D","year":"1994"},{"key":"e_1_2_10_25_1","first-page":"73","volume-title":"Annual review of applied linguistics","author":"Kempler D","year":"2008"},{"key":"e_1_2_10_26_1","doi-asserted-by":"publisher","DOI":"10.1075\/ps.17011.cum"},{"key":"e_1_2_10_27_1","doi-asserted-by":"publisher","DOI":"10.3233\/JAD-160252"},{"key":"e_1_2_10_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10072-005-0467-9"},{"key":"e_1_2_10_29_1","doi-asserted-by":"crossref","unstructured":"KarlekarS NiuT BansalM.Detecting linguistic characteristics of Alzheimer\u2032s dementia by interpreting neural models. In:WalkerM HengJ StentA eds.Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.Association for Computational Linguistics;2018:Volume2(Short Papers):701\u2010707. doi:10.18653\/v1\/N18\u20102110","DOI":"10.18653\/v1\/N18-2110"},{"key":"e_1_2_10_30_1","doi-asserted-by":"publisher","DOI":"10.3389\/fnagi.2017.00437"},{"key":"e_1_2_10_31_1","doi-asserted-by":"crossref","unstructured":"KumarY MaheshwariP JoshiS BathsV.Ml\u2010based analysis to identify speech features relevant in predicting Alzheimer's disease. InProceedings of the 8th International Conference on Computing and Artificial Intelligence 2022:207\u2010213.","DOI":"10.1145\/3532213.3532244"},{"key":"e_1_2_10_32_1","doi-asserted-by":"crossref","unstructured":"RudziczF CurrieLC DanksA MehtaT ZhaoS.Automatically identifying trouble\u2010indicating speech behaviors in Alzheimer's disease. InProceedings of the 16th International ACM SIGACCESS Conference on Computers & Accessibility ASSETS \u201914 Association for Computing Machinery;2014:241\u2010242. ISBN 978\u20101\u20104503\u20102720\u20106. doi:10.1145\/2661334.2661382","DOI":"10.1145\/2661334.2661382"},{"key":"e_1_2_10_33_1","doi-asserted-by":"publisher","DOI":"10.1044\/jshd.4501.27"},{"key":"e_1_2_10_34_1","doi-asserted-by":"publisher","DOI":"10.3233\/JAD-230367"},{"key":"e_1_2_10_35_1","doi-asserted-by":"publisher","DOI":"10.1017\/S1355617720000478"},{"key":"e_1_2_10_36_1","doi-asserted-by":"publisher","DOI":"10.1177\/1533317513481094"},{"key":"e_1_2_10_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0010-9452(08)70119-9"},{"key":"e_1_2_10_38_1","doi-asserted-by":"publisher","DOI":"10.1017\/S1041610209008424"},{"key":"e_1_2_10_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3172479"},{"key":"e_1_2_10_40_1","doi-asserted-by":"crossref","unstructured":"SirtsK PiguetO JohnsonM.Idea density for predicting Alzheimer's disease from transcribed speech. InProceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017).2017:322\u2010332.","DOI":"10.18653\/v1\/K17-1033"},{"key":"e_1_2_10_41_1","doi-asserted-by":"crossref","unstructured":"WankerlS N\u00f6thE EvertS.An n\u2010gram based approach to the automatic diagnosis of Alzheimer's disease from spoken language. In Interspeech.2017:3162\u20103166.","DOI":"10.21437\/Interspeech.2017-1572"},{"key":"e_1_2_10_42_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0288556"},{"key":"e_1_2_10_43_1","doi-asserted-by":"publisher","DOI":"10.1075\/ps.17011.cum"},{"key":"e_1_2_10_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-industry.15"},{"key":"e_1_2_10_45_1","doi-asserted-by":"crossref","unstructured":"CalderonN ReichartR DrorR.The alternative annotator test for LLM\u2010as\u2010a\u2010judge: How to statistically justify replacing human annotators with LLMs.Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics;Association for Computational Linguistics;2025.","DOI":"10.18653\/v1\/2025.acl-long.782"},{"key":"e_1_2_10_46_1","volume-title":"Frontiers in Econometrics","author":"McFadden D","year":"1972"},{"issue":"2","key":"e_1_2_10_47_1","first-page":"17","article-title":"A comparison of logistic regression pseudo r2 indices","volume":"39","author":"Smith TJ","year":"2013","journal-title":"Gen Linear Model J"},{"key":"e_1_2_10_48_1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511753831"},{"key":"e_1_2_10_49_1","doi-asserted-by":"publisher","DOI":"10.1136\/jnnp-2014-309445"},{"key":"e_1_2_10_50_1","doi-asserted-by":"crossref","unstructured":"Poursabzi\u2010SangdehF GoldsteinDG HofmanJM VaughanJWW WallachH.\u201cManipulating and measuring model interpretability\u201d.Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems.Association for Computing Machinery;2021.","DOI":"10.1145\/3411764.3445315"},{"key":"e_1_2_10_51_1","doi-asserted-by":"publisher","DOI":"10.1038\/s43856-024-00717-2"}],"container-title":["Alzheimer's &amp; Dementia: Diagnosis, Assessment &amp; Disease Monitoring"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/alz-journals.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/dad2.70248","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/alz-journals.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/dad2.70248","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/alz-journals.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/dad2.70248","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T11:10:49Z","timestamp":1781089849000},"score":1,"resource":{"primary":{"URL":"https:\/\/alz-journals.onlinelibrary.wiley.com\/doi\/10.1002\/dad2.70248"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":50,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1002\/dad2.70248"],"URL":"https:\/\/doi.org\/10.1002\/dad2.70248","archive":["Portico"],"relation":{},"ISSN":["2352-8729","2352-8729"],"issn-type":[{"value":"2352-8729","type":"print"},{"value":"2352-8729","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"2025-08-29","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-08","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70248"}}