{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T10:07:49Z","timestamp":1791540469715,"version":"4.3.4"},"reference-count":56,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2022,10,17]],"date-time":"2022-10-17T00:00:00Z","timestamp":1665964800000},"content-version":"vor","delay-in-days":46,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Novoic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Early detection of Alzheimer\u2019s disease is required to identify patients suitable for disease-modifying medications and to improve access to non-pharmacological preventative interventions. Prior research shows detectable changes in speech in Alzheimer\u2019s dementia and its clinical precursors. The current study assesses whether a fully automated speech-based artificial intelligence system can detect cognitive impairment and amyloid beta positivity, which characterize early stages of Alzheimer\u2019s disease. Two hundred participants (age 54\u201385, mean 70.6; 114 female, 86 male) from sister studies in the UK (NCT04828122) and the USA (NCT04928976), completed the same assessments and were combined in the current analyses. Participants were recruited from prior clinical trials where amyloid beta status (97 amyloid positive, 103 amyloid negative, as established via PET or CSF test) and clinical diagnostic status was known (94 cognitively unimpaired, 106 with mild cognitive impairment or mild Alzheimer\u2019s disease). The automatic story recall task was administered during supervised in-person or telemedicine assessments, where participants were asked to recall stories immediately and after a brief delay. An artificial intelligence text-pair evaluation model produced vector-based outputs from the original story text and recorded and transcribed participant recalls, quantifying differences between them. Vector-based representations were fed into logistic regression models, trained with tournament leave-pair-out cross-validation analysis to predict amyloid beta status (primary endpoint), mild cognitive impairment and amyloid beta status in diagnostic subgroups (secondary endpoints). Predictions were assessed by the area under the receiver operating characteristic curve for the test result in comparison with reference standards (diagnostic and amyloid status). Simulation analysis evaluated two potential benefits of speech-based screening: (i) mild cognitive impairment screening in primary care compared with the Mini-Mental State Exam, and (ii) pre-screening prior to PET scanning when identifying an amyloid positive sample. Speech-based screening predicted amyloid beta positivity (area under the curve = 0.77) and mild cognitive impairment or mild Alzheimer\u2019s disease (area under the curve = 0.83) in the full sample, and predicted amyloid beta in subsamples (mild cognitive impairment or mild Alzheimer\u2019s disease: area under the curve = 0.82; cognitively unimpaired: area under the curve = 0.71). Simulation analyses indicated that in primary care, speech-based screening could modestly improve detection of mild cognitive impairment (+8.5%), while reducing false positives (\u221259.1%). Furthermore, speech-based amyloid pre-screening was estimated to reduce the number of PET scans required by 35.3% and 35.5% in individuals with mild cognitive impairment and cognitively unimpaired individuals, respectively. Speech-based assessment offers accessible and scalable screening for mild cognitive impairment and amyloid beta positivity.<\/jats:p>","DOI":"10.1093\/braincomms\/fcac231","type":"journal-article","created":{"date-parts":[[2022,10,17]],"date-time":"2022-10-17T09:07:52Z","timestamp":1665997672000},"source":"Crossref","is-referenced-by-count":27,"title":["Leveraging speech and artificial intelligence to screen for early Alzheimer\u2019s disease and amyloid beta positivity"],"prefix":"10.1093","volume":"4","author":[{"given":"Emil","family":"Fristed","sequence":"first","affiliation":[{"name":"Novoic Ltd , London, N1 7EU , UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8692-7787","authenticated-orcid":false,"given":"Caroline","family":"Skirrow","sequence":"additional","affiliation":[{"name":"Novoic Ltd , London, N1 7EU , UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marton","family":"Meszaros","sequence":"additional","affiliation":[{"name":"Novoic Ltd , London, N1 7EU , UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raphael","family":"Lenain","sequence":"additional","affiliation":[{"name":"Novoic Ltd , London, N1 7EU , UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Udeepa","family":"Meepegama","sequence":"additional","affiliation":[{"name":"Novoic Ltd , London, N1 7EU , UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kathryn V","family":"Papp","sequence":"additional","affiliation":[{"name":"Center for Alzheimer Research and Treatment, Department of Neurology, Brigham and Women's Hospital, Harvard Medical School , Boston, Massachusetts, 02115 , USA"},{"name":"Department of Neurology, Massachusetts General Hospital , Harvard Medical School, Boston, Massachusetts, 02114 , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Ropacki","sequence":"additional","affiliation":[{"name":"Strategic Global Research & Development , Temecula, California, 94019 , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jack","family":"Weston","sequence":"additional","affiliation":[{"name":"Novoic Ltd , London, N1 7EU , UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2022,10,17]]},"reference":[{"key":"2022101711470671800_fcac231-B1","author":"Alzheimer\u2019s Association.","year":"2019"},{"key":"2022101711470671800_fcac231-B2","doi-asserted-by":"crossref","first-page":"978","DOI":"10.1080\/13607863.2011.596805","article-title":"Underdiagnosis of dementia in primary care: Variations in the observed prevalence and comparisons to the expected prevalence","volume":"15","author":"Connolly","year":"2011","journal-title":"Aging Mental Health"},{"key":"2022101711470671800_fcac231-B3","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1016\/S1474-4422(13)70044-9","article-title":"Amyloid \u03b2 deposition, neurodegeneration, and cognitive decline in sporadic Alzheimer\u2019s disease: A prospective cohort study","volume":"12","author":"Villemagne","year":"2013","journal-title":"Lancet Neurol"},{"key":"2022101711470671800_fcac231-B4","doi-asserted-by":"crossref","first-page":"117676","DOI":"10.1016\/j.neuroimage.2020.117676","article-title":"Time between milestone events in the Alzheimer\u2019s disease amyloid cascade","volume":"227","author":"Insel","year":"2021","journal-title":"Neuroimage"},{"key":"2022101711470671800_fcac231-B5","first-page":"1","article-title":"Diagnostic accuracy of the UDS 3.0 neuropsychological battery in a cohort with Alzheimer\u2019s disease in Colombia","volume":"24","author":"Porto","year":"2021","journal-title":"Appl Neuropsychol Adult"},{"key":"2022101711470671800_fcac231-B6","doi-asserted-by":"crossref","first-page":"375","DOI":"10.1093\/arclin\/acx005","article-title":"Effects of delay duration on the WMS logical memory performance of older adults with probable Alzheimer\u2019s disease, probable vascular dementia, and normal cognition","volume":"32","author":"Montgomery","year":"2017","journal-title":"Arch Clin Neuropsychol"},{"key":"2022101711470671800_fcac231-B7","first-page":"9","article-title":"Mini mental state examination and logical memory scores for entry into Alzheimer\u2019s disease trials","volume-title":"Alzheimer\u2019s Res Ther","author":"Chapman","year":"2016"},{"key":"2022101711470671800_fcac231-B8","volume-title":"WAIS-R Manual Wechsler Adult Intelligence Scale-revised","author":"Wechsler","year":"1981"},{"key":"2022101711470671800_fcac231-B9","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1016\/j.cortex.2020.07.008","article-title":"Proper names from story recall are associated with beta-amyloid in cognitively unimpaired adults at risk for Alzheimer\u2019s disease","volume":"131","author":"Mueller","year":"2020","journal-title":"Cortex"},{"issue":"3","key":"2022101711470671800_fcac231-B10","doi-asserted-by":"crossref","first-page":"448","DOI":"10.1111\/jnp.12235","article-title":"Serial position effects in the logical memory test: Loss of primacy predicts amyloid positivity","volume":"15","author":"Bruno","year":"2020","journal-title":"J Neuropsychol"},{"key":"2022101711470671800_fcac231-B11","doi-asserted-by":"crossref","first-page":"620251","DOI":"10.3389\/fpsyg.2021.620251","article-title":"Ten years of research on automatic voice and speech analysis of people with Alzheimer\u2019s disease and mild cognitive impairment: A systematic review article","volume":"12","author":"Mart\u00ednez-Nicol\u00e1s","year":"2021","journal-title":"Front Psychol"},{"issue":"4","key":"2022101711470671800_fcac231-B12","doi-asserted-by":"crossref","first-page":"1547","DOI":"10.3233\/JAD-200888","article-title":"Artificial intelligence, speech, and language processing approaches to monitoring Alzheimer\u2019s disease: A systematic review","volume":"78","author":"de la Fuente Garcia","year":"2020","journal-title":"J Alzheimer\u2019s Dis"},{"key":"2022101711470671800_fcac231-B13","author":"DementiaBank"},{"key":"2022101711470671800_fcac231-B14","first-page":"2172","author":"Luz","year":"2020"},{"issue":"12","key":"2022101711470671800_fcac231-B15","doi-asserted-by":"crossref","first-page":"3727","DOI":"10.1093\/brain\/awt269","article-title":"Connected speech as a marker of disease progression in autopsy-proven Alzheimer\u2019s disease","volume":"136","author":"Ahmed","year":"2013","journal-title":"Brain"},{"issue":"4","key":"2022101711470671800_fcac231-B16","doi-asserted-by":"crossref","first-page":"52","DOI":"10.12779\/dnd.2021.20.4.52","article-title":"A comparison of speech features between mild cognitive impairment and healthy aging groups","volume":"20","author":"Kim","year":"2021","journal-title":"Dement Neurocogn Disord"},{"key":"2022101711470671800_fcac231-B17","doi-asserted-by":"crossref","DOI":"10.1212\/WNL.0000000000200581","article-title":"Lexical and acoustic speech features relating to Alzheimer disease pathology","author":"Cho","year":"2022","journal-title":"Neurology."},{"key":"2022101711470671800_fcac231-B18","first-page":"2542","author":"Shivkumar","year":"2020"},{"key":"2022101711470671800_fcac231-B19","doi-asserted-by":"crossref","first-page":"749758","DOI":"10.3389\/fdgth.2021.749758","article-title":"Using digital speech assessments to detect early signs of cognitive impairment","volume":"3","author":"Robin","year":"2021","journal-title":"Front Digit Health"},{"key":"2022101711470671800_fcac231-B20","first-page":"11134","author":"Weston","year":"2021"},{"key":"2022101711470671800_fcac231-B21","doi-asserted-by":"crossref","first-page":"624488","DOI":"10.3389\/fcomp.2020.624488","article-title":"Pause for detection of Alzheimer\u2019s disease","volume":"2","author":"Yuan","year":"2021","journal-title":"Front Comput Science"},{"key":"2022101711470671800_fcac231-B22","doi-asserted-by":"crossref","first-page":"624683","DOI":"10.3389\/fcomp.2021.624683","article-title":"Exploring deep transfer learning techniques for Alzheimer\u2019s dementia detection","volume":"3","author":"Zhu","year":"2021","journal-title":"Front Comput Sci"},{"key":"2022101711470671800_fcac231-B23"},{"key":"2022101711470671800_fcac231-B24","doi-asserted-by":"crossref","first-page":"1541","DOI":"10.1093\/brain\/awaa074","article-title":"A unified model of post-stroke language deficits including discourse production and their neural correlates","volume":"143","author":"Alyahya","year":"2020","journal-title":"Brain"},{"key":"2022101711470671800_fcac231-B25","doi-asserted-by":"crossref","first-page":"634360","DOI":"10.3389\/fcomp.2021.634360","article-title":"A comparison of connected speech tasks for detecting early Alzheimer\u2019s disease and mild cognitive impairment using natural language processing and machine learning","volume":"3","author":"Clarke","year":"2021","journal-title":"Front Comput Sci"},{"key":"2022101711470671800_fcac231-B26","first-page":"4052","author":"Weston","year":"2022"},{"key":"2022101711470671800_fcac231-B27","doi-asserted-by":"crossref","first-page":"1828","DOI":"10.1016\/j.csda.2010.11.018","article-title":"An experimental comparison of cross-validation techniques for estimating the area under the ROC curve","volume":"55","author":"Airola","year":"2011","journal-title":"Comput Stat Data Anal"},{"key":"2022101711470671800_fcac231-B28","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1016\/j.jalz.2011.03.008","article-title":"The diagnosis of mild cognitive impairment due to Alzheimer\u2019s disease: Recommendations from the national institute on aging-Alzheimer\u2019s Association workgroups on diagnostic guidelines for Alzheimer\u2019s disease","volume":"7","author":"Albert","year":"2011","journal-title":"Alzheimer\u2019s Dementia"},{"key":"2022101711470671800_fcac231-B29","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1016\/0022-3956(75)90026-6","article-title":"\u201cMini-mental state\u201d A practical method for grading the cognitive state of patients for the clinician","volume":"12","author":"Folstein","year":"1975","journal-title":"J Psychiatr Res"},{"key":"2022101711470671800_fcac231-B30","doi-asserted-by":"crossref","first-page":"2412","DOI":"10.1212\/WNL.43.11.2412-a","article-title":"The clinical dementia rating (CDR): Current version and scoring rules","volume":"43","author":"Morris","year":"1993","journal-title":"Neurology"},{"key":"2022101711470671800_fcac231-B31","first-page":"668","article-title":"Optimizing the preclinical Alzheimer\u2019s cognitive composite with semantic processing: The PACC5","volume":"3","author":"Papp","year":"2017","journal-title":"Alzheimer\u2019s Dementia"},{"key":"2022101711470671800_fcac231-B32"},{"key":"2022101711470671800_fcac231-B33","volume-title":"WAIS-R Manual: Wechsler Adult Intelligence Scale-Revised","author":"Wechsler","year":"2008","edition":"4th ed"},{"key":"2022101711470671800_fcac231-B34","first-page":"266","article-title":"The free and cued selective reminding test: Evidence of psychometric adequacy","volume":"51","author":"Grober","year":"2009","journal-title":"Psychol Sci Q"},{"key":"2022101711470671800_fcac231-B35","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1017\/S1481803500013336","article-title":"Understanding receiver operating characteristic (ROC) curves","volume":"8","author":"Fan","year":"2006","journal-title":"CJEM"},{"key":"2022101711470671800_fcac231-B36","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020","journal-title":"arXiv"},{"key":"2022101711470671800_fcac231-B37","article-title":"RoBERTa: A robustly optimised BERT pretraining approach","author":"Liu","year":"2019","journal-title":"arXiv"},{"key":"2022101711470671800_fcac231-B38","author":"Google Speech-to-Text"},{"key":"2022101711470671800_fcac231-B39","article-title":"Datasets: A community library for natural language processing","author":"Lhoest","journal-title":"arXiv"},{"key":"2022101711470671800_fcac231-B40","doi-asserted-by":"crossref","first-page":"1389","DOI":"10.1109\/LSP.2014.2337313","article-title":"Fast implementation of Delong\u2019s algorithm for comparing the areas under correlated receiver operating characteristic curves","volume":"21","author":"Sun","year":"2014","journal-title":"IEEE Signal Proc Lett"},{"key":"2022101711470671800_fcac231-B41"},{"key":"2022101711470671800_fcac231-B42","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1212\/WNL.0000000000004826","article-title":"Practice guideline update summary: Mild cognitive impairment: Report of the guideline development, dissemination, and implementation subcommittee of the American academy of neurology","volume":"90","author":"Petersen","year":"2018","journal-title":"Neurology"},{"key":"2022101711470671800_fcac231-B43","doi-asserted-by":"crossref","first-page":"1924","DOI":"10.1001\/jama.2015.4668","article-title":"Prevalence of cerebral amyloid pathology in persons without dementia: A meta-analysis","volume":"313","author":"Jansen","year":"2015","journal-title":"JAMA"},{"key":"2022101711470671800_fcac231-B44","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1016\/j.jpsychires.2008.04.014","article-title":"A meta-analysis of the accuracy of the mini-mental state examination in the detection of dementia and mild cognitive impairment","volume":"43","author":"Mitchell","year":"2009","journal-title":"J Psychiatric Res"},{"key":"2022101711470671800_fcac231-B45","first-page":"434","article-title":"Population-based blood screening for preclinical Alzheimer\u2019s disease in a British birth cohort at age 70","volume":"144","author":"Keshavan","year":"2021","journal-title":"Brain"},{"issue":"807","key":"2022101711470671800_fcac231-B46","article-title":"Recall tests are effective to detect mild cognitive impairment: A systematic review and meta-analysis of 108 diagnostic studies","volume":"18","author":"Tsoi","year":"2017","journal-title":"JAMDA"},{"key":"2022101711470671800_fcac231-B47","first-page":"213","article-title":"Predicting amyloid burden to accelerate recruitment of secondary prevention clinical trials","volume":"7","author":"Langford","year":"2020","journal-title":"J Prev Alzheimer\u2019s Dis"},{"key":"2022101711470671800_fcac231-B48","first-page":"59","article-title":"The computerised cognitive composite (C3) in A4, an Alzheimer\u2019s disease secondary prevention trial","volume":"8","author":"Papp","year":"2021","journal-title":"J Prev Alzheimer\u2019s Dis"},{"key":"2022101711470671800_fcac231-B49","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1186\/s13195-021-00776-w","article-title":"Detecting Alzheimer\u2019s disease biomarkers with a brief tablet-based cognitive battery: Sensitivity to a\u03b2 and tau PET","volume":"13","author":"Tsoy","year":"2021","journal-title":"Alzheimer\u2019s Res Ther"},{"key":"2022101711470671800_fcac231-B50","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1016\/S0140-6736(20)30367-6","article-title":"Dementia prevention, intervention, and care: 2020 report of the lancet commission","volume":"396","author":"Livingston","year":"2020","journal-title":"Lancet"},{"key":"2022101711470671800_fcac231-B51","doi-asserted-by":"crossref","first-page":"1303","DOI":"10.1001\/jamaneurol.2021.3123","article-title":"Aducanumab and the business of Alzheimer disease-some choice","volume":"78","author":"Karlawish","year":"2021","journal-title":"JAMA Neurol"},{"key":"2022101711470671800_fcac231-B52","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1016\/S1474-4422(21)00361-6","article-title":"Blood-based biomarkers for Alzheimer\u2019s disease: Towards clinical implementation","volume":"21","author":"Teunissen","year":"2022","journal-title":"Lancet Neurol"},{"key":"2022101711470671800_fcac231-B53","doi-asserted-by":"crossref","DOI":"10.1093\/braincomms\/fcab008","article-title":"Detection of \u03b2-amyloid positivity in Alzheimer\u2019s disease neuroimaging initiative participants with demographics, cognition, MRI and plasma biomarkers","volume":"3","author":"Tosun","year":"2021","journal-title":"Brain Commun"},{"key":"2022101711470671800_fcac231-B54","doi-asserted-by":"crossref","first-page":"e2075","DOI":"10.1212\/WNL.0000000000010596","article-title":"Alzheimer\u2019s disease neuroimaging initiative. Association of CSF a\u03b2, amyloid PET, and cognition in cognitively unimpaired elderly adults","volume":"95","author":"Guo","year":"2020","journal-title":"Neurology"},{"key":"2022101711470671800_fcac231-B55","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1001\/jamaneurol.2021.5225","article-title":"Prevalence rates of amyloid positivity \u2013 updates and relevance","volume":"79","author":"Young","year":"2022","journal-title":"JAMA Neurol"},{"issue":"1\u20132","key":"2022101711470671800_fcac231-B56","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1177\/0898264320966266","article-title":"Age differences in the use of health information technology among adults in the United States: An analysis of the health information national trends survey","volume":"33","author":"Onyeaka","year":"2021","journal-title":"J Aging Health"}],"container-title":["Brain Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/braincomms\/article-pdf\/4\/5\/fcac231\/46543884\/fcac231.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/braincomms\/article-pdf\/4\/5\/fcac231\/46543884\/fcac231.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,17]],"date-time":"2022-10-17T12:14:20Z","timestamp":1666008860000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/braincomms\/article\/doi\/10.1093\/braincomms\/fcac231\/6761085"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,1]]},"references-count":56,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2022,9,1]]}},"URL":"https:\/\/doi.org\/10.1093\/braincomms\/fcac231","relation":{},"ISSN":["2632-1297"],"issn-type":[{"value":"2632-1297","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,10,1]]},"published":{"date-parts":[[2022,9,1]]},"article-number":"fcac231"}}