An automated machine learning approach to language changes in Alzheimer’s disease and frontotemporal dementia across Latino and English-speaking populations

一种针对拉丁裔和英语人群中阿尔茨海默病和额颞叶痴呆的语言变化的自动化机器学习方法

• 批准号: 10662053
• 负责人: MARIA LUISA GORNO TEMPINI
• 金额: $ 177.31万
• 依托单位: UNIVERSITY OF CALIFORNIA, SAN FRANCISCO
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-08-15 至 2028-06-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10662053
• 关键词: Acoustics; Address; Adoption; Affect; Alzheimer' s Disease; Atrophic; Award; Biodiversity; Biological; Biological Factors; Brain; Certification; Classification; Climacteric; Clinical; Cognitive; Cognitive deficits; Collection; Complement; Country; Data; Dementia; Detection; Diagnosis; Diagnostic; Diagnostic tests; Differentiation Antigens; Disease; Early Diagnosis; Education; Ensure; Environment; Equity; Frontotemporal Dementia; Functional Magnetic Resonance Imaging; Funding; Glean; Grain; Grant; Image; Impaired cognition; Inequity; Language; Latin America; Latin American; Latino; Latino Population; Life; Linear Regressions; Linguistics; Machine Learning; Magnetic Resonance Imaging; Manuals; Measures; Methods; Minority; Monitor; Neurocognitive; Outcome; Paper; Participant; Pathology; Pattern; Persons; Population; Prevalence; Primary Progressive Aphasia; Procedures; Protocols documentation; Publications; Race; Reproducibility of Results; Research; Research Personnel; Semantics; Site; Solid; Source; Speech; Surveys; Syndrome; Testing; Time; Training; Underrepresented Populations; United States; Variant; Visualization; behavioral variant frontotemporal dementia; bilingualism; brain health; cerebral atrophy; cohort; cost; deep learning; deep learning algorithm; diagnostic value; digital; ethnoracial; forging; high dimensionality; improved; innovation; machine learning algorithm; minority communities; multimodal data; neural; neural correlate; neuroimaging; neuroprotection; novel; outreach; predictive marker; recruit; sex; skills; social culture; social health determinants; sound; standard measure; targeted treatment; tool; underserved minority

PROJECT SUMMARY Alzheimer's disease (AD) and frontotemporal dementia (FTD) are highly prevalent in Latinos, the largest and fastest-growing minority in the United States (US). Yet, due to financial and cultural inequities, this group is challenged to afford standard diagnostic and monitoring procedures. Also, research on Latinos lacks scalable, culturally valid tests and it rarely examines whether potential markers are robust across socio-biological profiles. Such issues can be tackled with low-cost automated speech and language analyses (ASLA). Participants are asked to produce natural speech, generating multiple acoustic (sound wave) and linguistic (e.g., semantic) data that can be digitally extracted and analyzed to identify diseases or predict neurocognitive disruptions. Yet, ASLA findings are minimal in Latinos. Also, most ASLA studies are small and very few ha differentiated between AD and FTD variants, compared ASLA with standard measures, accounted for socio-biological factors (e.g., sex, race, brain profile, bilingualism) or tested for validity across languages and dialects. This project will develop a novel ASLA framework to jointly address such challenges. To capture socio-biological diversity and meet requisites for robust machine and deep learning analyses, we will leverage 2740 participants. These encompass Spanish speakers from five Latin American countries (700 AD, 700 FTD, 800 controls), English speakers from the US (140 AD, 140 FTD, 160 controls), and US-based Latinos (30 AD, 30 FTD, 40 controls), including the main variants of each disease. This is possible due to a strategic partnership between UCSF and the Consortium to Expand Dementia Research in Latin America, a multi-funded network bringing a fully harmonized environment and a large, growing cohort. The Global Brain Health Institute, a dementia training hub at UCSF, hosts expert clinicians in all sites. Speech and language data will be gleaned through our new Toolkit to Examine Lifelike Language, a HIPPA-compliant app for speech collection, storage, and visualization, supported by a language battery and survey. Enrollees are characterized with demographic, clinical, cognitive, and social determinants of health measures, alongside MRI and fMRI. Our ASLA approach comprises top predicted markers for each syndrome, added fine-grained features, and embedding features. Novel machine and deep learning algorithms for high-dimensional settings will be used to pursue three aims. In Aim 1, we will employ machine and deep learning to reveal the ASLA markers that best identify AD and FTD syndromes; compare them with cognitive and imaging measures; and test them for generalizability from Spanish onto English (a typologically different language). In Aim 2, via linear regressions, we will use optimal ASLA markers to capture syndrome-specific patterns of cognitive dysfunction, brain atrophy, and connectivity. In Aim 3, using high-dimensional machine learning, we will test such markers for validity across diverse socio-biological profiles, dialects, and bilingual skills (null, low, high). We will forge an affordable, scalable approach to assist AD and FTD diagnosis in Latinos, at a time when disease-modifying therapies may emerge.

项目概要 阿尔茨海默病 (AD) 和额颞叶痴呆 (FTD) 在拉丁裔人群中非常流行，这是最大且最常见的人群 美国（US）增长最快的少数族裔。然而，由于经济和文化的不平等，这个群体 面临负担标准诊断和监测程序的挑战。此外，对拉丁裔的研究缺乏可扩展性， 文化上有效的测试，并且很少检查潜在标记在社会生物学概况中是否稳健。 这些问题可以通过低成本的自动语音和语言分析（ASLA）来解决。参加者有 要求产生自然语音，生成多个声学（声波）和语言（例如语义）数据 可以进行数字提取和分析，以识别疾病或预测神经认知障碍。然而，美国景观设计师协会 在拉丁裔中的发现很少。此外，大多数 ASLA 研究规模都很小，很少区分 AD 和 AD 之间的差异。 和 FTD 变体，将 ASLA 与标准测量进行比较，考虑了社会生物学因素（例如性别、 种族、大脑概况、双语）或测试跨语言和方言的有效性。 该项目将开发一个新颖的 ASLA 框架来共同应对此类挑战。捕捉社会生物学 为了实现多样性并满足稳健的机器和深度学习分析的要求，我们将利用 2740 名参与者。 其中包括来自五个拉丁美洲国家的西班牙语使用者（公元 700 年、FTD 700 年、控制 800 年）， 来自美国的说英语的人（公元 140 年、FTD 140 年、160 个控制者）和居住在美国的拉丁美洲人（公元 30 年、FTD 30 年、40 年） 控制），包括每种疾病的主要变异。这是可能的，因为双方之间的战略合作伙伴关系 加州大学旧金山分校和联盟将扩大拉丁美洲的痴呆症研究，这是一个多方资助的网络，带来了 完全和谐的环境和庞大且不断增长的群体。全球脑健康研究所，痴呆症培训 加州大学旧金山分校的中心，在所有地点都有专家临床医生。语音和语言数据将通过我们的新工具收集 Toolkit to Examination Lifelike Language 是一款符合 HIPPA 标准的应用程序，用于语音收集、存储和可视化， 由语言电池和调查支持。参与者具有人口统计学、临床、认知、 以及健康措施的社会决定因素，以及 MRI 和 fMRI。我们的 ASLA 方法包括 预测每种综合症的标记，添加细粒度特征和嵌入特征。新颖机器 高维设置的深度学习算法将用于实现三个目标。 在目标 1 中，我们将利用机器和深度学习来揭示最能识别 AD 和 FTD 的 ASLA 标记 综合症；将它们与认知和成像测量进行比较；并测试它们在西班牙语中的普遍性 到英语（一种类型上不同的语言）。在目标 2 中，通过线性回归，我们将使用最优 ASLA 标记物来捕获认知功能障碍、脑萎缩和连通性的综合症特定模式。瞄准 3、使用高维机器学习，我们将测试这些标记在不同社会生物学中的有效性 个人资料、方言和双语技能（空、低、高）。我们将制定一种负担得起的、可扩展的方法来协助 拉丁美洲人的 AD 和 FTD 诊断，恰逢疾病缓解疗法可能出现。

项目成果

Toolkit to Examine Lifelike Language (TELL): An app to capture speech and language markers of neurodegeneration.

检查逼真语言的工具包 (TELL)：一款用于捕获神经退行性病变的语音和语言标记的应用程序。

• 发表时间: 2023-09-27
• 影响因子: 5.4
• 作者: García, Adolfo M;Johann, Fernando;Echegoyen, Raúl;Calcaterra, Cecilia;Riera, Pablo;Belloli, Laouen;Carrillo, Facundo
• 通讯作者: Carrillo, Facundo

Discriminating nonfluent/agrammatic and logopenic PPA variants with automatically extracted morphosyntactic measures from connected speech.

通过从连接的语音中自动提取形态句法测量来区分不流利/语法错误和语意缺失的 PPA 变体。

• 发表时间: 2024-04
• 作者: Lukic, Sladjana;Fan, Zekai;García, Adolfo M;Welch, Ariane E;Ratnasiri, Buddhika M;Wilson, Stephen M;Henry, Maya L;Vonk, Jet;Deleon, Jessica;Miller, Bruce L;Miller, Zachary;Mandelli, Maria Luisa;Gorno
• 通讯作者: Gorno

Viscous dynamics associated with hypoexcitation and structural disintegration in neurodegeneration via generative whole-brain modeling.

通过生成全脑模型研究与神经退行性疾病中低兴奋和结构崩解相关的粘性动力学。

• 发表时间: 2024-03-19
• 作者: Coronel;Gómez, Raúl Gónzalez;Ranasinghe, Kamalini;Sainz;Legaz, Agustina;Fittipaldi, Sol;Cruzat, Josephine;Herzog, Rubén;Yener, Gorsev;Parra, Mario;Aguillon, David;Lopera, Francisco;Santamaria
• 通讯作者: Santamaria