Novoic Ltd, London, England.
Northern California Institute for Research and Education (NCIRE), San Francisco, California, USA.
Alzheimers Dement. 2024 Oct;20(10):7248-7262. doi: 10.1002/alz.14206. Epub 2024 Sep 5.
Speech-based testing shows promise for sensitive and scalable objective screening for Alzheimer's disease (AD), but research to date offers limited evidence of generalizability.
Data were taken from the AMYPRED (Amyloid Prediction in Early Stage Alzheimer's Disease from Acoustic and Linguistic Patterns of Speech) studies (N = 101, N = 46 mild cognitive impairment [MCI]) and Alzheimer's Disease Neuroimaging Initiative 4 (ADNI4) remote digital (N = 426, N = 58 self-reported MCI, mild AD or dementia) and in-clinic (N = 57, N = 13 MCI) cohorts, in which participants provided audio-recorded responses to automated remote story recall tasks in the Storyteller test battery. Text similarity, lexical, temporal, and acoustic speech feature sets were extracted. Models predicting early AD were developed in AMYPRED and tested out of sample in the demographically more diverse cohorts in ADNI4 (> 33% from historically underrepresented populations).
Speech models generalized well to unseen data in ADNI4 remote and in-clinic cohorts. The best-performing models evaluated text-based metrics (text similarity, lexical features: area under the curve 0.71-0.84 across cohorts).
Speech-based predictions of early AD from Storyteller generalize across diverse samples.
The Storyteller speech-based test is an objective digital prescreener for Alzheimer's Disease Neuroimaging Initiative 4 (ADNI4). Speech-based models predictive of Alzheimer's disease (AD) were developed in the AMYPRED (Amyloid Prediction in Early Stage Alzheimer's Disease from Acoustic and Linguistic Patterns of Speech) sample (N = 101). Models were tested out of sample in ADNI4 in-clinic (N = 57) and remote (N = 426) cohorts. Models showed good generalization out of sample. Models evaluating text matching and lexical features were most predictive of early AD.
基于语音的测试在阿尔茨海默病（AD）的敏感和可扩展的客观筛查方面显示出前景，但迄今为止的研究提供的普遍性证据有限。
数据取自 AMYPRED（早期阿尔茨海默病的淀粉样蛋白预测：来自语音的声学和语言模式）研究（N=101，N=46 例轻度认知障碍 [MCI]）和阿尔茨海默病神经影像学倡议 4（ADNI4）远程数字（N=426，N=58 自我报告的 MCI、轻度 AD 或痴呆）和门诊（N=57，N=13 MCI）队列，其中参与者提供了对 Storyteller 测试电池中的自动化远程故事回忆任务的音频记录响应。提取了文本相似度、词汇、时间和声学语音特征集。在 AMYPRED 中开发了预测早期 AD 的模型，并在 ADNI4 中具有更多样化人群的样本外进行了测试（超过 33%来自历史上代表性不足的人群）。
语音模型在 ADNI4 远程和门诊队列的未见过数据中很好地泛化。表现最好的模型评估了基于文本的指标（文本相似度、词汇特征：曲线下面积为 0.71-0.84，跨越队列）。
来自 Storyteller 的基于语音的早期 AD 预测在不同的样本中具有很好的泛化性。
Storyteller 基于语音的测试是阿尔茨海默病神经影像学倡议 4（ADNI4）的客观数字预筛选器。在 AMYPRED（早期阿尔茨海默病的淀粉样蛋白预测：来自语音的声学和语言模式）样本中开发了预测阿尔茨海默病（AD）的基于语音的模型（N=101）。在 ADNI4 门诊（N=57）和远程（N=426）队列中对模型进行了样本外测试。模型表现出良好的样本外泛化能力。评估文本匹配和词汇特征的模型对早期 AD 的预测性最强。
