SCH: INT: Collaborative Research: Exploiting Voice Assistant Systems for Early Detection of Cognitive Decline

在独居老年人中及早发现阿尔茨海默病和相关痴呆(ADRD)对于开发、规划和启动干预和支持系统以改善患者的日常功能和生活质量至关重要。传统的、以临床为基础的早期诊断方法昂贵、不切实际且耗时。本项目旨在开发一种低成本、被动和实用的基于家庭的评估方法，使用语音辅助系统(VAS)来早期检测ADRD，包括一套新的稀疏时间序列语音数据挖掘技术。该项目有三个具体目标：1.使用递归神经网络(RNN)和Softmax回归模型，我们将开发一种迁移学习技术来研究实验室VAS任务中的语音与认知下降之间的联系，并发现与ADRD相关的语音生物标记物。利用PITT语料库对RNN参数进行优化，从而克服了VAS数据有限的问题。Softmax回归模型将允许我们对齐先前语音数据和实验室VAS语音的特征分布；2.我们将开发一种具有对称RNN结构的多对差预测模型，以从稀疏的时间序列数据中预测一个时间周期两端与ADRD相关的认知差异。该模型不同于以往的模型，因为学习的重点从用户之间的短期模式差异转移到了单个用户随着时间的模式差异。所提出的模型很好地适应了输入的高度动态特性，并最大限度地从预测结果中去除了个体特征。为了分析稀疏的时间序列语音，将使用新的数据采样技术来解决数据不平衡的问题，并将为所提出的模型制定数据质量度量；3.团队将进行为期18个月的实验室内评估和28个月的家庭评估，重点关注来自实验室评估的VAS任务和特征以及家庭VAS数据的重复特征是否能够测量和预测随着时间的推移家庭参与者与ADRD相关的认知下降。建议的方法将被集成到一个交互系统中，以实现患者、护理人员和临床医生之间关于ADRD状态的有效沟通。如果成功，该项目的结果将提供一个机会，为临床医生提供支持证据，以便在以临床为基础的环境之外及早发现ADRD。 项目相关性 本项目旨在开发一种低成本、被动和实用的认知评估方法，使用语音辅助系统(VAS)来早期发现ADRD相关的认知下降。如果成功，拟议的系统可能会被广泛传播，用于ADRD的早期诊断，以补充现有的诊断模式，最终可能使患者和照顾者能够长期规划，以保持个人在家中的独立性。

Early detection of Alzheimer’s Disease and Related Dementias (ADRD) in older adults living alone is essential for developing, planning, and initiating interventions and support systems to improve patients’ everyday function and quality of life. Conventional, clinic-based methods for early diagnosis are expensive, impractical, and time-consuming. This project aims to develop a low-cost, passive, and practical home-based assessment method using Voice Assistant Systems (VAS) for early detection of ADRD, including a set of novel data mining techniques for sparse time-series speech. The project has three specific aims: 1. Using a recurrent neural network (RNN) and a softmax regression model, we will develop a transfer learning technique to investigate the link between the speech from in-lab VAS tasks and cognitive decline and discover ADRD-related voice biomarkers. The Pitt Corpus speech database will be used to optimize the RNN parameters and thereby overcome the limited data problem of VAS. The softmax regression model will allow us to align the feature distributions from the previous speech data and in-lab VAS speech; 2. We will develop a novel “many-to- difference” prediction model with a symmetric RNN structure to predict the ADRD-related cognitive differences at two ends of a time period from the sparse time-series data. The proposed model is different from previous ones as the learning focus is shifted from the short-term pattern differences across users to the pattern difference over time for an individual user. The proposed model accommodates well for the highly dynamic nature of the inputs and maximally removes individual characteristics from the prediction result. To analyze the sparse time-series speech, a new data sampling technique will be used to address the imbalanced data problem, and a data quality metric will be developed for the proposed model; 3. The team will conduct an 18- month in-lab evaluation and a 28-month in-home evaluation with a focus on whether the VAS tasks and features from the in-lab evaluation and the repetition features of the in-home VAS data can measure and predict ADRD-related cognitive decline in the in-home participants over time. The proposed methods will be integrated into an interactive system to enable efficient communication on ADRD status among patients, caregivers, and clinicians. If successful, the outcomes of this project will provide an opportunity to provide supportive evidence to clinicians for the early detection of ADRD outside of a clinic-based setting. Project Relevance This project aims to develop a low-cost, passive, and practical cognitive assessment method using Voice Assistant Systems (VAS) for early detection of ADRD-related cognitive decline. If successful, the proposed system may be widely disseminated for the early diagnosis of ADRD to complement existing diagnostic modalities that could ultimately enable long-term patient and caregiver planning to maintain individual’s independence at home.