Early detection and monitoring of Alzheimers Disease and Related Dementias using non-semantic linguistic and acoustic features of speech derived from hearing aids

摘要 阿尔茨海默病及相关痴呆（ADRD）是一种严重的国家健康问题， 2020年影响了580万人，预计将比2020年增加40%。 未来十年有证据表明，功能，心理，病理， ADRD潜在的生理变化可能在临床治疗前多年出现。 认知症状的表现，这增加了早期发现的兴趣 和监测，以告知个人和 人口水平。此外，老年抑郁症和与年龄有关的抑郁症的发病率较高， 与ADRD相关的听力损失在长期治疗中使治疗复杂化， 疾病鉴于需要改进措施来了解和治疗ADRD， 国家老龄化研究所的部门呼吁改进方法， 对与衰老相关的认知衰退的预后、诊断和/或治疗监测， 对早期认知变化更敏感，成本更低，而且无创。 数字健康在听力保健、语音分析和机器学习方面的进展 提供了巨大的机会，以提供具有成本效益，用户友好的认知 可以随时使用或调整的措施，以供居住在偏远、城市和 城郊社区。助听器（HA）具有数字信号处理， 语音分析所需的计算和无线通信能力 任务HA自身语音检测的独特能力有助于分析 语音的非语义语言学声学特征指示了 认知健康通过HA提取语音的非语义特征的能力是 在临床或结构化之外维护用户隐私的关键方面 对话，即在人的日常生活的正常活动。

Abstract Alzheimer’s disease and related dementias (ADRD) are a serious national health concern that affected 5.8 million in 2020 and are expected to increase by 40% over the next decade. There is evidence that the functional, psychological, pathological, and physiological changes underlying ADRD may emerge many years prior to the clinical manifestation of cognitive symptoms, which is increasing the interest in early detection and monitoring to inform disease prediction and management at both the individual and population level. In addition, the higher rates of late-life depression and age-related hearing loss associated with ADRD complicate treatment over the long duration of the disease. Given the need for improved measures to understand and treat ADRD, several divisions of the National Institute of Aging have called for improved methodologies for prognosis, diagnosis and/or treatment monitoring of aging related cognitive decline that are more sensitive to early cognitive changes, less costly and noninvasive. Advances in digital health for hearing care, speech analysis and machine learning present tremendous opportunities to provide cost-effective, user-friendly cognitive measures that can be readily used, or adapted, for persons living in remote, urban, and peri-urban communities. The hearing aids (HAs) have the digital signal processing, computational and wireless communication capabilities needed for speech-analysis tasks. The unique ability of the HA for own voice detection facilitates the analysis of non-semantic paralinguistic acoustic features of speech indicative of early changes in cognitive health. The ability to extract non-semantic features of voice through the HA is a key aspect of maintaining privacy for the user outside of clinical or structured conversations, i.e. during the person’s normal activities of daily living.