SBIR Phase II: A tool for estimating objective outcome measures in clinical speech applications

SBIR 第二阶段：用于评估临床语音应用中客观结果测量的工具

• 批准号: 1853247
• 负责人: Shira Hahn
• 金额: $ 75万
• 依托单位: AURAL ANALYTICS, INC.
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-07-01 至 2022-12-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1853247&HistoricalAwards=false
• 关键词: SBIR; Phase; II; tool; estimating

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase II project is to introduce a set of powerful neurological health metrics for objective and reliable tracking of patient outcomes, clinician performance, and therapy efficacy. Significant societal benefits may be realized from the introduction of this technology in the clinical applications and clinical trials markets. The company's technology is easy to use, reliable, objective and cost-efficient. No other existing technology for tracking neurological health or patient outcomes shares this set of features. In the company's clinical application, the company can close the gap on current health disparities and access for 1) those in rural communities, 2) those living in urban islands with limited healthcare workforce, and 3) those too sick to travel. It enhances the practice of speech-language pathology, enabling rapid objective characterization of speech production to document treatment effects. In the clinical trials market, potential impact is enhanced by the aging of the global population, and the increasing prevalence of diseases such as Parkinson's and Alzheimer's disease. The company's technology holds promise for early detection and sensitive tracking of disease progression that provides the opportunity for global-scale impact in drug development for slowing or curing neurodegenerative disease. This Small Business Innovation Research (SBIR) Phase II project aims to address the serious challenge of tapping into brain health without expensive and invasive technologies by using speech analysis. Speaking is a deceptively complex task. Elaborate brain networks translate thoughts and ideas into sequences of movements that produce the sounds of speech. Any disturbance in these networks can lead to changes in how we speak and what we say. Research shows that subtle changes in speech precede diagnosis of many neurological diseases. Leveraging this research, the company built proprietary metrics that use speech to capture changes in neurological health. Here the company extends the analytics to detect changes in cognitive health as possible early indicators of Alzheimer's disease. The company will develop 1) a series of simple tasks to elicit speech from an individual using our app; 2) a custom speech recognition platform to automatically generate a transcript of what the person said; 3) algorithms to automatically analyze the transcript and output clinically interpretable measures of cognitive performance. Finally, the company will evaluate the validity/usability of the app in clinical settings. The product of this research is a platform ready to move toward commercialization to realize its maximum potential for health and societal impact.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

小型企业创新研究(SBIR)第二阶段项目的更广泛影响/商业潜力是引入一套强大的神经健康指标，以客观可靠地跟踪患者的结果、临床医生的表现和治疗效果。将这项技术引入临床应用和临床试验市场可能会带来显著的社会效益。该公司的技术使用方便、可靠、客观且具有成本效益。没有其他现有的跟踪神经健康或患者结果的技术共享这一组功能。在该公司的临床应用中，该公司可以缩小目前的健康差距，并为1)农村社区的人，2)居住在医疗保健劳动力有限的城市岛屿的人，以及3)病情严重而无法旅行的人提供服务。它加强了言语-语言病理学的实践，使言语产生的快速客观表征能够记录治疗效果。在临床试验市场上，全球人口老龄化以及帕金森氏症和阿尔茨海默病等疾病的日益流行增强了潜在的影响。该公司的技术有望对疾病进展进行早期检测和灵敏跟踪，从而为减缓或治疗神经退行性疾病的药物开发提供全球范围内产生影响的机会。这个小型企业创新研究(SBIR)第二阶段项目旨在通过使用语音分析来解决在不使用昂贵和侵入性技术的情况下利用大脑健康的严峻挑战。说话是一项看似复杂的任务。精心设计的大脑网络将思想和想法转化为产生语音的动作序列。这些网络中的任何干扰都可能导致我们说话方式和所说内容的改变。研究表明，在诊断许多神经系统疾病之前，语言的细微变化就会出现。利用这项研究，该公司建立了专有指标，使用语音来捕捉神经健康的变化。在这里，该公司扩展了分析，以检测认知健康的变化，作为阿尔茨海默病的早期指标。该公司将开发1)一系列简单的任务，以使用我们的应用程序从个人那里获取语音；2)定制语音识别平台，以自动生成个人所说内容的文字记录；3)自动分析文字记录并输出临床上可解释的认知表现测量的算法。最后，该公司将评估该应用程序在临床环境中的有效性/可用性。这项研究的成果是一个准备走向商业化的平台，以实现其对健康和社会影响的最大潜力。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Early detection and tracking of bulbar changes in ALS via frequent and remote speech analysis.

• DOI: 10.1038/s41746-020-00335-x
• 发表时间: 2020
• 期刊: NPJ digital medicine
• 影响因子: 15.2
• 作者: Stegmann GM;Hahn S;Liss J;Shefner J;Rutkove S;Shelton K;Duncan CJ;Berisha V
• 通讯作者: Berisha V

Automated semantic relevance as an indicator of cognitive decline: Out-of-sample validation on a large-scale longitudinal dataset.

• DOI: 10.1002/dad2.12294
• 发表时间: 2022
• 期刊: Alzheimer's & dementia (Amsterdam, Netherlands)
• 作者: Stegmann G;Hahn S;Bhandari S;Kawabata K;Shefner J;Duncan CJ;Liss J;Berisha V;Mueller K
• 通讯作者: Mueller K

Repeatability of Commonly Used Speech and Language Features for Clinical Applications.

• DOI: 10.1159/000511671
• 发表时间: 2020-09-01
• 期刊: Digital biomarkers
• 作者: Stegmann, Gabriela M;Hahn, Shira;Berisha, Visar
• 通讯作者: Berisha, Visar