R01AG083832

Automated Speech Assessment for Diagnosis of FTD Spectrum Disorders - Project Summary/Abstract

Alzheimer’s Disease and Related Dementias (ADRDS) are major causes of death and disability in the United States, with the number of adults with ADRDS projected to reach 13 million by 2050. Among these, the Frontotemporal Degeneration (FTD) spectrum disorders are among the most common causes of dementia in younger individuals (<60y), resulting in high social and economic burden.

Diagnosis of FTD is challenging, typically requiring subspeciality expertise that is not widely available in a timely manner. Many FTD spectrum disorders manifest in speech, and speech changes can help differentiate FTD subtypes. Prior research supports the clinical utility of speech-based prediction of FTD presence and subtype.

Unfortunately, rigor of these prior studies is limited for several reasons, including small sample sizes, failure to follow predictive modeling best practices, use of research grade speech recordings, and lack of prospective validation. We propose a highly innovative approach to speech-based prediction of FTD that avoids the weaknesses of prior work.

Central to our approach is the insight that FTD may be too rare to use powerful deep learning models, but the abnormal speech characteristics seen in FTD are also seen in other disorders. Training a model to recognize these characteristics in FTD does not require limiting the dataset to FTD patients. We plan use this to our advantage.

In Aim 1 we will use a self-administered, web-based speech exam to create a large dataset of all disorders seen in our speech clinic. Recordings will be made in a standard exam room using mobile phones or tablets. Our expert speech and language pathologist will annotate the recordings with perceptual speech characteristics, such as abnormal rate or vocal strain.

The large sample size will enable us to use deep learning for what it excels at – trainable feature extraction optimized for the task at hand. We will follow predictive modeling best practices, including use of a validation set.

In Aim 2 we will apply these trained models in a large cohort spanning the FTD spectrum and extract the data from the last layer in the network, just before it makes its prediction. This is a low dimensional representation of the speech signal, but which contains the information necessary for predicting perceptual characteristics. We will use these representations to develop a nearest neighbor classifier for FTD.

Essentially, the model matches a new case to similar ones in a labeled set based on the low-dimensional representation and uses the neighborhood to assign a label for the new case. Finally, in Aim 3 we will combine our self-administered speech exam and the models from Aims 1 and 2 into a single tool and perform a prospective validation study to test performance in a clinical setting.

The predicted increase in ADRDS and lack of access to specialists will necessitate a shift in clinical practice from a few expert centers to a distributed system of non-expert providers. The digital tool we propose meets this challenge head on through scalable and easy to use automated speech analysis and prediction of FTD.

Mayo Clinic

TO ENCOURAGE BIOMEDICAL, SOCIAL, AND BEHAVIORAL RESEARCH AND RESEARCH TRAINING DIRECTED TOWARD GREATER UNDERSTANDING OF THE AGING PROCESS AND THE DISEASES, SPECIAL PROBLEMS, AND NEEDS OF PEOPLE AS THEY AGE. THE NATIONAL INSTITUTE ON AGING HAS ESTABLISHED PROGRAMS TO PURSUE THESE GOALS. THE DIVISION OF AGING BIOLOGY EMPHASIZES UNDERSTANDING THE BASIC BIOLOGICAL PROCESSES OF AGING. THE DIVISION OF GERIATRICS AND CLINICAL GERONTOLOGY SUPPORTS RESEARCH TO IMPROVE THE ABILITIES OF HEALTH CARE PRACTITIONERS TO RESPOND TO THE DISEASES AND OTHER CLINICAL PROBLEMS OF OLDER PEOPLE. THE DIVISION OF BEHAVIORAL AND SOCIAL RESEARCH SUPPORTS RESEARCH THAT WILL LEAD TO GREATER UNDERSTANDING OF THE SOCIAL, CULTURAL, ECONOMIC AND PSYCHOLOGICAL FACTORS THAT AFFECT BOTH THE PROCESS OF GROWING OLD AND THE PLACE OF OLDER PEOPLE IN SOCIETY. THE DIVISION OF NEUROSCIENCE FOSTERS RESEARCH CONCERNED WITH THE AGE-RELATED CHANGES IN THE NERVOUS SYSTEM AS WELL AS THE RELATED SENSORY, PERCEPTUAL, AND COGNITIVE PROCESSES ASSOCIATED WITH AGING AND HAS A SPECIAL EMPHASIS ON ALZHEIMER'S DISEASE. SMALL BUSINESS INNOVATION RESEARCH (SBIR) PROGRAM: TO EXPAND AND IMPROVE THE SBIR PROGRAM, TO INCREASE PRIVATE SECTOR COMMERCIALIZATION OF INNOVATIONS DERIVED FROM FEDERAL RESEARCH AND DEVELOPMENT, TO INCREASE SMALL BUSINESS PARTICIPATION IN FEDERAL RESEARCH AND DEVELOPMENT, AND TO FOSTER AND ENCOURAGE PARTICIPATION OF SOCIALLY AND ECONOMICALLY DISADVANTAGED SMALL BUSINESS CONCERNS AND WOMEN-OWNED SMALL BUSINESS CONCERNS IN TECHNOLOGICAL INNOVATION. SMALL BUSINESS TECHNOLOGY TRANSFER (STTR) PROGRAM: TO STIMULATE AND FOSTER SCIENTIFIC AND TECHNOLOGICAL INNOVATION THROUGH COOPERATIVE RESEARCH DEVELOPMENT CARRIED OUT BETWEEN SMALL BUSINESS CONCERNS AND RESEARCH INSTITUTIONS, TO FOSTER TECHNOLOGY TRANSFER BETWEEN SMALL BUSINESS CONCERNS AND RESEARCH INSTITUTIONS, TO INCREASE PRIVATE SECTOR COMMERCIALIZATION OF INNOVATIONS DERIVED FROM FEDERAL RESEARCH AND DEVELOPMENT, AND TO FOSTER AND ENCOURAGE PARTICIPATION OF SOCIALLY AND ECONOMICALLY DISADVANTAGED SMALL BUSINESS CONCERNS AND WOMEN-OWNED SMALL BUSINESS CONCERNS IN TECHNOLOGICAL INNOVATION.

93.866 - Aging Research

National Institute on Aging (NIA) [HHS - NIH]

Rochester, Minnesota 559050001 United States

Single Zip Code

Research on Current Topics in Alzheimer's Disease and Its Related Dementias (R01 Clinical Trial Optional) (PAR-22-093)

Amendment Since initial award the total obligations have increased 198% from $804,124 to $2,396,290.