Alterations of speech and language are showing promise as possible early biomarkers of AD. Researchers can easily collect and analyze speech and language information using new and improved technology, hardware and data analytics. Likewise, ubiquitous use of smart devices enables remote data collection, both actively (prompted by the user) and passively (without user prompts). These tools can measure acoustic features such as pitch and amplitude, as well as lexical and syntactic aspects of speech and features of
written language such as text contextual or semantic information—all of which are associated with early AD and its progression.
Yet researchers have not been able to fully take advantage of the opportunities these tools can offer. To optimize speech and language biomarker discovery, researchers need a comprehensive speech-sample repository that covers a large, diverse cohort of subjects representing different accents, languages, speech and language components, and disease stages. They also need state-of-the-art participant characterization along with harmonized protocols and standards that cover the types of speech and language samples.
The proposed study, sponsored by the Diagnostics Accelerator at the ADDF, aims to address this gap and provide an essential resource for the advancement of speech-based detection of AD and related dementias.
The study protocol engages a global partnership between 6 clinical sites, researchers, and data scientists to meet these challenges, facilitating further identification, development and validation of speech-based biomarkers to enable researchers to apply artificial intelligence algorithms for AD screening, detection, prediction, diagnosis, and monitoring.
Data generated from the Speech and Language consortium (clinical, blood-based biomarkers, digital tests etc) will need to be harmonized across the 6 sites. MMS Holdings specializes in ensuring clinical data is properly collected, interpreted, and summarized and ensure that the collected data across each clinical site meets the required standards for integration into the Speech and
Language Consortium data warehouse. This includes checking for data completeness and standardizing the data for interoperability
across sites and for future data sharing.
The committee had previously approved $2,580,983 for 36 months (Stage 1), and stage 2 is projected to be $1,973,312 for 36 months, for the Speech and Language Consortium