Validation ki:e SB-C

We are grateful to announce that we will soon be collaborating in a major new decentralized trial, funded by the Alzheimer Drug Discoveries Foundation (ADDF) Diagnostics Accelerator, who advance the development of reliable and affordable biomarkers for Alzheimer’s disease.

The financing will be used for a longitudinal, epidemiologic cohort study across Europe, called “PROSPECT-AD”, which aims to develop remote, speech biomarkers used for pre-screening for future AD trial onboarding to accelerate drug development. To achieve this goal, preclinical, readily phenotyped AD patients from the Scottish EPAD cohort, the French INSIGHT I cohort, the German DESCRIBE cohort, and the Swedish BioFINDER cohort will be evaluated for 18 months in a follow-up design. Subjects undergo a semi- or fully automated speech task protocol on the telephone at regular time points. The speech patterns will be compared to known biomarkers of Alzheimer’s disease, such as CSF (cerebrospinal fluid) amyloid 1-42 and CSF p-Tau. If speech biomarkers can be identified in Alzheimer’s disease or Alzheimer’s dementia, intensive and invasive gold standard biomarker methods currently used, such as lumbar punctures and PET scans can be omitted.

The project is thus in line with ki:element’s mission to develop a digital speech-based biomarker for cognition (ki:e-SB-C) in preclinical Alzheimer’s disease. A relevant step in the development of a biomarker as an enrichment tool or exploratory endpoint in AD clinical trials is to validate that the biomarker captures the intended concept of interest and is clinically meaningful. Since the ki:e SB-C is also conducted fully automatic via the telephone, insights about the psychometric properties of this examination can be derived from the PROSPECT-AD study. This is important, as many cognitive tests are validated for face to face assessments, but only few are validated for assessment via the phone. It is important to understand how these tasks perform in this novel environment and what ceiling effects are seen. This is important to understand as the ability to employ a staff supported or fully automated system has both immediate (research testing able to take place regardless of lockdown guidelines in place in response to the Covid-19 pandemic) and long term (involvement of participants who previously wouldn’t have been able to engage with research projects if they couldn’t access a site due to health or geographical limitations) benefits. Specialist staff costs can be reduced and identical administration of the task for each participant is guaranteed. Participants will complete a survey to report acceptability of both baseline and follow up testing sessions to measure patient burden and user experience.

Having access to such a large dataset of gold-standard phenotyped preclinical AD patients in four different languages is a major asset in the validation of the ki:e SB-C speech biomarkers for preclinical AD.