AUTHOR=Gregory Sarah , Harrison John , Herrmann Janna , Hunter Matthew , Jenkins Natalie , König Alexandra , Linz Nicklas , Luz Saturnino , Mallick Elisa , Pullen Hannah , Welstead Miles , Ruhmel Stephen , Tröger Johannes , Ritchie Craig W. 

TITLE=Remote data collection speech analysis in people at risk for Alzheimer's disease dementia: usability and acceptability results

JOURNAL=Frontiers in Dementia

VOLUME=Volume 2 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/dementia/articles/10.3389/frdem.2023.1271156

DOI=10.3389/frdem.2023.1271156

ISSN=2813-3919

ABSTRACT=Digital cognitive assessments are gathering importance for the decentralized remote clinical trials of the future. Before including such assessments in clinical trials, they must be tested to confirm feasibility and acceptability with the intended participant group. This study presents usability and acceptability data from the Speech on the Phone Assessment (SPeAk) study. Participants (n=68, mean age 70.43 years, 52.9% male) provided demographic data and completed baseline and three-month follow-up phone-based assessments. The baseline visit was administered by a trained researcher and included a spontaneous speech assessment and a brief cognitive battery (immediate and delayed recall, digit span and verbal fluency). The follow-up visit repeated the cognitive battery and was administered by an automatic phonebot. Participants were randomized to receive their cognitive test results after the final or after each study visit. Participants completed acceptability questionnaires electronically after each study visit. There was excellent retention (98.5%), few technical issues (n=5) and good inter-rater reliability. Participants rated the assessment as acceptable, confirming the ease of use of the technology and comfort of completing cognitive tasks on the phone. Participants generally reported feeling happy to receive their cognitive tests results, and this disclosure did not cause participants to feel worried. The results from this usability and acceptability analysis suggests that completing this brief battery of cognitive tests via a telephone call is both acceptable and feasible in a midlife-to-older adult population in the UK, living at risk for AD. Deleted: The application of artificial intelligence (AI) to speech 129 data allows identification of clinically relevant features when 130 compared to traditional administration (Linz, Tröger et al. 2017, 131 Linz, Tröger et al. 2017). Speech as a digital biomarker may also 132 have more ecological validity compared to more traditional 133 assessments, as data can be collected under more naturalistic settings 134 (Robin, Harrison et al. 2020).