Abstract Details

Title A fully automated cognitive screening tool based on assessment of speech and language

Topic Aging, Dementia, and Behavioral Neurology

Presentation(s) P16 - Poster Session 16 (5:30 PM-6:30 PM)

Poster/Presentation
Number 10-003

Objective To determine the diagnostic accuracy of "CognoSpeak", a fully automated system designed to aid in the screening and monitoring of cognitive disorders.

Background The dramatic recent rise in referrals to specialist memory clinics has been associated with an increased proportion of patients referred with Functional Memory Disorder (FMD), i.e. non-progressive cognitive complaints. These referrals have exerted time and financial pressures on secondary care services, impairing their ability to deliver high-quality care for patients with neurodegenerative cognitive disorders. We have developed a fully automated system, “CognoSpeak”, which enables risk stratification at the primary-secondary care interface and ongoing monitoring of patients with memory concerns.

Design/Methods We recruited 15 participants to each of four groups: Alzheimer’s disease (AD), Mild Cognitive Impairment (MCI), FMD and healthy controls. Participants responded to 12 questions posed by a computer-presented talking head. Automatic analysis of the audio and speech data involved speaker segmentation, automatic speech recognition and machine learning classification.

Results CognoSpeak could distinguish between participants in the AD or MCI groups and those in the FMD or healthy control groups with a sensitivity of 86.7%. Patients with MCI were identified with a sensitivity of 80%.

Conclusions Our fully automated system achieved levels of accuracy comparable to currently available, manually administered assessments. Greater accuracy should be achievable through further system training with a greater number of users, the inclusion of verbal fluency tasks and mood assessments. The current data supports CognoSpeak’s promise as a screening and monitoring tool for patients with MCI. Pending confirmation of these findings, it may allow clinicians to offer patients at low risk of dementia earlier reassurance and relieve pressures on specialist memory services.

Authors/Disclosures
PRESENTER	No disclosure on file
	No disclosure on file
	No disclosure on file
	No disclosure on file
Markus Reuber (Sheffield Teaching Hospitals NHS Trust)	No disclosure on file
Annalena Venneri, PhD (Brunel University London)	No disclosure on file
	No disclosure on file
Daniel Blackburn, MD	No disclosure on file

��ɫ��

��ɫ��