Researchers from the University of Sheffield, UK, developed CognoSpeak, an AI tool designed to accelerate the diagnosis of early signs of dementia and Alzheimer’s disease.
Backed by the NHS and the National Institute for Health and Care Research, CognoSpeak leverages AI and speech technology to analyze language and speech patterns that potentially signal these conditions.
The tool operates as a virtual agent on a laptop or tablet, engaging the patient in a conversation and performing cognitive tests and memory-probing questions similar to outpatient consultations. It then analyzes the speech and language patterns for early signs of dementia or Alzheimer’s.
CognoSpeak has shown promise in early trials, demonstrating an accuracy rate comparable to traditional pen-and-paper assessments in predicting Alzheimer’s.
For instance, a 2020 study published by the CognoSpeak team involving participants with Alzheimer’s disease, mild cognitive impairment, functional cognitive disorder, and healthy controls distinguished between Alzheimer’s/mild cognitive impairment and functional cognitive disorder/healthy controls with an accuracy of 86.7%.
CognoSpeak is now undergoing broader trials involving 700 participants from UK memory clinics.
Dr. Blackburn from the University of Sheffield described the impact of CognoSpeak: “Waiting for a possible diagnosis of dementia can be a very anxious time for patients and their families. This tool could help patients start treatments sooner, reduce waiting times and give people certainty earlier.”
He also highlighted the system’s ability to transform dementia diagnosis by speeding assessments and freeing clinicians’ time.
Professor Heidi Christensen, from the Department of Computer Science at the University of Sheffield, explained the significance of speech in detecting cognitive health: “The way a person speaks can tell us a great deal about their cognitive health and emotional wellbeing, and give us a very early indication of any signs of cognitive decline that may not otherwise have been detected.”
AI for neurological disorders
AI has shown immense promise in supporting those with forms of neurological disability or impairment, from ALS to Alzheimer’s. Speech analysis has also been used to detect and analyze schizophrenia, again by detecting subtle speech changes.
Machine learning-integrated interfaces have restored movement to previously paralyzed limbs and helped those with severe speech disabilities to communicate.
For example, an AI system replicated a 48-year-old’s speech and facial expressions onto a digital avatar, whereas others have enabled thought-controlled natural movement in robotic limbs.
Together with research like CognoSpeak, these technologies harness AI to support both patients and clinicians.
