AI Tool Detects Early Signs of Dementia

A new AI tool built by researchers at the University of Sheffield aims to help doctors in assessing early signs of dementia. 

The tool, named CognoSpeak, is a virtual agent that asks memory-probing questions to the patient, based on outpatient consultations and cognitive tests. From there, the AI analyzes the responses from the patient for signs of Alzheimer’s disease, dementia, and other memory disorders. It then creates a report which a physician reads, who is then able to move the patient onto the appropriate care unit. 

SEE ALSO: Deep Learning in Drug Discovery Holds Great Promise

“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,” said Professor Heidi Christensen of the University of Sheffield’s Department for Computer Science. “The system we’ve developed here at Sheffield uses speech technology to automatically extract these signs and the automation means we can provide a consistent, accurate and fast assessment for everyone.”

Integrating artificial intelligence into the pathways for primary care could reduce the amount of time spent screening patients and move them onto specialists at a faster rate. Accordingly, the National Health Service in the UK and several other medical departments around the world are investigating ways to integrate AI. The NHS recently deployed an AI diagnostic tool for stroke recovery, with similar improvements to the speed of diagnosis and secondary care delivery.  

“Waiting for a possible diagnosis of dementia can be a very anxious time for patients and their families,” said Dr. Dan Blackburn, a professor at the University of Sheffield’s Department of Neuroscience, in a release. “This tool could help patients start treatments sooner, reduce waiting times and give people certainty earlier. The CognoSpeak system could transform how dementia and other memory disorders are diagnosed by speeding up assessments. This would also free-up clinicians’ valuable time and mean that those who need specialist care get access to it as quickly as possible.”

Having artificial intelligence as the judgment call of a person’s health might seem like a worrying thought for some, however, without the integration of tools for automating the diagnosis patients could be looking at waiting times of months before a diagnosis. This is especially true for centralized health systems, such as in the UK, where it is more difficult for a patient to shift their healthcare provider. 

The team developing the CognoSpeak system demonstrated an accuracy of 90 percent in trial tests at predicting the Alzheimer’s disease, which is as accurate as current pen-and-paper tests deployed in the UK. The obvious benefits of these tests is, once accepted by the NHS and other medical services, they can be completed by the patient at home in a few minutes and results can be sent to practitioners in a few hours. 

Outside of speeding up diagnostics and other clinician time, AI is also being deployed as a way to speed up drug discovery and formulate new protein and amino acid patterns. Market researchers project that healthcare and pharmaceutical industries could be two of the most impacted industries by AI in the next decade, due to the multitude of use cases and potential return on investment.