New machine-learning model can detect dementia in speech

There are three features that indicate signs of dementia: pauses in speech, word length or complexity, and speech intelligibility.

“For dementia patients, because there might be a need for more recall, they tend to forget words and they need a certain amount of time to recall those words, so there will be longer pauses,” Shah explained.

“A longer word, we assume, will have a higher degree of speech complexity rather than shorter words like ‘uh’ and ‘the.’

“Longer word duration … is a proxy for speech complexity,” she added. “Again, the hypothesis here is that dementia patients would have lower speech complexity compared to healthy controls.”

Tests were conducted on 237 English-speaking individuals and 46 Greek-speaking individuals. Approximately half were dementia patients and the second half were a control population.

A high accuracy

The model was found to work with 70-75 percent accuracy.

“It’s like a support tool for clinical diagnosis,” Shah said. “But we don’t foresee this tool to be a diagnostic tool in and of itself. It would need a human in the loop.”

“It’s the first point, triaging, screening for potentially at-risk populations to see where they are at this point in time and possibly flagging any higher-risk individuals in this category and asking them to look into further screening.”

Although it’s too early for the new model to replace clinical diagnosis it can allow anyone with a smartphone to evaluate their risk of developing dementia-related diseases.

Shah sees the future of the model in the shape of a mobile-friendly app.

“Which would not be monitoring continuously but you can open the app and speak into it. For example, you could have the app ask you on a daily basis: ‘How is your day going?’ and the person just responds in a spontaneous manner and the app could, in the background, potentially look at features in your speech to see how it’s changed,” she told Global News.