How Voice Recognition and Writing Could Predict Alzheimer's Risk

Framingham Heart Study researcher Rhoda Au is using digital voice recordings and a digital pen to determine whether changes in Framingham, Mass., residents' voices or how they write could help predict their risk of Alzheimer's, reports Being Patient . "I realized there's a richness in participants' response to neuropsychological tests," Au recalls. She says in recording their responses over the years, she learned the voice itself offers valuable data. "When you are testing people, you can hear differences over time," Au notes. "They may still test well, but they're starting to hesitate, have more difficulty finding the right word, they may choose a different one. There's lots of strategies people can have that makes them still look like they normally are, but that they're starting to shift." Voice analysis focusing on speech text features, audio qualities like pitch or tone shifts, hesitation, pauses, stutters, and fragmented sentences could differentiate cognitively impaired and normal subjects. Au adds that the writing analysis test involves a digital pen, then reading the pen strokes as derived measures. The procedure is designed to spot decision-making latencies, which as they grow longer may reflect changes in the subject's cognitive-processing ability.