Subtle voice changes may help doctors identify multiple sclerosis faster
Companies testing whether AI can detect disease based on vocal features
Written by |
AI voice concept banner with microphone icon, sound waveform and head silhouettes. Speech recognition, voice assistant, conversational AI, audio processing and digital communication.
- AI-powered vocal analysis is being studied as a way to detect MS earlier.
- Subtle voice changes, like slurred or hoarse speech, are seen in some MS patients.
- This noninvasive method aims for faster diagnosis and improved patient outcomes.
Canary Speech and Intermountain Ventures are collaborating to test whether subtle changes in a person’s voice can help identify multiple sclerosis (MS), potentially paving the way for noninvasive tools to diagnose the disease faster.
The research will rely on Canary’s vocal biomarker technology and be led by Timothy West, MD, a neurologist at Intermountain Health’s Salt Lake Clinic in Utah. Voice samples from people with MS will be analyzed to determine whether Canary’s artificial intelligence technology can accurately detect the condition based on vocal features.
“The ability to use voice to identify MS would offer a quick, [noninvasive] screening tool, enabling us to deliver faster care to patients,” West said in a Canary press release. “We’re thrilled to collaborate with Canary Speech and leverage their innovative technology in this pioneering study.”
Canary’s system extracts 2,500-plus features from a person’s voice
In MS, the immune system mistakenly attacks healthy tissue in the brain and spinal cord, causing damage that can lead to a wide range of symptoms.
Speech requires the precise coordination of many different brain regions and muscles, and damage to any of those regions can lead to changes in speech. About 20% to 40% of people with MS are estimated to experience speech problems, including slow or slurred speech, a hoarse or nasal voice, or difficulty controlling volume or pitch.
Early diagnosis and intervention are critical to halt nervous system damage and improve long-term patient outcomes. However, the process is often complex and time-consuming, typically involving neurological exams, imaging tests, and laboratory analyses.
Partnering on this critical study will hopefully allow us to screen for MS earlier and improve the quality of care for millions of patients.
Now, researchers hope that analyzing speech patterns could provide a quicker, less invasive screening tool to help identify people who may need further testing.
Canary’s system extracts more than 2,500 features from a person’s voice and uses machine-learning algorithms to combine them to signal the presence of certain conditions. The platform is designed to analyze speech in real time, potentially allowing clinicians to assess patients during routine conversations.
According to the company, its vocal biomarker technology has already shown promise in identifying and measuring the severity of other neurological conditions, including Parkinson’s disease and Alzheimer’s disease. It may also be used to monitor patients and detect issues earlier than current methods.
“We chose to work with Intermountain Health because they are leading the way in adopting innovative technologies to serve their patients better,” said Henry O’Connell, co-founder and CEO of Canary Speech. “Partnering on this critical study will hopefully allow us to screen for MS earlier and improve the quality of care for millions of patients.”
