Download PDF
Twilio > Case Studies > Parkinson's Voice Initiative: Detecting Parkinson's Disease Through Voice Analysis
Twilio Logo

Parkinson's Voice Initiative: Detecting Parkinson's Disease Through Voice Analysis

Technology Category
  • Platform as a Service (PaaS) - Application Development Platforms
  • Platform as a Service (PaaS) - Device Management Platforms
Applicable Industries
  • Electronics
  • Telecommunications
Applicable Functions
  • Product Research & Development
Use Cases
  • Onsite Human Safety Management
  • Speech Recognition
Services
  • System Integration
  • Testing & Certification
The Challenge
Parkinson's disease is a degenerative disorder of the central nervous system affecting around six million people today, with projections indicating a rise to almost 10 million by 2030. The Parkinson's Voice Initiative, a team of mathematicians and clinicians, aimed to develop a low-cost test to identify patients with Parkinson's symptoms using voice recordings. The challenge was to accurately record phone calls from around the world, analyze the voice fluctuations, tremors, and other symptoms, and compare them against sample sets of both Parkinson's sufferers and healthy individuals. The team needed a robust solution that could handle large volumes of call data and ensure a high level of accuracy.
About The Customer
The Parkinson's Voice Initiative is a team of mathematicians and clinicians based in Cambridge, MA. The initiative was founded in 2012 by Max Little, a mathematician and TED fellow who has been analyzing the human voice from a mathematical perspective since studying for his PhD at Oxford University in 2003. The initiative aims to use voice recordings to detect Parkinson's disease, potentially improving treatment management for those affected. The team developed a set of computer algorithms that can analyze fluctuations, tremors, and other symptoms in voice recordings, effectively detecting the presence of symptoms associated with the disease.
The Solution
The team developed a set of computer algorithms that could analyze symptoms in voice recordings. They used Twilio, a cloud communications platform, to record and analyze calls made by patients with Parkinson's. Participants were given a local Twilio phone number to call from any voice call enabled device. After a brief recorded prompt, participants submitted around 20-30 seconds of steady 'ahhh' voice recording. Twilio sent this data to Parkinson's Voice's programmable PHP-based platform, which collected, analyzed, and stored the recordings. The initiative also collated and contrasted this voice data with self-reported symptom data provided by health-focused social network, PatientsLikeMe, to verify symptom predictions based on the voice recordings. Twilio's robust system allowed for a 100% capture rate, ensuring the accuracy needed for the initiative.
Operational Impact
  • The Parkinson's Voice Initiative successfully opened its lines in January 2014 for a new study and collected over 600 calls from around the world by the end of the month. Twilio's system made it a simple process for each number to have its own recorded voice prompt, allowing the team to operate in different languages and offer regional/national accents. This was particularly important as many of the test subjects were elderly, and offering a familiar accent helped make the experience easier for them. The six-month project ran until June 2014, with plans to upload their findings to Sage Bionetworks, a collaborative, open-science research platform, once all the voice recordings were collated.
Quantitative Benefit
  • 6 million people currently have Parkinson's
  • 10,000 phone calls captured by Parkinson's Voice Initiative
  • 100% call capture rate

Related Case Studies.

Contact us

Let's talk!

* Required
* Required
* Required
* Invalid email address
By submitting this form, you agree that IoT ONE may contact you with insights and marketing messaging.
No thanks, I don't want to receive any marketing emails from IoT ONE.
Submit

Thank you for your message!
We will contact you soon.