How Tencent’s AI can diagnose Parkinson’s disease ‘within minutes’
New technology could help patients track their condition from their smartphones

The Chinese technology giant Tencent has developed an artificial intelligence (AI) programme that can speed up the process of diagnosing Parkinson’s disease.
Developed in collaboration with the London-based medical firm Medopad, the AI uses cameras that monitor how patients move their hands in order to evaluate the severity of their symptoms.
The AI has been trained to identify symptoms by studying existing video footage of Parkinson’s patients, says Forbes. The process, often referred to as machine learning, was completed with the help of London’s King’s College Hospital.
The Week
Escape your echo chamber. Get the facts behind the news, plus analysis from multiple perspectives.

Sign up for The Week's Free Newsletters
From our morning news briefing to a weekly Good News Newsletter, get the best of The Week delivered directly to your inbox.
From our morning news briefing to a weekly Good News Newsletter, get the best of The Week delivered directly to your inbox.
The process of monitoring a patient’s symptoms normally takes about half an hour, but the tech developed through the partnership could cut that down to three minutes.
According to Wei Fan, Tencent’s head of medical research, the technology would allow medical professionals to set drug dosage levels and monitor patients without the need for hospital visits, Bloomberg reports.
In an interview with the BBC, Medopad’s chief executive Dan Vahdat said the company had been hoping to create an AI programme for smartphones that was capable of detecting Parkinson’s symptoms but couldn’t find a Britain-based firm that could match “what Tencent offered as a partner.”
“Our ambition is to impact a billion patients around the world – and to be able to get to that kind of scale we need to work with partners that have international reach”, he said.
A free daily email with the biggest news stories of the day – and the best features from TheWeek.com
Can these AI techniques be used for other diseases?
If the technology developed for Parkinson’s patients proves a reliable method for tracking symptoms it’s certainly a possibility.
The technology is still a prototype. But if the AI could be transferred onto a smartphone – an area that Medopad specialises in – it could be adapted for other diseases.
Fan and Vahdat told Bloomberg that the technology could be applied to childhood brain cancers, for example. It could also be used to monitor the progression of scoliosis (a spinal condition) in younger patients.
-
Your therapist, the chatbot
Feature Americans are increasingly turning to artificial intelligence for mental health support. Is that sensible?
-
Supersized: The no-limit AI data center build-out
Feature Tech firms are investing billions to build massive AI data centers across the U.S.
-
Digital addiction: the compulsion to stay online
In depth What it is and how to stop it
-
AI workslop is muddying the American workplace
The explainer Using AI may create more work for others
-
Prayer apps: is AI playing God?
Under The Radar New chatbots are aimed at creating a new generation of believers
-
Is the UK government getting too close to Big Tech?
Today’s Big Question US-UK tech pact, supported by Nvidia and OpenAI, is part of Silicon Valley drive to ‘lock in’ American AI with US allies
-
Google: A monopoly past its prime?
Feature Google’s antitrust case ends with a slap on the wrist as courts struggle to keep up with the tech industry’s rapid changes
-
Albania’s AI government minister: a portent of things to come?
In The Spotlight A bot called Diella has been tasked with tackling the country's notorious corruption problem