Skip to main content

IBM and Michael J. Fox Foundation make a breakthrough in fighting Parkinson’s

To a generation, Michael J. Fox is Marty McFly, the plucky underdog hero of the Back to the Future movies. But, through his battles with Parkinson’s disease and his foundation’s efforts to help find a cure for the terrible neurodegenerative disorder, he’s also emerged as something of a hero in real life as well.

Recommended Videos

In early 2019, IBM Research and the Michael J. Fox Foundation announced a collaboration to dig deeper into Parkinson’s disease data with the use of cutting-edge A.I. technologies. The idea was to use new types of smart machine learning technologies to find effective treatments for a disease that has proven exceptionally difficult to treat. On Friday, August 7, the team announced new progress resulting from their collaboration.

Please enable Javascript to view this content

Specifically, they have built an A.I. that can help clinicians work out exactly how far a person’s Parkinson’s symptoms have progressed. This is a particularly difficult observation to make since medication can mask certain symptoms such as involuntary tremors. While simply categorizing the progression of a disease might not sound like a proactive move in fighting Parkinson’s, it’s a crucially important step in the process. That is because it can help medical experts to design better, more efficient personalized treatment plans for patients. It can also assist drug development by allowing scientists to better recruit the right participants for clinical trials for possible new cures.

“In this initial study, we focused on using only clinical data as measured by the Movement Disorder Society’s Unified Parkinson’s Disease Rating Scale,” Kristen Severson of IBM Research told Digital Trends. “We plan to expand our analysis to use additional data in future work. Our goal is to learn a progression model of Parkinson’s disease which uses a small number of disease states to label patients based on their symptoms and progression. Because Parkinson’s disease has diverse symptoms affecting both motor and non-motor function, disease state definitions can be complex. We hope that such a model could be used for patient care management, cohort generation, and clinical trial outcome modeling.”

There are plenty of high-tech and groundbreaking scientific approaches being explored by various labs right now when it comes to the treatment of Parkinson’s. However, when it comes to leveraging the latest machine learning tools and having access to the best supercomputers, it certainly doesn’t hurt to have a giant like IBM in your corner.

Luke Dormehl
Former Digital Trends Contributor
I'm a UK-based tech writer covering Cool Tech at Digital Trends. I've also written for Fast Company, Wired, the Guardian…
IBM’s autonomous Mayflower ship lifted into the water ahead of launch
Mayflower

Is this the era of autonomous ships?

After two years of work on design, construction, and A.I. training, the Mayflower Autonomous Ship -- a.k.a. the fully autonomous trimaran that will cross the ocean from Plymouth, England to the U.S. -- was today lifted into the waters in advance of its official launch Wednesday.

Read more
Staggering implications: Smartphones may soon use our gait to see if we’re drunk
6 photography tips for snapping better beer pics 1500x844 jpg

Researchers from Stanford University and the University of Pittsburgh have developed software that harnesses a smartphone’s built-in accelerometer, and uses this to determine whether its user might be drunk -- based entirely on how they walk.

“Every smartphone currently manufactured has many embedded sensors,” Brian Suffoletto, associate professor in emergency medicine at Stanford University, told Digital Trends. “One of these sensors is a 3-axis accelerometer. We accessed this sensor and sampled the movement in the forward-backward, side-to-side, and up-down direction 100 times per minute while individuals were walking in a straight line using a free app, Phyphox. We then cleaned the data and generated features related to walking such as step speed and variability of side-to-side movement. [After that, we] trained a model where each person served as their own control and examined how well these models, when shown new data on the individual, could discriminate between periods of intoxication and sobriety.”

Read more
A.I.’s next big challenge? Playing a quantum version of Go
alphago zero

When Google DeepMind’s AlphaGo program defeated the world’s greatest Go player in March 2016, it represented a major tech breakthrough. Go, a Chinese board game in which the goal is to surround more territory than your opponent, is a game that’s notoriously easy to learn but next to impossible to master. The total number of allowable board positions exceeds the total number of atoms in the observable universe. However, an A.I. still learned to defeat one of humanity’s best players.

But while cutting-edge technology made this possible, cutting-edge technology could also make mastering Go even more difficult for future machines -- thanks to the insertion of quantum computing concepts like entanglement to add a new element of randomness to the game.

Read more