Harnessing AI for Parkinson’s Research


Harnessing AI for Parkinson’s Research

by Krishna Knabe,
January 14, 2019

Last week at the annual Consumer Electronics Show (CES), one of the big stories was health technologies. During CES, The Michael J. Fox Foundation (MJFF) and IBM announced a partnership using artificial intelligence (AI) to develop a model for Parkinson’s disease.

Though they are now gaining traction, artificial intelligence strategies, such as machine learning, have been a priority for MJFF for many years. In 2013, we launched a data challenge to spur ideas for Parkinson’s disease monitoring and treatment. The winners used machine learning and data collected from smartphones to improve communication between doctors and patients about symptoms. Since then, we have supported more research using artificial intelligence to analyze Parkinson’s data, including another data challenge in 2016 with partners at GE Healthcare.
Data is the key to this endeavor. You have to have a lot of comprehensive data from patients, collected using strict protocols, before you can apply machine learning or other types of artificial intelligence to it. MJFF has made a herculean effort over the last decade to collect this data in Parkinson’s, through the Parkinson’s Progression Markers Initiative, BioFIND, the LRRK2 Cohort Consortium and other MJFF-driven studies.

In an article in HealthLeaders, Mark Frasier, PhD, our senior vice president of research programs explains: “Today our challenge is to analyze this treasure-trove of complex imaging, clinical, and molecular data… AI and machine learning technologies can help scientists identify trends and models across Parkinson’s data. These frameworks can help researchers design more efficient and accurate clinical studies and drug trials, speeding discovery and bringing new personalized treatments to patient hands faster.”

The promise of artificial intelligence is that it can uncover fresh insights and trends in data that researchers might never find because they would not know to look for it or because the data analysis required is very complex. In our project with IBM, researchers will use our PPMI data to develop a model of the distinct stages of Parkinson’s. The next step will be to use that to develop a predictive model of how the disease might continue to progress. This understanding could improve patient care, but it will also help researchers understand what to expect during a clinical trial. When designing a trial, researchers want to make sure that patients are in the trial long enough to show a benefit. If they understand stages of progression, they can understand what is likely to happen over that span of time to patients on a placebo and, conversely, the benefit (in slowing or stopping progression) in patients taking a drug.

Our partnership with IBM Research Healthcare and Life Sciences is one of several designed to foster data analysis in Parkinson’s disease. Last year, we announced a partnership with Blackfynn to analyze data in PPMI using its data integration and analysis platform. And we are making our data sets available through our collaborations with AMP PD and BRAIN Commons. Important insights into Parkinson’s disease and how to treat it lie in the data we have collected, and we are doing everything possible to make sure they get found.

TAGS: Parkinson’s Data Challenge, Research News, Industry & Nonprofit Collaboration

Parkinson’s Inosine Trial Ending Early


Posted by

Rachel Dolhun, MD, December 10, 2018

Parkinson's Inosine Trial Ending Early

Researchers recently announced that SURE-PD3, a Phase III clinical trial evaluating the potential of inosine to slow Parkinson’s progression, will end earlier than planned. At a regularly scheduled meeting, the study’s Data and Safety Monitoring Board (DSMB), a group of independent experts, reviewed trial progress and available data. Based on the study’s primary measure and timeline, the board determined that SURE-PD3 would be unable to show that inosine slows Parkinson’s progression. While disappointing, this illustrates the importance of solid trial design and measurement tools and the value of research participation. Though the outcome is not what participants and researchers hoped for, there is still much to gain.

To learn more about this study, the use of inosine, and what this news means for people with Parkinson’s, we spoke with Michael Schwarzschild, MD, PhD, SURE-PD3’s principal investigator and scientific advisor to The Michael J. Fox Foundation (MJFF).

MJFF: What is the SURE-PD3 study?

Michael Schwarzschild (MS): SURE-PD3 (Study of Urate Elevation in Parkinson’s Disease) is a Phase III clinical trial to evaluate whether increasing levels of urate (a natural antioxidant) using inosine could slow disease progression in people recently diagnosed with Parkinson’s and not yet taking dopamine medication for symptoms.

The trial is randomized and placebo-controlled, meaning that roughly half of the participants are taking inosine capsules and the other half are taking placebo capsules, which are indistinguishable from inosine and contain an inactive substance. The study also is double-blind, meaning that neither study volunteers nor researchers know who is taking inosine and who is taking placebo.

The SURE-PD3 trial is being conducted at nearly 60 sites across the United States and is funded by the National Institutes of Health (NIH)/National Institute of Neurological Disorders and Stroke (NINDS).”

MJFF: Why were you interested in studying inosine?

MS: Parkinson’s disease occurs and progresses because the cells in the brain that make dopamine and are essential for voluntary movements are damaged and lost. In laboratory studies, urate protects these brain cells. In epidemiological, or population, studies, researchers have found an association between higher levels of urate and a lower risk of Parkinson’s as well as slower disease progression in people with Parkinson’s.

Inosine is a precursor, or building block, to urate so it raises urate levels. Inosine has several attractive characteristics: it’s widely available over-the-counter in pill form and fairly inexpensive. It’s what’s known as a “repurposed” therapy — used for a different reason, in this case as a dietary supplement, and now being tested for safety and benefit in Parkinson’s.

SURE-PD3 built on The MJFF-funded Phase II SURE-PD trial, which demonstrated that inosine was safe, tolerable and raised urate levels in the blood and spinal fluid.

Listen to Dr. Schwarzschild discuss inosine in a podcast.

MJFF: Tell us about the design of SURE-PD3. How do you measure disease progression?

MS: SURE-PD3 enrolled 298 people who were recently diagnosed with Parkinson’s (an average of one year prior), had lower blood urate levels and had low levels of dopamine brain cells on DaT scan, a specialized brain imaging study that looks at the dopamine brain chemical system. An interesting feature of SURE-PD3 is that it is one of the first studies to use DaT scan as an “enrichment tool,” a way to ensure that the trial only enrolled people with Parkinson’s symptoms who have dopamine brain cell loss.

Through a process similar to flipping a coin, we randomly assigned half the volunteers to take inosine and the other half to take placebo. Every three months, we checked blood urate levels and, if necessary, adjusted an individual’s inosine dose to keep their urate within the range that appeared optimal in the Phase II inosine study. SURE-PD3 is unique in that instead of examining a specific dose (or doses) of inosine, we adjusted each participant’s inosine dose to target a specific urate level. Each participant was instructed to take an individualized daily dose for up to 24 months.

To monitor progression, we assessed Movement Disorder Society Unified Parkinson’s Disease Rating Scale (MDS-UPDRS) scores, a measure of movement and non-movement symptoms and ability to do daily activities, every three months. The plan was to evaluate each participant’s MDS-UPDRS score at every visit for two years.

MJFF: What other data do you collect in SURE-PD3?

MS: As I mentioned, the main goal of the study was to examine the change in MDS-UPDRS scores over time to see whether raising urate levels with inosine could slow Parkinson’s progression.

But we are collecting a large amount of additional data on other Parkinson’s features that are not captured by the MDS-UPDRS. And we also are conducting several sub-studies, most of which are funded by The Michael J. Fox Foundation. This rich and varied information on a group of people who are recently diagnosed will increase our understanding of Parkinson’s, regardless of SURE-PD3’s final results. The sub-studies include:

  • DaT scan imaging at enrollment and within three months of inosine or placebo discontinuation to see how the brain changes in early stages of disease, as well as whether inosine modifies those changes, 
  • Measures of blood plasma and genetic markers as well as whole genome sequencing to identify factors that might modify the risk of Parkinson’s or its rate of progression, and 
  • Use of technology, such as smartphone apps and surveys to measure and track symptoms remotely and more continuously.

Upon study completion, participants have the opportunity to enroll in the AT-HOME PD study, which aims to learn more about how telehealth could optimize research by tracking participants in their natural home environment and decreasing trial costs.

MJFF: Why is SURE-PD3 ending early?

MS: We recently determined that, based on the trial’s design and the main measure we’re using to track disease progression (MDS-UPDRS score change over two years), we won’t be able to show that inosine slows Parkinson’s progression. So, it doesn’t make sense to continue inosine treatment for the originally planned two years.

We obviously didn’t know this at the outset of the trial. When you begin a trial, you “make a bet” on the best way to support your idea. Our hope was that inosine could slow Parkinson’s progression and we thought we could show that by measuring MDS-UPDRS scores over two years.

Our Data and Safety Monitoring Board (DSMB) — an independent group of scientific experts and a patient advocate that regularly evaluates study safety and performance — concluded, at their most recent review, that we were not likely to show that inosine slows Parkinson’s progression. The DSMB therefore recommended that we stop the study early. Importantly, the DSMB did not note any significant safety concerns.

MJFF: What happens now?

MS: We’ve been working with each study site and each participant to systematically end the trial in a way that maximizes what we can learn from SURE-PD3 and its sub-studies for the benefit of the Parkinson’s community.

Because there were no significant safety concerns prompting early closure, we’re asking participants to remain in the study but change the timeline of their participation. At their next regularly scheduled visit, participants will discontinue taking their study drug (inosine or placebo). Within the following three months, we’ll perform a final safety evaluation and a second DaT scan.

Once all participants have completed the study, we will analyze and report the data. We expect to report results of SURE-PD3 and its sub-studies by the end of 2019.

MJFF: What is the future of inosine research?

MS: It’s hard to say right now. When we have the results of SURE-PD3 next year, it may be easier to express an opinion on whether additional research is worth pursuing.

When we analyze the data, we’ll look at all the measures in SURE-PD3 and its sub-studies — not just MDS-UPDRS — for any hint of benefit with inosine. Given what the DSMB has already seen when reviewing changes in MDS-UPDRS scores, we likely will not see improvement on movement symptoms. But perhaps we could see positive change on cognition, mood, or quality of life, or in a sub-population of people with Parkinson’s. If we do, this may warrant further study. Conversely, if the results for other measures are consistent with the interim analysis, then inosine likely would not merit any more research for its potential to slow disease progression.

MJFF: How do studies like SURE-PD3 advance our understanding, even when their outcome isn’t as anticipated?

MS: When a study ends early and you don’t get the results you hoped for, it’s certainly disappointing. But once you get over that initial disappointment, you can see there’s still a lot to learn. No matter the results of SURE-PD3, urate remains a clue in Parkinson’s. Laboratory and population studies show that urate is linked to Parkinson’s. The results from SURE-PD3 may still help us learn more about the role of urate in Parkinson’s and new ways to target the disease. And if inosine isn’t the way to slow disease progression, that’s beneficial too. It helps us close one door so we can now walk through another, and each door we try gets us closer to our goal.

The time, effort and information that research participants volunteer is extremely valuable. Even when results are negative, there are still successes. Every bit of data we gather contributes to and broadens our understanding so that we can ask smarter questions about the causes of Parkinson’s, pick better candidates to test against those causes and design better trials to test those candidates.

MJFF: What does this mean for people with Parkinson’s who are thinking about taking inosine?

MS: Unfortunately, SURE-PD3 did not show that raising urate levels with inosine can slow Parkinson’s in the way we thought it might.

Because inosine is widely available over-the-counter, inexpensive and relatively safe, many people wonder about taking the supplement despite the lack of scientific evidence. (Don’t confuse “relatively safe” with lack of side effects; inosine can cause kidney stones, gout and possibly other harmful conditions.) I do not recommend that my Parkinson’s patients take unproven candidate protectants such as inosine to slow progression (unless, of course, they are enrolled in a clinical trial testing the therapy). If you are considering taking inosine or any other over-the-counter supplement, make sure you talk with your physician about the pros and cons and how it may fit in your regimen.

What’s the future for us


I have been diagnosed with Parkinson’s Disease 8 years ago when I’m 38 years old. At first 2 years I did not take it seriously but as the time goes by little by little I feel the symptoms and it’s very progressive. 

Causes of Parknson’s


Parkinson’s disease (PD) is an extremely diverse disorder. While no two people experience Parkinson’s the same way, there are some commonalities. Parkinson’s affects about one million people in the United States and ten million worldwide. The main finding in brains of people with PD is loss of dopaminergic neurons in the area of the brain known as thesubstantia nigra.



There is no “one way” to diagnose Parkinson’s disease (PD). However, there are various symptoms and diagnostic tests used in combination. Making an accurate diagnosis of Parkinson’s — particularly in its early stages — is difficult, but a skilled practitioner can come to a reasoned conclusion that it is PD. It is important to remember that two of the four main symptoms must be present over a period of time for a neurologist to consider a PD diagnosis:

  • Shaking or tremor
  • Slowness of movement, called bradykinesia
  • Stiffness or rigidity of the arms, legs or trunk
  • Trouble with balance and possible falls, also called postural instability

Often, a Parkinson’s diagnosis is first made by an internist or family physician. Many people seek an additional opinion from a neurologist with experience and specific training in the assessment and treatment of PD — referred to as a movement disorder specialist.

The Parkinson’s Foundation recommends that a person with symptoms resembling those of PD consider making an appointment with a movement disorder specialist. To find a specialist in your community, call our free Helpline at 1-800-4PD-INFO (473-4636) from Monday to Friday, 9:00 AM ET to 8:00 PM ET.

Page reviewed by Dr. Ryan Barmore, Movement Disorders Fellow at the University of Florida, a Parkinson’s Foundation Center of Excellence.



There is no standard treatment for Parkinson’s disease (PD). Treatment for each person with Parkinson’s is based on his or her symptoms.Treatments include medication and surgical therapy. Other treatments include lifestyle modifications, like getting more rest and exercise.There are many medications available to treat the Parkinson’s symptoms, although none yet that reverse the effects of the disease. It is common for people with PD to take a variety of these medications — all at different doses and at different times of day — to manage symptoms.While keeping track of medications can be a challenging task, understanding your medications and sticking to a schedule will provide the greatest benefit from the drugs and avoid unpleasant “off” periods due to missed doses.Page reviewed by Dr. Chauncey Spears, Movement Disorders Fellow at the University of Florida, a Parkinson’s Foundation Center of Excellence.