Skip to main content
Prizes

Data Challenges

Technology now allows researchers to easily collect data from people with Parkinson's disease. The data can supplement the details that doctors get from patients during appointments and help researchers develop more efficient clinical trials.

Overview

Parkinson's disease (PD) is an ideal model system for big data approaches. The Michael J. Fox Foundation (MJFF) offers large datasets to problem-solve big scientific questions in PD. Our past challenges involve the questions we want to answer in Parkinson's research.

2017 Parkinson's Disease Digital Biomarker DREAM Challenge

The Parkinson's Disease Digital Biomarker DREAM Challenge was a first-of-its-kind challenge designed to look for digital Parkinson's biomarkers, which are objective measures to diagnose and track disease. There are currently no PD biomarkers.

Launched in spring 2017, the DREAM challenge asked experts to analyze data from two studies, including MJFF's Levodopa Response Trial, which evaluated the use of a smartwatch to monitor dyskinesia (uncontrolled, involuntary movements) and "off" periods (times when symptoms return because medication is not working optimally). Funding for the challenge was provided by MJFF and the Robert Wood Johnson Foundation.

Winners, announced in January 2018, developed methods to detect PD from a walk-and-balance test, as well as to predict the severity of different Parkinson's symptoms using wearables. These approaches could increase the ability to monitor PD outside of doctors' visits.

2016 PPMI Data Challenge

The Parkinson's Progression Markers Initiative (PPMI) has generated a comprehensive, standardized, longitudinal set of clinical, biological and imaging data unique to the Parkinson's disease field and ripe for novel and innovative exploration. In mid-2016, study sponsor The Michael J. Fox Foundation (MJFF) cast an open call to computational scientists, data scientists and neuroscientists to analyze PPMI data with a view to gaining new insights into PD diagnosis and progression.

Parkinson's is highly variable, with age of onset, rate of progression, and type and severity of symptoms different among the 6 million people worldwide living with the disease. Identifying models for prognosis and subtyping would aid in subject selection for clinical studies and the design of trials related to novel therapies.

The PPMI Data Challenge, sponsored jointly by PPMI industry partner GE Healthcare and MJFF, offered $50,000 in total prizes ($25,000 per question). The Data Challenge Review Committee comprised MJFF staff and a team of external experts in statistics, data science and Parkinson's disease research. Winners were announced in December 2016.

Read more on the analysis and findings of the winners who answered the following questions:

  1. What factors are involved in baseline predict clinical progression?
  2. What are the subtypes of Parkinson's disease?

Watch our webinar of the 2016 PPMI Data Challenge winning submissions, including a detailed description of methods used, summary of results and impact of analysis to the PD research community.

2016 PPMI Data Challenge Winning Submissions Webinar

2013 Data Challenge

In February 2013, The Michael J. Fox Foundation sponsored a $10,000 Data Challenge to spur ideas for using patient data, collected using smartphones, in Parkinson’s disease monitoring and treatment. The winner of the prize — a team from LIONsolver, Inc. developed a “machine learning” approach to tackling the problem.

 

Two female doctors talking in the lab.

Apply for a Grant

Our funding programs support basic, translational and clinical research from academia and industry.

See Funding Opportunities
We use cookies to ensure that you get the best experience. By continuing to use this website, you indicate that you have read our Terms of Service and Privacy Policy.