Practice Fusion Releases EMR Dataset, Launches Health Data Challenge with Kaggle
WASHINGTON, June 6, 2012 /PRNewswire/ — Practice Fusion, the innovative Electronic Medical Records (EMR) company, is launching a data challenge today on stage at the Health Data Initiative Forum (Health Datapalooza) conference hosted by the Institute of Medicine and US Department of Health and Human Services.
“This challenge is an opportunity to use data in developing new and unique ways to improve public health,” said Matthew Douglass, Co-founder and Vice President of Engineering at Practice Fusion. “By releasing a sample of our de-identified dataset to some of the brightest minds we hope to find new uses for clinical data and drive innovation that will improve lives.”
Practice Fusion is partnering with Kaggle, a platform for predictive data modeling competitions, to post a new 10,000 record HIPAA-compliant dataset for the challenge. The dataset includes lab results, diagnoses, medications, allergies, immunizations, vital signs and other key markers of health behavior.
“Practice Fusion has a strong track record of opening up its datasets to drive health care innovation,” said Jeremy Howard, President and Chief Scientist, Kaggle. “This latest dataset is ideal for a Kaggle Prospect challenge. With Kaggle’s nearly 40,000 data scientists analyzing Practice Fusion’s data, I’m certain we’ll see fresh, compelling ideas about how machine learning approaches can uncover hidden insights in electronic health data.”
Past Practice Fusion data challenges have sparked a range of creative visualizations, applications, analyses, and even a few start-ups. 100Plus, developed by a previous challenge contestant, is now incubating at Practice Fusion headquarters and has received $1.25 million in venture funding. Two separate data challenges are being launched today with the goal of solving healthcare problems:
- Open Challenge: Competitors are invited to combine Practice Fusion’s clinical dataset posted on Kaggle with one or more public datasets available at Data.gov. The mash-up can be used to create virtually anything. For example: a map of chronic disease across the country, a personal health app, or a tool for running clinical trials. Submissions close on August 30, 2012.
- Prediction Challenge: In the second challenge, Practice Fusion is soliciting ideas on prediction problems based on the dataset provided. Competitors can submit their prediction problems on Kaggle, using a newly launched tool for crowdsourced data prospecting. The selected prediction challenge will then be open to competition by the entire research community. For example: a model to predict diagnosis of diabetes or cholesterol changes. Submissions for ideas close on June 30, 2012. One predictive problem will be selected from the top voted submissions and the competition will begin no later than July 9 and run until September 10.
Winners and runners-up will be eligible for a total of $20,000 in cash prizes as well as beta access to Practice Fusion’s API, Dell computers, consultations with Practice Fusion’s founders, recognition on Practice Fusion’s research site and access to larger datasets. Winners will be announced during October’s Health Innovation Week in San Francisco.
About Practice Fusion’s Research Division
Practice Fusion’s Research Division provides information from one of the largest, longitudinal clinical databases in the US for the purposes of clinical research and public health analysis. With a focus on real-time insight into adverse drug reactions, disease outbreaks and other national health issues, Practice Fusion’s Research Division powers studies that are providing new insight into healthcare and how it is delivered. All research information utilized is fully de-identified and compliant with HIPAA cfr 164.514. For more information, please visit http://www.practicefusion.com/research/.
SOURCE Practice Fusion