MIT, Philips bullish on open data
January 21, 2015 in Medical Technology
Back in 2012, when Todd Park was chief technology officer of the United States, “set data free,” became his rallying cry.
“Open data and open innovation have the power to improve healthcare in America,” he would assert time and again.
[See also: Why Todd Park wants to set data free.]
Last week, Royal Philips and Massachusetts Institute of Technology answered Park’s call.
Together with MIT, Philips has launched a new initiative that gives healthcare researchers access to what the company’s executives call one of the largest data sources available on critical care.
Philips will be providing MIT access to data from more than 100,000 patients that have been collected and de-identified through the Philips Hospital to Home eICU telehealth program.
The Laboratory of Computational Physiology within the MIT Institute for Medical Engineering and Science will serve as the academic research hub for the initiative, and will provide and maintain access, as well as help educate researchers on the database and offer a platform for collaboration.
The type of data made available matters. Researchers today are limited mostly to insurance claims data, which offers just a summary of a patient’s stay.
“There’s quite a bit of heterogeneity within the ICU setting: There’s a lot of types of patients with different conditions, and there’s a lot of practices that go on in the ICU that don’t have very strong data behind it,” Omar Badawi, a researcher with Philips Healthcare, and an expert In ICU, intensive care medicine and business intelligence, told Healthcare IT News.
As he sees it, one of the “great things” about creating these large standardized databases of what’s happening in the ICU is that “we start looking at these questions that need to be answered about what type of interventions and practices that are benefitting patients and have enough data available to draw conclusions on that.”
Through this new initiative, Philips will release a more comprehensive look at the ICU patient’s journey by opening up data sets from patient stays in eICU centers representing approximately 10 percent of all adult ICU beds in the United States. The secure database will include anonymized and detailed clinical data such as vital signs, pharmacy medication orders, laboratory results, diagnoses and severity of illness scores, giving researchers comprehensive insights into a patient stay.
“Researchers are always looking for better, more accurate and comprehensive data that enables a holistic representation of the patient experience,” said Leo Anthony Celi of MIT, in a statement. “The quality and resolution of the data Philips has been collecting in the critical care domain is unprecedented. This kind of access will provide researchers with data that will enable investigations otherwise unimaginable.”
The data will be available to researchers via PhysioNet before the end of the year.
PhysioNet offers free web access to large collections of physiologic signals and related open-source software. Investigators will be able to contribute to the expanding knowledge base by sharing their methodologies and findings with the larger research community to facilitate faster discoveries in the future.
“This initiative will make it easier for researchers to share methods and findings, bypassing the need to reinvent the wheel with each new research project,” said Derek Smith, senior vice president, Hospital to Home, Philips Healthcare, in a Jan. 15 news release. “We hope this will lead to better, faster breakthroughs – and ultimately better medicine.”
The data set is compiled from records shared by hundreds of ICUs across the United States, and is managed by the Philips eICU Research Institute. This is one of the most extensive ICU-centric longitudinal data sets in existence, according to Philips.
Badawi noted that Philips and MIT have worked together in the past, with data from Beth Israel Deaconess Medical Center in Boston.
“Beth Israel had enough vision and foresight to be able to take their data and deidentify it with the MIT group and help from Philips. They allowed their ICU patient data to be available online for researchers all over the world. There’s that precedent.
“We can now take that same model and apply it across hundreds of hospitals in the U.S,” he said.