De-Identified Patient Data Access from EHR’s Fueling COVID-19 Research

De-Identified Patient Data Access from EHR’s Fueling COVID-19 Research

EHR and data vendors are putting together and allowing access to de-identified patient data repositories to help their clients and researchers battle the spread of COVID-19.


To make the data de-identified, identifiers must be removed from patient health information. The list of identifiers includes names, all geographic data (state, address, zip code, etc.), birth date, telephone numbers, Social Security numbers, and other information that can identify a specific individual.


Patients are beginning to understand the importance of sharing their data to help researchers in the future.


According to a study published in JAMA Network Open, only 3.7 percent of individuals said they are not comfortable with sharing their data for research and 72.9 percent said they would be willing to share their data selectively.


And now, as the healthcare industry dogged down by COVID-19 spread works toward a vaccine and treatment option for the disease, health data giants are capitalizing on that patient preference. Across the country, different EHR vendors and health technology leaders are using the data patients have shared and making it available to researchers.


EHR vendor, Cerner, is now offering free access to health systems and research centers to its de-identified COVID-19 patient data.


The vendor says access to this data set will help researchers conduct epidemiological studies, clinical trials, and COVID-19 medical treatments.


“Cerner believes deeply in the power of clinical data to advance global research,” said Donald Trigg, president of Cerner.


“The current COVID-19 pandemic compelled our team to develop a strategy to help leading health systems advance the search for critical solutions,” Trigg continued. “When we ultimately move from crisis response to recovery, I am hopeful it will also demonstrate the promise of a ‘learning heath network’ to accelerate the next generation of discovery.”


Cerner’s de-identified data is located in its HealtheDataLab, which is run by Amazon Web Services (AWS). The data set includes coronavirus-related demographics that can be utilized to help curb the spread of the virus.


Last year, Cerner and AWS utilized de-identified data to help reduce re-admissions to hospitals and make early determinations on why patients were returning to the hospital.


“This is a pivotal moment in time when having access to the right information at the right time can help save lives,” said Shez Partovi, MD, director of Worldwide Business Development for Healthcare, Life Sciences, and Genomics for AWS.


“By supporting complimentary access to Cerner HealtheDataLab there is an opportunity to bring health systems, academic medical centers and technology efforts together to securely share information and approaches to better understand, combat and contain COVID-19.”


Cerner has been making an effort to work with researchers to give clinicians more access to data.


“This opportunity with Cerner is an important example of how access to open science benefits the needs of providers, patients and communities,” said Eric Peterson, MD, of the Duke Clinical Research Institute and strategic adviser at Cerner. “By harnessing the power of these data sets, researchers can quickly, securely and freely answer scientific questions about this pandemic.”


While Cerner is leveraging its de-identified data as an EHR vendor, Health Catalyst, which is a data and analytics technology company, is doing the same.


Health Catalyst is using its Touchstone data platform that is home to over 80 million de-identified patient data records to try and answer the tough questions that are being asked about COVID-19.


Using its data from over 20 different EHR vendor systems, the company is trying to see how existing treatments may impact patient outcomes, while also getting insights on surveillance, testing, capacity planning, and treatment responses.


The platform is extremely detailed, allowing viewers to see data of every healthcare encounter from orders, medications, labs, therapies, and observations.


“There are essentially two strategies for managing COVID-19, and both require vast amounts of this data,” said Sadiqa Mahmood, senior vice president and general manager of Health Catalyst’s Life Sciences Business. “First, we need better testing and therapeutic treatment options in the near term to improve the testing, care and survival of COVID-19 patients.”


“Second, and longer term, we need a vaccine to protect the population. Both strategies are fundamentally reliant upon large and granular clinical data sets,” continued Mahmood. “There are several large commercial and public data sets in healthcare, but the most valuable data in fighting COVID-19 comes from the real-world clinical data extracted from electronic health records.”


Next, a group of research companies and health organizations partnered to develop the COVID-19 Research Database, which is a data repository that shows de-identified data to researchers and lawmakers across the country.


Like the other two databases, this one aims to uncover EHR and claims data that will help fuel COVID-19 research.


“The first challenge that many researchers have run into with this crisis is the difficulty of accessing high-quality health data that can be used to answer pressing questions such as drug and non-drug treatment effects, factors that drive differential risk of catching the disease and very different outcomes in those who do,” said Mark Cullen, MD, professor of medicine at Stanford University and the head of the COVID-19 Research Database Scientific Steering Committee.


“As a massive public-private collaboration, the COVID-19 Research Database offers researchers a solution and a chance to dramatically accelerate our understanding of this highly infectious virus.”


To give researchers more information to help curb the spread of COVID-19, the access to de-identified data is crucial.





Subscribe Our Newsletter
to get Coronavirus Updates