mCODE: learning from everyone with cancer

LBehind the firewalls of proprietary systems lies a treasure trove of data that could help diagnose heart disease, diabetes, cancer and other conditions more quickly and accurately, and better treat those who have them. But it sits there, largely untapped, because the electronic health record infrastructure was never designed to allow organizations to easily share data.

Electronic health records were first developed in the 1960s but did not become common until about 12 years ago when the federal government provided incentives for their use. At the time, they were expected to be the solution to transparently and securely collect and share valuable patient data. EHRs would reduce the need to fax records from one doctor’s office to another and end the practice of manually entering the same information into multiple databases.

The country is not there yet. The rush to develop electronic health records has produced proprietary and competing data systems that are customized for each healthcare provider organization, such as hospitals and medical practices. In addition, it took years to develop software standards that enabled data sharing between systems. Thanks to organizations such as Health level seven international and the Office of the National Health Information Technology Coordinatorprogress has been made.

advertising

The Covid chaos has underscored the lack of standards and what electronic health records cannot do easily, such as making shareable patient data quickly available so doctors can assess which treatments have worked for which patients.

At the height of the pandemic, as doctors at the Mayo Clinic struggled to keep patients alive, medical staff frequently had to take breaks to complete long REDCap surveys to let Minnesota state health officials know how many patients they were seeing with Covid-19. The state-mandated investigations lived outside of Mayo’s regular EHR system and therefore required painstaking manual labor to record Covid case information on giant Excel spreadsheets. “When we were going through our surges, we were drowned out and overwhelmed” by all the paperwork, Priya Sampathkumar, an infectious disease and intensive care specialist at Mayo, told my team at MITER, the non-profit research and development organization I work for. System A couldn’t talk to System B. “Filling in those pieces of paper only adds insult to injury.”

advertising

Given the way electronic health records are currently structured, it is difficult, if not impossible, to share and analyze high-quality data from millions of patients in disparate health systems to stimulate research, improve current treatments and inform meaningful discussions between patients and their providers. .

For example, most of the data that leads to new cancer treatments today comes from clinical trials. That’s a problem, because these trials involve less than 6% of American adults with cancer. The percentage for children is even lower. This means that there is little information about which treatments work for which patients. Clinicians and researchers do not have easy access to data from the vast majority of cancer patients, data that could potentially identify treatments that worked well for, say, a 52-year-old Hispanic woman with diabetes as well than breast cancer or a 70-year-old man with stage 3 lung cancer.

The quest to expand standards and interoperability between electronic health record systems to improve the quality, safety and efficiency of patient care is fortunately not starting from scratch. Rapid Healthcare Interoperability (FHIR) Resources Standard facilitates data sharing by defining how health information can be exchanged between different computer networks, regardless of how it is stored in those systems.

In 2019, MITER and several other nonprofit organizations have launched an effort to develop a common standard and language for cancer care that could be incorporated into EHRs and used to capture the characteristics, treatments, and outcomes of each person with cancer. cancer. We built our standard on existing best practices, such as HL7’s experience in developing the Fast Healthcare Interoperability Resources standard.

The result, mCODE (short for Minimal Common Oncology Data Elements), is currently being tested by more than 60 healthcare organizations and other stakeholders – including EHR providers – who see the potential to learn from the experiences of millions of patients. We chose cancer to test the hypothesis that only a minimal amount of critical information is needed to produce valid results comparable to those found in clinical trial reports.

We also learned about the need to engage the community to build consensus around new standards and move them forward. mCODE was developed by a multidisciplinary group of subject matter experts, including cancer clinicians, computer scientists, health services researchers, data standards and interoperability experts, people living with cancer, and others under the auspices of MITER and the American Society of Clinical Oncology.

Rather than focusing on data exchange standards, mCODE aims to standardize health records so that various stakeholders can share information in meaningful ways to achieve large-scale results, such as more efficient research, faster trial matching and more personalized medicine. Using mCODE’s common data language and non-proprietary open source model, organizations can access and analyze data from various EHR systems, including critical data that may be difficult to find today, such as stadiums of patients’ cancer or the results of specific treatments.

In its first pilot project, the mCODE team collaborated with a clinical trials group that is testing a new use for an existing drug to treat breast cancer. Early results on preliminary data, not yet published, indicate that the accuracy of mCODE results matches those of the clinical trial team 95% of the time. Since then, mCODE has been incorporated into several other clinical trials and is being tested for other uses, such as cancer registries and prior authorization of treatments. The team also freely shares its expertise and open source technology with organizations involved in heart disease, genomics and dementia who wish to use the mCODE approach to develop and test standards for their specialties.

With a standards-based approach like mCODE, every physician would have valuable information about a patient’s disease and possible treatments at the point of care at their fingertips. The knowledge has the potential to improve patient care and shared decision-making, drive innovation, and lay the foundation for a national cancer health learning system.

The possibilities for improving patient care and research with shareable data are endless. But it will take the whole community to make this happen: electronic health record vendors, health systems, payers, researchers and patients. It will also require a change in incentives. Many players today, such as EHR providers and healthcare systems, have made their patient data proprietary, believing it gives them a competitive advantage. This is no longer the case, as no single organization can ever have enough data on its own to solve big problems.

As doctors, scientists, and patients desperate for effective treatments see the clear benefits of access to large-scale data, they will push this approach forward. Unleashing the potential of these proprietary systems couldn’t be more important.

Jay J. Schnitzer is a pediatric surgeon and Senior Vice President, Chief Medical Officer and Chief Technology Officer at MITRE.

First Notice Bulletin: If you enjoy reading opinion and perspective essays, get a weekly top opinion digest delivered to your inbox every Sunday. register here.