The following is a guest blog post by Dr. Mike Zalis, practicing MGH Radiologist and co-founder of QPID Health.
Remember the “World Wide Web” before search engines? Less than two decades ago, you had to know exactly what you were looking for and where it was located in order to access information. There was no Google—no search engine that would find the needle in the haystack for you. Curated directories of URLs were a start, but very quickly failed to keep up with the explosion in growth of the Web. Now our expectation is that we will be led down the path of discovery by simply entering what’s on our mind into a search box. Ill-formed, half-baked questions quickly crystalize into a line of intelligent inquiry. Technology assists us by bringing the experience of others right to our screens.
Like the Internet, EHRs are a much-needed Web of information whose time has come. For a long time, experts preached the need to migrate from a paper-based documentation systems – aka old school charts—to electronic records. Hats off to the innovators and the federal government who’ve made this migration a reality. We’ve officially arrived: the age of electronic records is here. A recent report in Health Affairs showed that 58.9% of hospital have now adopted either a basic or comprehensive EHR—this is a four-fold increase since 2010 and the number of adoptions is still growing. So, EHRs are here to stay. Now, we’re now left to answer the question of what’s next? How can we make this data usable in a timely, efficient way?
My career as a radiologist spanned a similar, prior infrastructure change and has provided perspective on what many practitioners need—what I need—to make the move to an all-electronic patient record most useful: the ability to quickly get my hands on the patient’s current status and relevant past history at the point-of-care and apply this intelligence to make the best decision possible. In addition to their transactional functions (e.g., order creation), EHRs are terrific repositories of information and they’ve created the means but not the end. But today’s EHRs are just that—repositories. They’re designed for storage, not discovery.
20 years ago, we radiologists went through a similar transition of infrastructure in the move to the PACS systems that now form the core of all modern medical imaging. Initially, these highly engineered systems attempted to replicate the storage, display, and annotation functions that radiologists had until then performed on film. Initially, they were clunky and in many ways, inefficient to use. And it wasn’t until several years after that initial digital transition that technological improvements yielded the value-adding capabilities that have since dramatically improved capability, efficiency, and value of imaging services.
Something similar is happening to clinicians practicing in the age of EHRs. Publications from NEJM through InformationWeek have covered the issues of lack of usability, and increased administrative burden. The next frontier in Digital Health is for systems to find and deliver what you didn’t even know you were looking for. Systems that allow doctors to merge clinical experience with the technology, which is tireless and leaves no stone unturned. Further, technology that lets the less-experienced clinician benefit from the know-how of the more experienced.
To me, Digital Health means making every clinician the smartest in the room. It’s filtering the right information—organized fluidly according to the clinical concepts and complex guidelines that organize best practice—to empower clinicians to best serve our patients. Further, when Digital Health matures, the technology won’t make us think less—it allows us to think more, by thinking alongside us. For the foreseeable future, human experience, intuition and judgment will remain pillars of excellent clinical practice. Digital tools that permit us to exercise those uniquely human capabilities more effectively and efficiently are key to delivering a financially sustainable, high quality care at scale.
At MGH, our team of clinical and software experts took it upon ourselves some 7 years ago to make our EHR more useful in the clinical trench. The first application we launched reduced utilization of radiology studies by making clinicians aware of prior exams. Saving time and money for the system and avoiding unnecessary exposure for patients. Our solution also permitted a novel, powerful search across the entirety of a patient’s electronic health record and this capability “went viral”—starting in MGH, the application moved across departments and divisions of the hospital. Basic EHR search is a commodity, and our system has evolved well beyond its early capabilities to become an intelligent concept service platform, empowering workflow improvements all across a health care enterprise.
Now, when my colleagues move to other hospitals, they speak to how impossible it is to practice medicine without EHR intelligence—like suddenly being forced to navigate the Internet without Google again. Today at QPID Health, we are pushing the envelope to make it easy to find the Little Data about the patient that is essential to good care. Helping clinicians work smarter, not harder.
The reason I chose to become a physician was to help solve problems and deliver quality care—it’s immensely gratifying to contribute to a solution that allows physicians to do just that.
Dr. Mike Zalis is Co-founder and Chief Medical Officer of QPID Health, an associate professor at Harvard Medical School, and a board certified Radiologist serving part-time at Massachusetts General Hospital in Interventional Radiology. Mike’s deep knowledge of what clinicians need to practice most effectively and his ability to translate those needs into software solutions inform QPID’s development efforts. QPID software uses a scalable cloud-based architecture and leverages advanced concept-based natural language processing to extract patient insights from data stored in EHRs. QPID’s applciations support decision making at the point of care as well as population health and revenue cycle needs.