- The rate of EHR adoption and usability of data contained in current EHR and health IT systems contribute to the healthcare industry’s lack of preparedness to benefit from the use of big data and healthcare analytics, according to new research by the Institute for Health Technology Transformation (iHT2). “Although EHR use has grown from about 20 percent of providers to some 60 percent in 2012, U.S. health care remains predominantly a paper-based system. It will take significant effort to shift attitudes and educate providers about available and emerging technologies,” note the authors of “Transforming Health Care Through Big Data.”
Even for those organizations that have successfully adopting EHR and health IT systems, the ability to manage large amounts of data lags significantly behind their ability to capture health information. “Health care organizations are accumulating 85 percent more data than they did two years ago, but 77 percent of health care executives give their organizations a ‘C’ or below for managing their data,” explain the authors, citing a Oracle survey of American and Canadian C-level executives. “Of health care executives interviewed, none gave their organizations an ‘A’ for data “preparedness.’”
And even methods for capturing patient data showed weaknesses, the authors observe:
Moreover, despite the high priority they place on implementing EHRs, health care leaders report their organizations are struggling to leverage them: while 34 percent reported being able to capture data from EHRs to help patients, 43 percent said they were unable to collect sufficient data to improve care.
Two obstacles to leveraging these captured data and the big data tools for analyzing them are the structure of the data and how this information is stored.
Of the first, the authors draw attention to the unstructured content comprising an important part of any EHR. “Most clinical data is stored in ‘unstructured’ form, especially within EHRs, making it difficult to access for effective analytics,” they continue. “For example, while individual physicians can read narrative text within an EHR, most current analytics applications cannot effectively utilize this unstructured data.”
Being largely unable to access this kind of information, the healthcare industry has come to rely on claims or administrative data, which are too far removed from the point of care to influence patient and population outcomes. As the researchers emphasize and our recent interview with Health Fidelity CEO Dan Riskin, MD, confirms, new health IT tools are emerging to tap into value trapped within unstructured data such as free text.
Of the second, the authors indicate the need to normalize health data into a central repository where big data solutions can be applied and prove valuable:
The separation, or fragmentation, of data among labs, hospital systems, financial IT systems and EHRs, is another significant obstacle to leveraging big data in health care. Each entity serves as a single repository, or silo, for information whose purpose is to provide clinical care, scheduling or billing information, or operational information. This continues to be problematic for organizations seeking to get individual systems to communicate with each other easily. It remains especially challenging in smaller organizations with multiple systems and taxonomies that make extracting useful information difficult for data mapping.
If big data is to have a big impact on the healthcare industry, namely in improvements to care delivery and health outcomes for individuals and entire populations of patients, then the industry needs to first address how it can implement, adopt, and use EHR and other health IT systems more effectively to support healthcare big data.