The following is a guest blog post by Dr. Chris Tackaberry, CEO of Clinithink.
There is a veritable gold mine of high value data locked inside the free text fields of all EHR systems, as well as in the free text of other sources of clinical documentation such as progress notes, discharge summaries, consult requests and diagnostic reports. In all of these sources, rich, actionable patient data is trapped in unstructured text—stored side by side with more easily accessible structured data.
Take echocardiography reports, for example. The data contained within them—specifically ejection fraction, for instance—are crucial to the management of heart failure as outlined within NQMC core measures for this serious chronic condition. Yet seldom is an ejection fraction captured as structured data. Instead, it is usually documented as free text.
Since narrative has been an inherent part of clinical workflow for many years, HIT software vendors have reasonably added free text fields to their applications. While there is clearly value in driving insights from structured data captured in such systems, the unstructured piece in free text fields remains untapped. This represents a source of potentially significant additional value that can be gleaned from EHR and other clinical documentation sources. However, conventional structured data tools do not support the ability to exploit it for use in clinical decision making.
Unlocking the clinical value in unstructured data
In the days of paper charts, highly experienced physicians were able to quickly scan large charts to find information such as allergies, medications, family history, past and current symptoms, social history, and other background detail that provided the context so critically important to any clinical encounter. This information was usually summarized in documents (discharge summaries, referrals, etc.). Ironically, such information is now more difficult to find when stored electronically.
If the existence of unstructured narrative data were known, discoverable, searchable and actionable for every patient—across any EMR or other health IT systems—the currently hidden additional diagnostic and clinical data could further increase the efficiency and quality of care. Clinical Natural Language Processing (CNLP) is a technology that enables access to unstructured narrative data which can be used to unlock this additional value. Using narrative data found in reports, web pages, transcribed output, EMRs, and other electronic sources of free text at the point of care can expand our knowledge of the patient beyond the information obtained from structured data.
Recently, the AMA issued a report in conjunction with the RAND Corporation on the need for EHR vendors to improve the software solutions they are delivering to better meet the needs of physicians. Utilizing CNLP technology to access the clinical value inherent in unstructured EHR data would allow vendors to begin addressing some of the potential improvements.
As we move from a world in which healthcare is delivered on an episodic basis retrospectively to one where care is delivered almost continuously and prospectively, CNLP increases the opportunity to deliver rich, actionable and meaningful clinical content to help improve decision-making for more accurate, evidence-based and effective care.
Dr. Chris Tackaberry is the CEO of Clinithink.