"If we weren’t already doing it this way, is this how we would start?”
Last week, I was at a healthcare conference in Boston where Paul DePodesta, current chief strategy officer for the NFL’s Cleveland Browns, delivered the event’s closing keynote. DePodesta, who is most well-known for his appearance in the book and movie Moneyball, which was based on the MLB’s Oakland Athletics’ analytical, evidence-based, sabermetric approach to assembling a competitive baseball team, was called an “analytics expert” by the local Cleveland media when the Browns hired him.
But DePodesta was not at the conference to talk about healthcare or health IT; rather to discuss how to sharpen an organization’s competitive edge through a variety of innovative approaches centered on big data and applicable analytics. Indeed, the “moneyball” methodology has become a core strategy for business leaders looking for new approaches for revamping stagnant systems.
The above quote from DePodesta makes me think about clinical documentation, and how new approaches are helping to transform how physician notes are generated. As I wrote about in the Healthcare Informatics September/October cover story, in the shift to value-based healthcare, increased demands have been placed on physicians to be far more accurate in the clinical record. As you may have heard already, MDs feel more stressed out than perhaps ever before, with documentation burdens serving as a leading driver for that tension.
As Rasu Shrestha, M.D., chief innovation officer for UPMC (University of Pittsburgh Medical Center), said in the feature story, physicians’ caseload indexes continue to increase, and oftentimes the severity of these patients’ conditions continues to increase. “And the options we have around how we treat these patients continue to go up, too. What all this means is that there is a lot of pressure amongst clinicians to up their game, not just doing the clerical work that’s required around the care process, but also meeting the demands of their large caseloads. And at the same time you cannot falter; if one thing goes wrong, there’s a human life at the other end,” Shrestha said.
Indeed, with healthcare comes an enormous amount of responsibility to be right—and not just most of the time, but every time. So what can be done to alleviate these pressures so that doctors can go back to focusing on what they do best, which is taking care of patients?
As I noted in the story, UPMC is just one leading healthcare organization that has taken to natural language processing (NLP) to aid in clinical documentation. NLP—a technology that allows providers to gather and analyze unstructured data, such as free-text notes—has great potential to increase efficiency without detriment in document quality, as some researchers have stated, since it can make sense of the unstructured free text that is often “trapped” in clinical notes.
For instance, in the story, Elizabeth Marshall, M.D., director of clinical analytics at Linguamatics, a U.K.-based NLP-based text mining software provider, simplified how the technology can be so helpful with documentation. Marshall noted that structured data does a very good job of telling the “what” of a patient’s story, as in what has happened to them (what the patient’s conditions, procedures, and labs are, for instance), but this structured data is limited when it comes to telling the “why,” as the why is predominantly hidden in unstructured form.
She added that if the patient has documented uncontrolled diabetes, this can be well represented in structured form. “But, why is it uncontrolled? Maybe the patient simply doesn’t want to take the medications, or perhaps he or she is unable to get to the pharmacy, or maybe he or she has a form of cognitive impairment and forgets to take his or her meds. What we need to know to answer that question is, what’s the underlying issue? Social determinants of health play a major role in this and they are often trapped in clinical notes. Knowing the reason why is the first step to addressing the problem, and unstructured data may be the primary place to find those answers,” Marshall said.
Meanwhile, back at UPMC, leaders at the 20-plus-hospital health system took to creating its own NLP product with the help of a then-Silicon Valley startup. The product, called HCC Scout, specifically utilizes NLP and big data to identify documentation that is in the clinical record to support the coding of specific conditions relevant to the risk adjustment model. As Shrestha told me, HCC (hierarchical condition category) coding—used by insurance companies to determine patients' future medical needs—is incredibly important when it comes to reimbursement and ICD-10 codes. UPMC implemented the HCC Scout product, with its engine that looks for documentation that is relevant for the risk adjustment coding, at one of its hospitals, and in the first year alone, the hospital saw upwards of $29 million in annual revenue.