It is widely recognized that social determinants of health (SDOH) can have a much greater impact than physical health in determining the overall well-being of individuals, particularly in underserved communities. However, gaining an understanding of how specific SDOH factors affect individuals is extremely difficult because data on SDOH are not systematically collected by clinicians.
Although SDOH data exists in patient records, it is too difficult and time-consuming for clinicians to make sense of it because SDOH-related information is usually buried in patient notes. This problem ultimately hinders their ability to use data to inform decisions about people receiving care.
Natural language processing (NLP)—a key AI discipline that uses computers to understand the written word—can overcome this challenge, and I encourage health and human services organizations and hospitals to explore this method of inferring SDOH data, especially as technological innovation in this area has developed significantly over the past few years.
Here are the top three reasons why health and human services organizations and hospitals should adopt NLP to make sense of SDOH.
1. Cost savings and more efficient care: As it stands, clinicians, therapists, and caseworkers spend an inordinate amount of time reading typed or handwritten case notes to understand their patients’ conditions and identify potential courses of treatment. This is simply wasted time that could be better spent interacting directly with the patient.
The magic of NLP is that it can automatically highlight impactful indicators and trends in case or patient notes and therefore quickly reveal SDOH to caseworkers and case clinicians. The NLP platform can relieve health and social care workers of the time required to sift through unmanageable amounts of records by easily highlighting SDOH in a case.
2. Improved results: NLP empowers caseworkers and clinicians with the information they need to make impactful decisions and enables supervisors to maximize the quality of care provided. This is because NLP provides a deeper understanding of a patient or case.
The Gravity Project is a national community collaboration creating diagnosis codes for SDOH factors with the goal of incorporating these codes into the existing list of medical diagnosis codes. NLP can extract the information in unstructured data such as case notes to support and translate it into SDOH-related diagnostic codes. These diagnoses would then trigger interventions that improve outcomes.
3. Risk reduction: NLP enables organizations to quickly identify patients at the highest level of risk so that interventions can be targeted to those most in need of services. I firmly believe that you can only truly identify risk by understanding what is included in the narrative data. Most risk stratification systems today simply look at claims data to do this. But claims data is an incomplete picture. If care coordinators had a complete picture through the SDOH, then they would have a much better tool to identify those who are most at risk and where early interventions can prevent more serious health problems from occurring.
The case for using NLP to make sense of SDOH is clear. While it is now more widely understood that SDOH plays an important role in people’s overall health, we need to make it easier for hospitals and health and human service organizations to use and interpret this data to understand how SDOH affects individual patients. This will only help providers make the best decisions for their patients, leading to more efficient care delivery and improved outcomes.
Photo: vaeenma, Getty Images