NLP Tech Can Help Providers Address Social Drivers of Health

Researchers have developed algorithms that can scrub EHR notes for references to specific social factors, giving providers the data they need to improve care management and treatment.

Researchers have developed natural language processing tools to pull data from clinical notes that will help address social drivers of health.

In a study recently published in JAMIA Open, researchers at the Regenstrief Institute and the Indiana University Fairbanks School of Public Health created basic algorithms to screen unstructured notes in the EHR for data on housing challenges, financial instability, and employment status.

The technology aims to help healthcare providers address SDOH in care management and treatment plans for patients.

“Health and well-being are not just about medical care," Joshua Vest, PhD, a faculty member at both the Regenstrief Institute and Fairbanks School of Public Health and the study leader, said in a recent press release. "Mostly, they are about our behaviors, our environment, our social connections. More and more healthcare organizations are having to deal with social determinants because it is factors like financial resources, housing, and employment status that really drive costs that make people unhealthy. The challenge for healthcare organizations is effectively measuring and identifying patients with social risks so that they can intervene.”

Vest and his team developed three rule-based NLP algorithms and scanned notes from two different Indiana-based health systems, targeting keywords specific to three social factors.

"The demand from payers, policy-makers, and advocates for information on patients’ social factors and needs is substantial and multiple approaches are requested to obtain this information," they noted in their study. "In recent years, coding standards for recording social risks as structured data within EHRs using ICD-10 or LOINC codes have advanced substantially. Nevertheless, these structured data are very underutilized in practice."

The study noted that this technology would work best as part of an overall social health measurement strategy.

"It is important to not discard clinical text in favor of screening or other structured methods for data collection," the researchers noted. "However, social factors extracted via NLP could be utilized to impute missing survey results, augment survey data, or—given the ability to apply retrospectively—provide a longitudinal description of social factors. As products of a clinical encounter, these patient interactions and the information within clinical notes are important. However, it is also critical to remember that the text is, by nature, selective, filtered, and containing omissions (either left unrecorded by the provider or never volunteered by the patient). A comprehensive health measurement strategy will include formalized screening as well as information garnered from clinical documentation."

Vest said the study is one of the first to apply NLP tools to SDOH collection, and it points to the value of using a "relatively simplistic" tool to collect data from notes rather than more sophisticated AI tools that many health systems can't use or afford.

“We purposely designed a system that could run in the background, read all the notes and create tags or indicators that says this patient’s record contains data suggesting possible concern about a social indicator related to health," he said in the press release. 

"Our overall goal is to measure social determinants well enough for researchers to develop risk models and for clinicians and healthcare systems to be able to use these factors—housing challenges, financial security and employment status—in routine practice to help individuals and to provide a better understanding of the overall characteristics and needs of their patient population.”