Nurse meets with patient

Study Reveals the Role of Verbal Cues in Home Health Care

In the realm of patient-nurse interactions, a Columbia University School of Nursing study published in the Journal of American Medical Informatics Association makes a compelling case for integrating verbal cues into home health care.  

Home health care serves over 6 million patients in the U.S., a significant number of whom are aged 65 and older and grappling with chronic conditions. Alarmingly, one in three patients receiving care at home eventually requires emergency department visits or hospitalization. Conventional risk identification models, which rely on electronic health record data and are used to determine if a patient needs elevated care, have yielded only modest success in identifying these high-risk cases. 

To conduct the study, published October 17, 2023, the research team collaborated with VNS Health, one of the nation's largest home- and community-based health care nonprofits, and recorded 126 patient-nurse encounters involving 47 patients, eight of whom later faced emergency department visits or hospitalization. The team refined the risk models by introducing three crucial components: structured data from the Outcome and Assessment Information Set (OASIS), clinical notes, and verbal communication features. Utilizing advanced natural language processing methods, the team deciphered the nuances of patient-nurse exchanges. They found the inclusion of verbal communication data sparked a remarkable 26% improvement in risk models. Results also highlighted subtle cues — such as expressions of "sadness" and "anxiety," alongside extended periods of silence — that were indicative of high-risk patients. 

“This development holds the potential to elevate patient care, decrease hospitalization rates, and empower health care providers to swiftly identify and address risks during hospitalizations and emergency department visits,” said Maryam Zolnoori, PhD, an assistant professor of health sciences research at Columbia University School of Nursing and the study’s lead author. 

Other noteworthy study authors include Maxim Topaz, PhD, associate professor at Columbia Nursing; Zoran Kostic from the Department of Electrical Engineering at Columbia University; Kathryn H. Bowles from the School of Nursing at the University of Pennsylvania and Center for Home Care Policy & Research, VNS Health; Margaret V. McDonald, Sridevi Sridharan, and Sasha Vergez from the Center for Home Care Policy & Research, VNS Health; and Ali Zolnour from the School of Electrical and Computer Engineering, University of Tehran.