- EHR data use can assist in clinical decision support to more efficiently identify senior patients with a high risk of falling, according to a study published in the Fall 2017 issue of AHIMA’s online journal, Perspectives in Health Information Management.
Adam Baus, PhD, et al. built a model that used EHR data for clinical decision support to improve senior fall risk screening by proactively identifying and targeting patients who would likely benefit from screening.
The final model comprised priority and extended measures. It showed an EHR data model with moderate discriminatory power could be useful in a clinical setting for identifying patients at risk of falls sooner than typical office visits.
In partnership with the West Virginia University Office of Health Services Research (OHSR), researchers conducted a retrospective analysis of de-identified EHR data from two primary care center organizations consisting of nine healthcare facilities. De-identified EHR data included patient demographics and information about patient health condition, medications, services provided, and vital signs.
Additionally, researchers convened focus groups to work together between August 2014 and January 2015 to discuss how to better support senior patient fall prevention. Focus group participants included doctors, osteopathy specialists, nurse practitioners, nurses, and medical assistants. An average of 10 healthcare team members took part in each session.
Ultimately, focus groups agreed fall risk identification and prevention efforts were often impeded by the time and energy constraints imposed on brief office visits. The brevity of patient encounters was seen as a significant barrier to fall prevention, and confirmed the need to promote data-driven, team-based care.
Focus group participants determined EHR data models designed to identify fall risk patients could assist in overcoming this barrier.
“We find that data germane to fall risk identification are routinely collected in EHRs, providing an opportunity for model building and providing the basis for development of policies and procedures to leverage informatics for fall risk screening and prevention of falls,” wrote researchers in the report.
“However, these data are not recognized as collectively pertinent to risk identification and are instead used only at the point of care in their component pieces,” the team noted.
Researchers determined there needs to be increased support and training for primary care providers to ensure EHR data about fall risk is managed and used for population-based care and intervention.
“Recognizing the potential for and benefit of repurposing routinely collected patient-level data for clinic-wide identification of at-risk patients is a prerequisite for changes in fall risk screening at the health system level,” maintained researchers.
Researchers performed analyses of the demographic characteristics, health profiles, services received, and medication records of the patient population. Researchers selected a model accounting for all risk-related factors and determined the significance of each factor in heightening the likelihood of a fall.
The research team found that female individuals aged 65 years and older with gait and balance impairment, a history of falls, a fear of falling, vision impairment, hearing impairment, Parkinson’s disease, dizziness, and certain prescriptions – among other factors – were at an especially high risk of falling.
Ultimately, the EHR data model was successful in pinpointing which factors were most significant in signaling a patient’s risk of falling.
“Increased public health efforts are needed to help foster a system-based approach to fall risk identification and prevention in primary care,” wrote researchers. “The complex healthcare needs of older adults, combined with brief office visits, result in challenges that can be addressed by enhancing the application of routinely collected data.”
Leveraging EHR data to improve upon screening efforts during office visits could improve low rates of fall risk screening and bolster senior population health management overall.
“We therefore recommend, for the Appalachian population studied, that clinical decision support based on the findings of this study be incorporated into EHRs to enable enhanced team-based care for patients at risk of unintentional falls,” concluded researchers.