Artificial Intelligence Tool Identifies Healthcare-associated Violence That Might Otherwise Go Unreported

Healthcare-associated violence negatively impacts patients, families, and healthcare workers but goes largely under-reported. In a study, “Surveillance of Healthcare-Associated Violence Using Natural Language Processing” published in the August 2024 Pediatrics, researchers used an artificial intelligence tool to search nurses’ notes to identify unreported incidents of verbal and physical violence against nurses. This AHRQ funded study, published online July 8, reports on the use of a natural language processing tool that scanned more than 19,000 nurses’ notes involving 2,827 inpatients at an urban community hospital. Researchers defined healthcare-associated violence as an intentional action by a patient or caregiver in the setting of care delivery with potential to cause harm or insult, to self or to others. Surveillance activity focused on nursing notes, since data suggest that nurses are most often the victims of healthcare-associated assault. Between July-December 2022, the tool identified 26 violent episodes that would be considered as workplace violence according to the hospital’s criteria, only seven of which had been reported, according to the study. There were six ‘new’ cases of physical assault, one cases of verbal assault, seven outburst cases that required either physical or medical restraint of patients, six self-harm cases and four cases where patients assaulted their own family members while inpatient.  The authors suggest that artificial intelligence can be used to help identify healthcare-associated violence and improve reporting - ultimately to improve safety for patients and staff by reducing staff harm and burnout.

###

The American Academy of Pediatrics is an organization of 67,000 primary care pediatricians, pediatric medical subspecialists and pediatric surgical specialists dedicated to the health, safety and well-being of infants, children, adolescents and young adults.