Healthcare-associated violence negatively impacts patients, families, and healthcare workers, but it largely goes under-reported, according to a release by Connecticut Children’s.
In a study titled “Surveillance of Healthcare-Associated Violence Using Natural Language Processing” published in the August 2024 issue of Pediatrics, “researchers utilized an artificial intelligence tool to search nurses’ notes and identify unreported incidents of verbal and physical violence against nurses.” According to the release, this study, funded by the Agency for Healthcare Research and Quality, “highlights the potential of artificial intelligence to enhance the reporting and management of healthcare-associated violence.”
The study involved scanning more than 19,000 nurses’ notes from 2,827 inpatients visits between July and December 2022. According to the release, the authors “made sure visits from tertiary care pediatric as well an urban community hospitals were represented to show feasibility and generalizability. Researchers defined healthcare-associated violence as intentional actions by a patient or caregiver in the setting of care delivery that have the potential to cause harm or insult, to self or others. The focus was on nursing notes, given that data suggest nurses are most often the victims of healthcare-associated assault.”
The natural language processing tool identified 26 violent episodes that met the hospital’s criteria for workplace violence, only seven of which had been previously reported. The breakdown of these episodes included six new cases of physical assault, one case of verbal assault, seven outbursts requiring physical or medical restraint of patients, six self-harm cases, and four cases where patients assaulted their own family members while inpatient.
Amir Kimia, one of the study’s lead researchers, stated, “This study underscores the importance of leveraging artificial intelligence to identify and report healthcare-associated violence more effectively. By improving our surveillance capabilities, we can better protect our healthcare workers and create a safer environment for both staff and patients.”
Connecticut Children’s Physician-in-Chief, Juan Salazar, emphasized the significance of the findings: “Healthcare workers, especially nurses, often face significant risks that go unreported. The use of artificial intelligence in this study can provides us with a powerful tool to uncover hidden incidents of violence and take proactive steps to address them. Our goal is to enhance safety measures, reduce staff harm and burnout, and ensure a safer environment for everyone involved in patient care.”
The authors of the study suggest that “artificial intelligence can play a crucial role in identifying healthcare-associated violence and improving reporting processes. This advancement could ultimately lead to enhanced safety for both patients and staff, reducing incidents of harm and alleviating burnout among healthcare workers,” the release said.
Originally Published:
link