Using AI in Triage: A New Era in Emergency Room Efficiency
Researchers at Yale School of Medicine and Johns Hopkins University have created an artificial intelligence program that can improve the emergency room process by making triage more efficient and accurate. Triage is the process by which nurses assess the severity of conditions at the intake of patients.
The Study
The study, published in The New England Journal of Medicine, found that nurses using the AI program were able to move patients through the emergency room process more rapidly, from initial care to assigning a bed to discharging patients. This resulted in decreased time in the ER overall.
The AI Program
The AI program, a clinical decision support tool (CDS), uses a "tree" of possible decisions to navigate and choose the best course of action. It takes into account the age, sex, arrival mode, vital signs, chief complaint, comorbidities, and active medical problems of each patient at intake.
Patient Flow Results
The study found that the number of patients grouped by high or low acuity changed, with the number of people in the "low" acuity group rising by nearly 50%, and the total in the "high" category declining by almost 9%. More older patients were moved into the high-acuity group, while more young people were moved into the low-acuity group.
Efficiency Isn’t the Only Outcome
The study also found that the number of patients properly assigned to critical care rose when using the CDS, meaning patients who eventually wound up dying in the hospital or being admitted to the intensive care unit were more accurately identified beforehand during triage.
Limitations
The study had several limitations, including the uncertainty about the role of human nurses’ individual acumen, seasonal trends in different ERs, and the limitations of electronic health records.
Conclusion
The study shows that AI can lead to improved triage performance and patient flow, with a marked change in the triage process. However, future research should consider longer-term factors to fully understand the implications of AI support in clinical decision-making within emergency settings.
FAQs
- What is triage in an emergency room?
Triage is the process by which nurses assess the severity of conditions at the intake of patients. - What is the AI program used in the study?
The AI program is a clinical decision support tool (CDS) that uses a "tree" of possible decisions to navigate and choose the best course of action. - What were the results of the study?
The study found that nurses using the AI program were able to move patients through the emergency room process more rapidly, with decreased time in the ER overall. - What are the limitations of the study?
The study had several limitations, including the uncertainty about the role of human nurses’ individual acumen, seasonal trends in different ERs, and the limitations of electronic health records.
