Emergency Departments (EDs) in the United States have many problems to deal with:
All these issues make it take longer to see, treat, and discharge patients. This can lower the quality of care and make both patients and staff unhappy.
Triage means quickly checking patients when they arrive to see how urgent their care is. Usually, nurses decide the patient’s severity by giving a number from 1 to 5, where 1 is the most serious. This process is done well but can differ from one nurse to another. This causes some patients to be handled differently even if they have the same problem.
New AI tools help nurses by giving a more exact risk level. These tools look at things like vital signs, medical history, and symptoms. For example, a tool called TriageGO was created by Johns Hopkins researchers and then bought by Beckman Coulter. It works with Electronic Health Records (EHRs) and helps nurses decide within seconds. It finds patients with low risk and suggests the right level for triage. This helps nurses feel more sure about their choices.
AI reduces differences in triage decisions. In busy times or during big emergencies, AI helps keep things more fair and organized. It finds patients who need less urgent care quickly and sends them to the right place. This helps patients move through care faster.
Getting patients through care quickly depends on good triage and moving them to the next step fast. AI helps with triage and also with running the department better by predicting admissions and how long patients will stay.
Mayo Clinic researchers reviewed many AI models that use triage data to guess if patients will need to be admitted to the hospital. These models were very good at guessing, with scores between 0.81 and 0.93. When hospitals know who will be admitted, they can better manage beds and staff. This helps lower overcrowding in the ED.
AI can also warn about serious conditions early, like sepsis. This allows doctors to act faster and stop conditions from getting worse.
AI is also used to automate tasks in EDs. This helps the department run smoother and reduces work for staff.
Simbo AI is an example of a company that uses AI to answer phone calls in healthcare settings. Their voice agents work 24 hours a day. They answer patient calls, set up appointments, call back patients, and send reminders by phone or text. This lowers the number of calls staff must answer. It also lowers waiting times for patients, reduces missed appointments, and improves communication.
The AI phone system keeps patient information private by following HIPAA rules and encrypting calls. Making appointment reminders and scheduling automatic helps patient flow, especially in emergency and urgent care centers where fast care is important.
AI systems with NLP can understand notes by doctors, patient descriptions, or call records. They create accurate clinical notes and instructions automatically. This saves time for doctors and cuts down mistakes in paperwork.
AI watches patient data in real-time and sends alerts if vital signs change or if the patient’s condition is getting worse. For example, it can spot early sepsis or breathing problems, so the care team can respond quickly and change treatments if needed.
AI can predict how many patients will come at different hours. It helps schedule nurses and doctors based on these predictions. This reduces problems caused by having too many or too few staff. AI can also help decide how to use space, like opening fast-track lanes for less serious patients to speed up care.
Even though AI offers good benefits, there are some problems that healthcare leaders must think about before using it:
Many hospitals in the U.S. already use AI to help triage and run workflows. Johns Hopkins Hospital’s Emergency Departments, like Bayview Medical Center and Howard County General Hospital, use TriageGO to make triage more consistent and reliable. Tests have expanded to hospitals in Florida, Connecticut, and Missouri, showing it can work in different places.
At Virginia Hospital Center, AI helps improve how symptoms are checked and records are kept. AI tools like Simbo AI’s phone system help reduce wait times and cut down too many phone calls.
Several ongoing trends push the need for AI in emergency departments:
Many EDs see AI not just as a clinical help but also as a way to run operations better and keep patients happier.
When thinking about using AI to improve triage and patient flow, administrators and IT managers should:
Artificial intelligence is playing a bigger role in helping U.S. Emergency Departments handle growing challenges. AI tools assist triage nurses by giving objective risk levels with tools like TriageGO. They also automate front-office phone tasks with systems like Simbo AI. This helps reduce wait times, manage resources better, and move patients faster.
There are challenges such as making sure data is good, managing bias, and getting clinicians to trust AI. Still, with careful use, AI can make real improvements. Healthcare leaders are important in choosing good AI tools, helping staff use them, and keeping systems working well.
As more patients need emergency care, AI offers hospitals practical ways to improve both the quality of care and how the department runs.
The AI tool is designed to assist emergency department nurses in triaging incoming patients by predicting their risk of acute outcomes and recommending a triage level of care based on the collected data.
The tool integrates with patients’ digital health records, allowing nurses to input patient information and vital signs, which the AI uses to quickly assess risk and suggest triage levels, enhancing accuracy and efficiency.
The AI tool helps nurses confidently identify low-risk patients, enabling those individuals to receive care more efficiently, ultimately improving patient flow through emergency departments.
The AI tool is used in the emergency departments at The Johns Hopkins Hospital, Johns Hopkins Bayview Medical Center, Howard County General Hospital, and other hospitals in Florida, Connecticut, and Missouri.
The AI tool is called TriageGO, developed by the company Stocastic, which was co-founded by Scott Levin and Eric Hamrock.
The triage level, which ranges from one (the sickest) to five (the least sick), determines the path of care for patients, influencing the urgency and type of treatment they receive.
By efficiently identifying low-risk patients, the AI tool helps streamline care pathways, allowing quicker discharge for those patients and thus optimizing overall patient flow in the emergency department.
Scott Levin, an associate professor of emergency medicine, and Eric Hamrock, a health care administrator, are notable figures in the development of TriageGO and its parent company, Stocastic.
TriageGO and its parent company Stocastic were acquired by Beckman Coulter, a company specializing in clinical diagnostics.
The tool is set to launch in several hospitals in Missouri, expanding its utilization to improve triage and patient care in more emergency departments.