AI vs. Human Expertise: Study Reveals Limitations of AI in Emergency Triage

Doctors and nurses are better than AI at triaging patients, research indicates

Doctors and nurses are better at triaging patients in emergency departments than artificial intelligence (AI), according to research presented at the European Emergency Medicine Congress. However, Dr. Renata Jukneviciene, a postdoctoral researcher at Vilnius University, Lithuania, who presented the study, said that AI could be useful when used in conjunction with clinical staff, but should not be used as a stand-alone triage tool. "We conducted this study to address the growing issue of overcrowding in the emergency department and the escalating workload of nurses," said Dr. Jukneviciene. "Given the rapid development of AI tools like ChatGPT, we aimed to explore whether AI could support triage decision-making, improve efficiency and reduce the burden on staff in emergency settings." The researchers distributed a paper and digital questionnaire to six emergency medicine doctors and 51 nurses working in the emergency department of Vilnius University Hospital Santaros Klinikos. They asked them to triage clinical cases selected randomly from 110 reports cited in the PubMed database on the internet. The clinical staff were required to classify the patients according to urgency, placing them in one of five categories from most to least urgent, using the Manchester Triage System. The same cases were analyzed by ChatGPT (version 3.5). A total of 44 nurses (86.3%) and six doctors (100%) completed the questionnaire. "Overall, AI underperformed compared to both nurses and doctors across most of the metrics we measured," said Dr. Jukneviciene. "For example, AI's overall accuracy was 50.4%, compared to 65.5% for nurses and 70.6% for doctors. Sensitivity -- how well it identified true urgent cases -- for AI was also lower at 58.3% compared to nurses, who scored 73.8%, and doctors, who scored 83.0%." Doctors had the highest scores in all the areas and categories of urgency that the researchers analyzed. "However, AI did outperform nurses in the first triage category, which are the most urgent cases; it showed better accuracy and specificity, meaning that it identified the truly life-threatening cases. For accuracy, AI scored 27.3% compared to 9.3% for nurses, and for specificity, AI scored 27.8% versus 8.3%." "These results suggest that while AI generally tends to over-triage, it may be somewhat more cautious in flagging critical cases, which can be both a strength and a drawback," said Dr. Jukneviciene. Doctors also performed better than AI when considering cases that required or involved surgery, and in cases that required treatment with medication or other non-invasive therapies. For surgical cases, doctors scored 68.4%, nurses scored 63% and AI scored 39.5% for reliability. For therapeutic cases, doctors scored 65.9%, nurses scored 44.5% and AI did better than nurses, scoring 51.9% for reliability. "While we anticipated that AI might not outperform experienced clinicians and nurses, we were surprised that in some areas AI performed quite well. In fact, in the most urgent triage category, it demonstrated higher accuracy than nurses. This indicates that AI should not replace clinical judgment, but could serve as a decision-support tool in specific clinical contexts and in overwhelmed emergency departments. "AI may assist in prioritizing the most urgent cases more consistently and in supporting new or less experienced staff. However, excessive triaging could lead to inefficiencies, so careful integration and human oversight are crucial. Hospitals should approach AI implementation with caution and focus on training staff to critically interpret AI suggestions," concluded Dr. Jukneviciene. The researchers are planning follow-up studies using newer versions of AI and AI models that are fine-tuned for medical purposes. They want to test them in larger groups of participants, include ECG interpretation, and explore how AI can be integrated into nurse training, specifically for triage and incidents involving mass casualties. Limitations of the study include its small numbers, that it took place in a single center, and that the AI analysis took place outside a real-time hospital setting, so it was not possible to assess how it could be used in the daily workflow; nor was it possible to interact with patients, assess vital signs and have follow-up data. In addition, ChatGPT 3.5 was not trained specifically for medical use. Strengths of the study were that it used real clinical cases for comparison by a multidisciplinary group of doctors and nurses, as well as AI; its accessibility and flexibility was increased by distributing the questionnaire digitally and on paper; it was clinically relevant to current health care challenges such as overcrowding and staff shortages in the emergency department; and the study identified that AI over-triages many patients, assigning higher urgency to them, which is crucial knowledge for the safe implementation of AI in emergency departments. Dr. Barbra Backus is chair of the EUSEM abstract selection committee. She is an emergency physician in Amsterdam, The Netherlands, and was not involved in the study. She said, "AI has the potential to be a useful tool for many aspects of medical care and it is already proving its worth in areas such as interpreting X-rays. However, it has its limitations, and this study shows very clearly that it cannot replace trained medical staff for triaging patients coming in to emergency departments. "This does not mean it should not be used, as it could aid in speeding up decision-making. However, it needs to be applied with caution and with oversight from doctors and nurses. I expect AI will improve in the future, but should be tested at every stage of development." On 29 September, a colleague of Dr. Jukneviciene's assistant professor, Rakesh Jalali, from the University of Warmia and Mazury (Olsztyn, Poland), gave a presentation at the congress on the use of virtual reality to train clinical staff in how to treat patients who have been subject to multiple traumatic injuries.

Doctors still outperform AI in medical emergencies, study finds

A small study indicates AI is not yet ready to help make decisions in the emergency room. Artificial intelligence (AI) tools are worse than doctors and nurses at prioritising emergency room patients, a small new study has found. The findings indicate that while AI holds a great deal of promise in the medical realm, health workers should not outsource decisions about the care of emergency patients whose lives may be at risk, the researchers said. "Given the rapid development of AI tools like ChatGPT, we aimed to explore whether AI could support triage decision-making, improve efficiency, and reduce the burden on staff in emergency settings," Dr Renata Jukneviciene, one of the study's authors and a researcher at Vilnius University in Lithuania, said in a statement. The research, which has not yet been reviewed by independent experts or published in a medical journal, was presented at the European Emergency Medicine Congress on Tuesday. Jukneviciene's team asked six emergency doctors and 44 nurses to review patient cases - randomly selected from an online medical database - and triage them, or classify them in order of urgency on a 1-5 scale. The researchers then asked ChatGPT, the commonly used chatbot from OpenAI, to analyse the same cases. ChatGPT's overall accuracy rate was 50.4 per cent, compared with 65.5 per cent for nurses and 70.6 per cent for doctors. There was an even bigger gap in sensitivity, or the ability to identify truly urgent cases, with ChatGPT reaching 58.3 per cent compared to 73.8 per cent among nurses and 83 per cent among doctors, the study found. However, the AI model did outperform nurses when it came to identifying the most urgent or life-threatening cases, with both better accuracy and specificity. The findings indicate "AI may assist in prioritising the most urgent cases more consistently and in supporting new or less experienced staff," Jukneviciene said. However, ChatGPT was far more likely than either doctors or nurses to classify cases as highly urgent, meaning "human oversight" would be important to prevent "inefficiencies," Jukneviciene said. "Hospitals should approach AI implementation with caution and focus on training staff to critically interpret AI suggestions," she said. The study has some limitations, notably the small size and the fact that it took place in a single hospital in Lithuania. The ChatGPT model used in the study had not been trained for medical purposes, meaning fine-tuned AI tools may have fared better. Other research suggests that AI could be a boon for the health sector, outperforming human doctors at diagnosing complex medical issues, reading X-rays faster and more accurately, and making it possible to predict future health problems. But scientists have also warned that an overreliance on AI tools could cause health workers' skills to degrade over time. Jukneviciene's team is now planning additional studies using newer AI models, larger patient groups, and a range of scenarios, such as nurse training and interpretation of electrocardiogram (ECG or EKG) scans that identify unusual heart activity. In the meantime, she said "AI should not replace clinical judgement, but could serve as a decision-support tool in specific clinical contexts and in overwhelmed emergency departments".