AI steps in emergency care at Utrecht hospital

By Laio

Utrecht’s St. Antonius Hospital has launched an innovative AI project to streamline patient care in its emergency department. The algorithm predicts whether patients need admission or can be discharged, updating every 5 minutes based on vital signs and test results. This system aims to reduce wait times, improve patient satisfaction, and alleviate staff workload. While AI assists in decision-making, doctors retain the final say on patient care. The project, which began on September 2, 2024, will be tested in monthly on-off cycles to accurately measure its effectiveness in enhancing emergency care efficiency.

How it works

The AI system analyzes multiple data points such as age, blood values, heart rate, and primary complaints. Every 5 minutes, it recalculates the likelihood of whether a patient should be admitted or can be safely discharged. This dynamic update ensures that the medical staff has the most current and relevant information to make informed decisions. The algorithm’s recommendations are presented to the emergency physicians, providing a comprehensive overview of each patient’s condition.

At peak times, ED physicians often juggle multiple patients, making it challenging to provide immediate and thorough care. The AI tool addresses this issue by automating part of the decision-making process. When the algorithm predicts a patient needs to be admitted, preparations for the transfer can begin immediately. This proactive approach reduces the wait time for patients and frees up beds more quickly for incoming emergencies.

Elderly’s living standards improve with AI

To many, it might come as a shock, but people in Europe and North America spend, on average, 90% of their time indoors. In older adults, most of this share is spent at home. As the population ages, how can we improve the quality of life for older people while taking good care of them? Yet again, AI can step in. 

Balancing technology and human expertise

Dr. Marleen Vreeburg, an emergency physician at St. Antonius Hospital, underscores the benefits: ‘AI will help us shorten the length of stay for patients in the ED. As soon as the algorithm suspects a patient needs to be admitted, the emergency coordinator can start arranging a bed, and the receiving department can make all necessary preparations. This allows us to focus more on patient care while the AI handles much of the logistical work.’

While the AI system provides substantial support, it does not replace the critical judgment of medical professionals. ‘The decision to admit a patient remains with the treating physician,’ emphasizes Dr. Vreeburg. The AI serves as an adjunct, offering data-driven insights that can enhance the quality of care while preserving the essential human element in medical decision-making.

To rigorously assess the effectiveness of the algorithm, the hospital is conducting a controlled study. The AI system will be active for one month and inactive the next, allowing for a clear comparison of outcomes. This cyclical testing aims to provide robust data on how AI integration impacts patient throughput, staff workload, and overall care quality.