JMIR Publications

ABSTRACT

Background:

Overcrowding in the emergency department (ED) is a growing challenge, associated with increased medical errors, longer patient stays, higher morbidity, and mortality rates. AI decision support tools have shown potential to address this problem by assisting with faster decision making regarding patient admissions, yet many studies neglect to focus on the clinical relevance and practical applications of these AI solutions.

Objective:

This study aimed to evaluate the clinical relevance of an AI model in predicting patient admission from the ED to hospital wards and its potential impact on reducing the time needed to make an admission decision.

Methods:

A retrospective study was conducted using anonymised patient data from St. Antonius Hospital, The Netherlands, covering January 2018 to September 2023. An XGBoost AI model was developed and tested on this data to predict admission decisions. The model was evaluated using data segmented into 10-minute intervals, which reflects the real-world applicability. The primary outcome measured was the reduction in time per admission decision compared to healthcare professionals. Secondary outcomes analysed the performance of the model of various subgroups, including the age of the patient, the medical specialty, the classification category, and the time of day.

Results:

The AI model demonstrated a precision of 0.78 and a recall of 0.73, with a median saved 111 minutes for true positive predicted patients. Subgroup analysis revealed that elderly patients and certain specialities, such as pulmonology, benefited the most from the AI model, with time savings of up to 90 minutes per patient.

Conclusions:

The AI model shows significant potential to reduce the time to admission decisions, alleviate ED overcrowding, and improve patient care. The model offers the advantage of always providing weighted advice on admission, even when the ED is under pressure. Future prospective studies are needed to assess the impact in the real world and further enhance the performance of the model in diverse hospital settings.