Prediction of hospitalization using artificial intelligence for urgent patients in the emergency department

Abstract

Timely assessment to accurately prioritize patients is crucial for emergency department (ED) management. Urgent (i.e., level-3, on a 5-level emergency severity index system) patients have become a challenge since under-triage and over-triage often occur. This study was aimed to develop a computational model by artificial intelligence (AI) methodologies to accurately predict urgent patient outcomes using data that are readily available in most ED triage systems. We retrospectively collected data from the ED of a tertiary teaching hospital between January 1, 2015 and December 31, 2019. Eleven variables were used for data analysis and prediction model building, including 1 response, 2 demographic, and 8 clinical variables. A model to predict hospital admission was developed using neural networks and machine learning methodologies. A total of 282,971 samples of urgent (level-3) visits were included in the analysis. Our model achieved a validation area under the curve (AUC) of 0.8004 (95% CI 0.7963–0.8045). The optimal cutoff value identified by Youden's index for determining hospital admission was 0.5517. Using this cutoff value, the sensitivity was 0.6721 (95% CI 0.6624–0.6818), and the specificity was 0.7814 (95% CI 0.7777–0.7851), with a positive predictive value of 0.3660 (95% CI 0.3586–0.3733) and a negative predictive value of 0.9270 (95% CI 0.9244–0.9295). Subgroup analysis revealed that this model performed better in the nontraumatic adult subgroup and achieved a validation AUC of 0.8166 (95% CI 0.8199–0.8212). Our AI model accurately assessed the need for hospitalization for urgent patients, which constituted nearly 70% of ED visits. This model demonstrates the potential for streamlining ED operations using a very limited number of variables that are readily available in most ED triage systems. Subgroup analysis is an important topic for future investigation.

The effects of triage applying artificial intelligence on triage in the emergency department: A systematic review of prospective studies

“…According to the South Korea 2021 Emergency Medical Statistical Yearbook, only 7.1% of patients visiting the emergency department had a high severity of KTAS 1 and 2, but 92.9% of patients had KTAS 3-5, it is becoming the main cause of emergency department overcrowding [6]. In particular, in the current triage system, classi cation accuracy is reduced owing to middle-level classi cation ambiguity, such as level 3 [48], and some patients classi ed as nonemergency patients face problems of undertriage and overtriage [49,50]. In addition, previous studies have shown that a triage system using an automated algorithm predicts hospitalization for ESI level 3-5 patients better than nurses do, suggesting the need for AI-based triage to increase the accuracy of classi cation by targeting level 3-5 patients [51].…”

Use of Artificial Intelligence in Triage in Hospital Emergency Departments: A Scoping Review

“…They concluded that early prediction of admission and discharge probabilities during the ED triage process could be utilized to enhance patient flow and contribute to more effective bed management. AI models were found to have the potential to streamline ED operations, mitigate challenges associated with ED crowding, as well as contribute to the efficient management of ED resources [23].…”

“…The combined model demonstrated a sensitivity of 58% in detecting NSICU admission with a false positive rate of 1:100 (99% specificity). Another study conducted using data from a tertiary teaching hospital in Taiwan focused on urgent level-3 patients and found that using an AI model achieved an AUROC of 0.8004 and accurately determined the necessity of hospitalization for patients requiring urgent attention [23].…”

“…2021 [23] This model can increase ED physicians' confidence in their decisions regarding patient disposition and allow for quicker initiation of hospital admission.…”

Application of artificial intelligence to the public health education

“…With advances in AI, personalized predictions and prevention are possible ( 65 , 66 ). Up to now, multiple disease prediction models had been developed and improved to provide targeted and personalized health advice ( 67 – 70 ). Furthermore, AI has also greatly contributed to the development of the psychological counseling industry.…”