JMIR Form Res. 2026 Apr 16. doi: 10.2196/89306. Online ahead of print.
ABSTRACT
BACKGROUND: There are a large number of pediatric emergency patients. Due to the fact that the children cannot describe their own conditions, there is a shortage of nursing staff, it is extremely important to identify the early warning signs of the children’s conditions as early as possible. The current targeted care needs to be improved.
OBJECTIVE: This study aimed to investigate the application of an artificial intelligence-based pediatric early warning score (PEWS) in the pediatric emergency observation unit, analyze the relationship between PEWS and disease severity , and assess its impact on length of hospital stay and hospitalization costs after admission, so as to provide references for targeted nursing care.
METHODS: We performed a retrospective study. A total of 1,233 pediatric patients admitted via the pediatric emergency department of a tertiary specialty hospital in Guangzhou from September 2023 to March 2024 were included. The patients were divided according to the status of the activation of the early-warning group (PEWS score ≥ 1) vs. not triggered [score 0]) during emergency observation. Length of stay and hospitalization costs were compared between the early warning group and the non-early warning group.The differences between groups were performed with the Mann-Whitney U test. We did the multivariable logistic regression to discuss the association of resource utilization metrics and the status of AI-PEWS, adjusted by age, sex and disease category (respiratory, neurological, hematologic).
RESULTS: In 1,233 patients, 597 (48.4%) triggered the AI-PEWS (mean score 2.44 ± 1.41), and 636 (51.6%) did not. In the early warning group, 68 children were transferred to the intensive care unit, with a mean PEWS of 3.32 ± 1.73. Compared with the non-early warning group, the early warning group had a longer hospital stay (z = -5.180, P < 0.001) and higher hospitalization costs (z = -6.500, P < 0.001), and the differences between groups were statistically significant (P < 0.001). Among the top three admission categories-respiratory, neurological, and hematologic diseases-children in the PEWS early warning group had significantly longer hospital stays and higher hospitalization costs, with statistically significant differences between groups (P < 0.01). The β coefficient for length of hospital stay was 0.053 (SE=0.010), Waldχ²=5.533, OR=1.055 (95% CI: 1.035-1.075); while the β coefficient for hospitalization costs was 0.001 (SE=0.000), Waldχ²=6.075, OR=1.001 (95% CI: 1.001-1.001).
CONCLUSIONS: Compared with the non-early-warning group, the early-warning group had significantly longer hospital stays and higher hospitalization costs; similar patterns were observed within respiratory, neurological, and hematologic disease categories. It shows differences between children who triggered the warning and children who did not, providing a reference for identifying critically ill children and for targeted care.
PMID:41995245 | DOI:10.2196/89306