Application of an AI-Based Pediatric Early Warning Score in the Pediatric Emergency Department: Cross-Sectional Study

Background: Pediatric emergency departments see a high volume of patients. Given that children often cannot describe their condition and there is a shortage of nursing staff, it is essential to identify the early warning signs of adverse conditions among children as quickly as possible. Current targeted care needs to be improved. Objective: This study aimed to investigate the application of an artificial intelligence (AI)–based version of the Pediatric Early Warning Score (PEWS) in a pediatric emergency observation unit, analyze the relationship between PEWS and disease severity, and assess its impact on the length of hospital stay and hospitalization costs after admission, thereby providing a reference for targeted nursing care. Methods: We performed a retrospective study. A total of 1233 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 whether they triggered a PEWS early warning into an early warning group (PEWS ≥1) and a non–early warning group (PEWS=0) during emergency observation. Length of stay and hospitalization costs were compared between the early warning group and the non–early warning group. Differences between groups were assessed using the Mann-Whitney test. We performed multivariable logistic regression to discuss the association of resource use metrics and PEWS status, adjusted by age, sex, and disease category (respiratory, neurological, and hematologic). Results: Of 1233 patients, 597 (48.4%) triggered the PEWS early warning (mean score 2.44, SD 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 (SD 1.73). Compared with the non–early warning group, the early warning group had a longer hospital stay (=−5.180; <.001) and higher hospitalization costs (=−6.500; <.001), and the differences between groups were statistically significant (<.001). Among the top 3 admission categories—respiratory, neurological, and hematologic diseases—children in the early warning group had significantly longer hospital stays and higher hospitalization costs (all <.01). The β coefficient for length of hospital stay was 0.053 (SE 0.010; Wald ²=5.533; odds ratio 1.055, 95% CI 1.035‐1.075), while the β coefficient for hospitalization costs was 0.001 (SE 0.000; Wald ²=6.075; odds ratio 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 (<.001); similar patterns were observed within respiratory, neurological, and hematologic disease categories (all <.01). These findings show differences between children who triggered the warning and children who did not, providing a reference for identifying critically ill children for targeted care.

STAT+: Why the WakeMed – Atrium Health hospital merger matters

This is the online version of STAT’s weekly email newsletter Health Care Inc. Sign up here.

Thanks for being here! So much to read, including a new series from my colleagues Lev Facher and Isa Cueto. They delved into the perils of alcohol despite its ubiquity in American culture. The opening piece has several passages and quotes that will make you stop and think in a gratifying, educational way. Give it a read, and as always, pour your thoughts and tips my way: bob.herman@statnews.com.

Wide a-Wake(Med)

Most of you reading this do not live in North Carolina. But a hospital system merger in that state that has created local rage has national relevance.

Continue to STAT+ to read the full story…

Heatwave-related variations in psychiatric consultations and admissions: a time-series analysis

BackgroundHeatwaves are becoming increasingly frequent and intense across Europe, posing significant risks to physical and mental health. Emerging evidence suggests that prolonged exposure to high temperatures may exacerbate psychiatric symptoms and increase the demand for acute mental health services.ObjectivesThis study examined the relationship between extreme heat events and psychiatric service utilization in Bolzano, Italy, by analyzing emergency psychiatric consultations and acute psychiatric admissions across three non-consecutive years.MethodsA retrospective observational analysis was conducted using daily psychiatric consultations in the Emergency Department (ED) and daily admissions to acute psychiatric wards from 2013, 2018, and 2023. Meteorological data were obtained from the provincial environmental agency. Time-series analyses employed ARIMA models, incorporating daily minimum and maximum temperatures, tropical nights, and a cumulative heatwave index (n_hot_htwv). Model selection was based on BIC, and the effect of exogenous temperature variables was evaluated through changes in AIC. Residual diagnostics guided the inclusion of weekly seasonal dummy variables.ResultsNon-seasonal ARIMA models with day-of-week dummies provided the best fit for both consultations and admissions. Adding the cumulative heatwave variable (n_hot_htwv) consistently improved model fit across all years, whereas minimum and maximum temperatures alone did not. Heatwave duration emerged as a more sensitive predictor of psychiatric service utilization than isolated temperature peaks. No evidence of yearly seasonality was found, and residual diagnostics supported the robustness of models including weekly dummy variables.ConclusionHeatwaves are associated with increased psychiatric consultations and hospital admissions in Bolzano, with cumulative heat exposure representing a critical determinant. These effects cannot be explained solely by seasonal patterns, suggesting an independent climatic influence. Given the projected rise in heatwave intensity and duration, mental health services should incorporate climate-responsive planning and early-warning strategies.

The trajectories of Demoralization Syndrome and its related factors among elderly patients with end-stage kidney disease: a longitudinal study

ObjectiveElderly ESKD patients frequently experience a range of psychosocial difficulties, with Demoralization Syndrome (DS) being especially prevalent. This study sought to delineate distinct longitudinal trajectories of DS and to examine factors associated with trajectory membership.MethodsA prospective longitudinal cohort of 363 elderly ESKD patients was recruited from Department of Nephrology in grade a hospital in Anhui, China from January 2023 to December 2025. DS was measured 4 time points from the first hemodialysis session after diagnosis to the 18 month follow-up. LCGM was applied to identify latent DS trajectory classes. Differences among classes were explored with the Two-way ANOVA, Wilcoxon rank-sum test, and multinomial logistic regression was used to assess associations between baseline characteristics and trajectory membership.ResultsThree DS trajectories were identified: Severe Class (54.0%), Moderate Class (41.6%), and Mild Class (4.4%).Membership in the more adverse trajectories was significantly associated with higher use of negative coping styles, lower perceived social support, lower Barthel Index scores, and more negative perceptions of aging (all P < 0.05).ConclusionsConsiderable heterogeneity in DS trajectories exists among elderly ESKD patients, with the majority following a severe pattern. These findings suggest that clinicians should monitor physical and cognitive functioning, regularly assess DS levels, and consider interventions targeting social support and coping strategies to mitigate worsening demoralization over time.

Assessing the Effects of Cool Roofs on Indoor Environments and Health in Tavua, Fiji

Conditions: Resting Heart Rate; Blood Glucose Control; Depression; Heat-related Symptoms; Physician Diagnosed Heat-related Illnesses; Food Insecurity; Diet Quality; Health-Related Quality-of-Life; Indoor Thermal Comfort; Coping Ability; Life Satisfaction; Healthcare Provider Utilization; Hospitalization; Systolic Blood Pressure; Diastolic Blood Pressure; Inner Ear Canal Temperature; Dehydration; Sleep Quality; Cognition; Productivity; Aggression; Indoor Air Temperature; Indoor Relative Humidity; Indoor Heat Index; Household Energy Expenditure

Interventions: Other: Cool roof

Sponsors: Aditi Bunker; Heidelberg University; Rutgers University; Boston University; Resene; Fiji National University

Not yet recruiting