Characteristics and Admission Preferences of Pediatric Emergency Patients and Their Waiting Time Prediction Using Electronic Medical Record Data: Retrospective Comparative Analysis

Abstract

Background: The growing number of patients visiting pediatric emergency departments could have a detrimental impact on the care provided to children who are triaged as needing urgent attention. Therefore, it has become essential to continuously monitor and analyze the admissions and waiting times of pediatric emergency patients. Despite the significant challenge posed by the shortage of pediatric medical resources in China's health care system, there have been few large-scale studies conducted to analyze visits to the pediatric emergency room.

Objective: This study seeks to examine the characteristics and admission patterns of patients in the pediatric emergency department using electronic medical record (EMR) data. Additionally, it aims to develop and assess machine learning models for predicting waiting times for pediatric emergency department visits.

Methods: This retrospective analysis involved patients who were admitted to the emergency department of Children's Hospital Capital Institute of Pediatrics from January 1, 2021, to December 31, 2021. Clinical data from these admissions were extracted from the electronic medical records, encompassing various variables of interest such as patient demographics, clinical diagnoses, and time stamps of clinical visits. These indicators were collected and compared. Furthermore, we developed and evaluated several computational models for predicting waiting times.

Results: In total, 183,024 eligible admissions from 127,368 pediatric patients were included. During the 12-month study period, pediatric emergency department visits were most frequent among children aged less than 5 years, accounting for 71.26% (130,423/183,024) of the total visits. Additionally, there was a higher proportion of male patients (104,147/183,024, 56.90%) compared with female patients (78,877/183,024, 43.10%). Fever (50,715/183,024, 27.71%), respiratory infection (43,269/183,024, 23.64%), celialgia (9560/183,024, 5.22%), and emesis (6898/183,024, 3.77%) were the leading causes of pediatric emergency room visits. The average daily number of admissions was 501.44, and 18.76% (34,339/183,204) of pediatric emergency department visits resulted in discharge without a prescription or further tests. The median waiting time from registration to seeing a doctor was 27.53 minutes. Prolonged waiting times were observed from April to July, coinciding with an increased number of arrivals, primarily for respiratory diseases. In terms of waiting time prediction, machine learning models, specifically random forest, LightGBM, and XGBoost, outperformed regression methods. On average, these models reduced the root-mean-square error by approximately 17.73% (8.951/50.481) and increased the R² by approximately 29.33% (0.154/0.525). The SHAP method analysis highlighted that the features "wait.green" and "department" had the most significant influence on waiting times.

Conclusions: This study offers a contemporary exploration of pediatric emergency room visits, revealing significant variations in admission rates across different periods and uncovering certain admission patterns. The machine learning models, particularly ensemble methods, delivered more dependable waiting time predictions. Patient volume awaiting consultation or treatment and the triage status emerged as crucial factors contributing to prolonged waiting times. Therefore, strategies such as patient diversion to alleviate congestion in emergency departments and optimizing triage systems to reduce average waiting times remain effective approaches to enhance the quality of pediatric health care services in China.

Keywords: admission preferences; characteristics; electronic medical record; machine learning; pediatric emergency department; waiting time.

Figure 1

Workflow for analyzing the characteristics and waiting time of pediatric emergency department visits. KNN: K-nearest neighbor; LightGBM: light gradient-boosting machine; XGBoost: extreme gradient boosting.

Figure 2

(A) Ridgeline plots between age and common diseases of PED visits. Density plot for each group is represented by different colors. (B) The average daily number of PED visits at different days of the week. (C) The box plot shows the daily median waiting time (minutes) at different days of the week. PED: pediatric emergency department.

Figure 3

(A) Distribution of the temporal trends of the average number of PED visits for 24 hours of the day. The average number of arrivals in different hours of the day is represented by dotted lines with different colors. (B) The daily number of PED visits (green line) and the median waiting time (purple line) from January 1, 2021, to December 31, 2021. PED: pediatric emergency department.

Figure 4

Temporal trends of the age distribution in pediatric emergency department visits from January 1, 2021, to December 31, 2021. The daily proportion of PED visits in different age groups is represented by different colors. PED: pediatric emergency department.

Figure 5

(A) Box plots for waiting time of PED patients with different diseases. (B). Ridgeline plots between arrival time and common diseases of PED visits. The density plot for each group is represented by different colors. (C) Scatter plot of the monthly top 5 common causes of PED visits and the corresponding number of PED visits. (D) Scatter plot of the top 5 causes with the highest monthly median waiting times, those top causes with monthly occurrences less than 300 were removed. PED: pediatric emergency department.

Figure 6

The distribution of the actual waiting time and the predicted waiting time by different models. (A) Daily median waiting times and their 95th quantile intervals for the actual waiting time and the predicted waiting time by different computational models are presented in the line chart with different colors. (B) Monthly median waiting times and their 95th quantile intervals for the actual waiting time and the predicted waiting time by different computational models are presented in the line chart with different colors. KNN: K-nearest neighbor; LASSO: least absolute shrinkage and selection operator; LightGBM: light gradient-boosting machine; LR: linear regression; RF: random forest; XGBoost: extreme gradient boosting.