arXiv subjects

Brittany F. Lindsey

Publications and source records attributed to Brittany F. Lindsey.

3 recordsLinked to original sources

arXiv2025

Deep Learning-Based Forecasting of Boarding Patient Counts to Address ED Overcrowding

This study presents a deep learning-based framework for predicting emergency department (ED) boarding counts six hours in advance using only operational and contextual data, without patient-level information. Data from ED tracking systems, inpatient census, weather, holidays, and local events were aggregated hourly and processed with comprehensive feature engineering. The mean ED boarding count was 28.7 (standard deviation = 11.2). Multiple deep learning models, including ResNetPlus, TSTPlus, and TSiTPlus, were trained and optimized using Optuna, with TSTPlus achieving the best results (mean absolute error = 4.30, mean squared error = 29.47, R2 = 0.79). The framework accurately forecasted boarding counts, including during extreme periods, and demonstrated that broader input features improve predictive accuracy. This approach supports proactive hospital management and offers a practical method for mitigating ED overcrowding.

cs.LG↗

arXiv2025

Assessing the Impact of External and Internal Factors on Emergency Department Overcrowding

Study Objective: To analyze the factors influencing Emergency Department (ED) overcrowding by examining the impacts of operational, environmental, and external variables, including weather conditions and football games. Methods: This study integrates ED tracking and hospital census data from a southeastern U.S. academic medical center (2019-2023) with data from external sources, including weather, football events, and federal holidays. The dependent variable is the hourly waiting count in the ED. Seven regression models were developed to assess the effects of different predictors such as weather conditions, hospital census, federal holidays, and football games across different timestamps. Results: Some weather conditions significantly increased ED crowding in the Baseline Model, while federal holidays and weekends consistently reduced waiting counts. Boarding count positively correlated with ED crowding when they are concurrent, but earlier boarding count (3-6 hours before) showed significant negative associations, reducing subsequent waiting counts. Hospital census exhibited a negative association in the Baseline Model but shifted to a positive effect in other models, reflecting its time-dependent influence on ED operations. Football games 12 hours before significantly increased waiting counts, while games 12 and 24 hours after had no significant effects. Conclusion: This study highlights the importance of incorporating both operational and non-operational factors (e.g., weather) to understand ED patient flow. Identifying robust predictors such as weather, federal holidays, boarding count, and hospital census can inform dynamic resource allocation strategies to mitigate ED overcrowding effectively.

cs.CY↗

arXiv2025

An Artificial Intelligence-Based Framework for Predicting Emergency Department Overcrowding: Development and Evaluation Study

Background: Emergency department (ED) overcrowding remains a major challenge, causing delays in care and increased operational strain. Hospital management often reacts to congestion after it occurs. Machine learning predictive modeling offers a proactive approach by forecasting patient flow metrics, such as waiting count, to improve resource planning and hospital efficiency. Objective: This study develops machine learning models to predict ED waiting room occupancy at two time scales. The hourly model forecasts the waiting count six hours ahead (e.g., a 1 PM prediction for 7 PM), while the daily model estimates the average waiting count for the next 24 hours (e.g., a 5 PM prediction for the following day's average). These tools support staffing decisions and enable earlier interventions to reduce overcrowding. Methods: Data from a partner hospital's ED in the southeastern United States were used, integrating internal metrics and external features. Eleven machine learning algorithms, including traditional and deep learning models, were trained and evaluated. Feature combinations were optimized, and performance was assessed across varying patient volumes and hours. Results: TSiTPlus achieved the best hourly prediction (MAE: 4.19, MSE: 29.32). The mean hourly waiting count was 18.11, with a standard deviation of 9.77. Accuracy varied by hour, with MAEs ranging from 2.45 (11 PM) to 5.45 (8 PM). Extreme case analysis at one, two, and three standard deviations above the mean showed MAEs of 6.16, 10.16, and 15.59, respectively. For daily predictions, XCMPlus performed best (MAE: 2.00, MSE: 6.64), with a daily mean of 18.11 and standard deviation of 4.51. Conclusions: These models accurately forecast ED waiting room occupancy and support proactive resource allocation. Their implementation has the potential to improve patient flow and reduce overcrowding in emergency care settings.

cs.LG↗