Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Forecasting emergency department overcrowding: A deep learning framework.

Fouzi Harrou1, Abdelkader Dairi2, Farid Kadri3

  • 1King Abdullah University of Science and Technology (KAUST) Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division, Thuwal 23955-6900, Saudi Arabia.

Chaos, Solitons, and Fractals
|September 28, 2020
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Steps in Outbreak Investigation01:18

Steps in Outbreak Investigation

394
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
394

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Label-free anomaly detection in wastewater treatment plants via enhanced independent component analysis.

Scientific reports·2026
Same author

Exploring Antiviral Drugs on Monolayer Black Phosphorene: Atomistic Theory and Explainable Machine Learning-Assisted Platform.

International journal of molecular sciences·2024
Same author

Stacked deep learning approach for efficient SARS-CoV-2 detection in blood samples.

Artificial intelligence in medicine·2024
Same author

Semi-Supervised KPCA-Based Monitoring Techniques for Detecting COVID-19 Infection through Blood Tests.

Diagnostics (Basel, Switzerland)·2023
Same author

Synergy of Small Antiviral Molecules on a Black-Phosphorus Nanocarrier: Machine Learning and Quantum Chemical Simulation Insights.

Molecules (Basel, Switzerland)·2023
Same author

EEG-Based Mental Tasks Recognition via a Deep Learning-Driven Anomaly Detector.

Diagnostics (Basel, Switzerland)·2022
Same journal

Studying Synchronization of Neural Oscillators through NMDA-AMPA Receptor interactions.

Chaos, solitons, and fractals·2026
Same journal

Prediction of excitable wave dynamics using machine learning.

Chaos, solitons, and fractals·2025
Same journal

A network-based model to assess vaccination strategies for the COVID-19 pandemic by using Bayesian optimization.

Chaos, solitons, and fractals·2025
Same journal

COVID-19 dynamics and immune response: Linking within-host and between-host dynamics.

Chaos, solitons, and fractals·2024
Same journal

Ion gradient-driven bifurcations of a multi-scale neuronal model.

Chaos, solitons, and fractals·2023
Same journal

Growth Feedback Confers Cooperativity in Resource-Competing Synthetic Gene Circuits.

Chaos, solitons, and fractals·2023
See all related articles

Accurate emergency department (ED) visit forecasting is crucial for managing patient flow and preventing overcrowding. A novel deep learning approach using Variational AutoEncoder (VAE) demonstrated superior performance in predicting daily and hourly ED visits compared to other models.

Area of Science:

  • Healthcare Management
  • Artificial Intelligence
  • Time Series Analysis

Background:

  • Increasing demand for medical care strains hospital resources, particularly in emergency departments (EDs).
  • ED overcrowding degrades the quality of medical services and necessitates efficient patient flow management.
  • Accurate forecasting of ED visits is critical for resource optimization and mitigating overcrowding.

Purpose of the Study:

  • To propose an effective deep learning method for forecasting daily and hourly emergency department visits.
  • To investigate the application of Variational AutoEncoder (VAE) for patient arrival time-series data forecasting.
  • To evaluate the VAE model's performance against established forecasting methods.

Main Methods:

  • Utilized the Variational AutoEncoder (VAE), a deep learning model known for feature extraction and nonlinear approximation.
Keywords:
Deep learningED demandsEmergency departmentsForecastingPatient flows

Related Experiment Videos

  • Conducted both one-step-ahead and multi-step-ahead forecasting of ED patient arrivals.
  • Employed time-series data from a pediatric emergency department at Lille regional hospital center, France.

    • Main Results:

    • The VAE model demonstrated promising performance in forecasting ED visits.
    • VAE outperformed seven other methods, including RNN, LSTM, BiLSTM, ConvLSTM, RBM, GRUs, and CNN.
    • The study highlights the effectiveness of deep learning models, particularly VAE, for ED visit forecasting.

    Conclusions:

    • The Variational AutoEncoder (VAE) presents a powerful tool for enhancing the accuracy of emergency department visit forecasts.
    • Accurate forecasting using VAE can significantly aid in managing patient flow and optimizing resource allocation in EDs.
    • This research establishes VAE as a leading method for predicting patient arrivals, outperforming conventional deep learning techniques.