ANN Models Predict Monkeypox Outbreaks Accurately

In an article recently published in the journal Heliyon, researchers comprehensively analyzed using artificial neural networks (ANNs) to predict monkeypox (MPXV) outbreaks. Their goal was to improve public health preparedness by accurately forecasting the severity and spread of this viral disease, which has led to major outbreaks in several countries.

ANN Models Predict Monkeypox Outbreaks Accurately
Study: A comprehensive analysis of the artificial neural networks model for predicting monkeypox outbreaks. Image Credit: greenbutterfly/Shutterstock.com

Background

MPXV is a zoonotic viral disease related to smallpox that has gained attention for its potential to spread across species and globally. Studying MPXV is crucial for understanding its outbreak patterns and developing control strategies. Recent outbreaks underscore the need for global surveillance and effective diagnostic and management approaches.

The virus spreads through contact with infected animals or humans, causing symptoms like fever, headaches, swollen lymph nodes, and a rash. Although smallpox vaccines provide some protection, there is no specific treatment for MPXV, emphasizing the importance of accurate prediction and management.

ANNs, inspired by the structure and function of neurons in the human brain, are widely used to predict infectious diseases. They effectively model complex relationships between variables and have been valuable in forecasting disease outbreaks.

About the Research

In this paper, the authors developed and validated ANN models using a time-series dataset of MPXV cases from countries including Brazil, Argentina, France, Chile, Germany, and Mexico. They employed the Levenberg-Marquardt (LM) algorithm to create single and two-hidden-layer ANN models.

Various model architectures with different numbers of neurons in the hidden layers were trained using the K-fold cross-validation method. The performance of the ANN models was then compared with long short-term memory (LSTM) and gated recurrent unit (GRU) models, which are commonly applied for time-series data analysis.

The methodology involved collecting MPXV case data from the "Our World in Data" website. The confirmed cases in the six countries were represented using statistical graphs to provide an overview of the data.

The dataset was divided into 80% for training and 20% for validation, ensuring models were trained and tested on different data segments. K-fold cross-validation was further utilized to evaluate the models' generalization performance and to identify potential issues like underfitting or overfitting.

For model optimization, the ADAM optimizer was used to compare the performance of LSTM, GRU, and ANN models. The ANN architecture included an input layer, one or two hidden layers, and an output layer.

Neurons in the hidden layers processed inputs by applying a sigmoid activation function to the weighted sums. The LM algorithm, which combines Gauss-Newton and steepest descent methods, was specifically employed to optimize the ANN models for better performance.

Research Findings

The outcomes showed that ANN models, especially those with two hidden layers, performed well in predicting MPXV outbreaks. These models demonstrated high accuracy in forecasting the severity and spread of the disease across different countries.

The researchers found that the ANN models outperformed LSTM and GRU models in terms of prediction accuracy and computational efficiency. Specifically, the ANN-LM model achieved an R-value of approximately 99%, compared to around 98% for both LSTM and GRU models. The LM algorithm and the ADAM optimizer enhanced the robustness and reliability of the ANN models.

The statistical analysis revealed distinct patterns in the time series data of MPXV cases, with peak periods varying by country. For example, Argentina experienced a peak from August to December 2022, while Brazil’s peak occurred from July to October 2022. The study emphasized the importance of using advanced neural network techniques to capture these variations and provide accurate predictions.

The authors also observed that model performance varied across countries. While the ANN-LM model performed better in predicting outbreaks in some countries, LSTM and GRU models showed superior results in others. This result underscores the need for tailored approaches depending on regional data characteristics and model suitability.

Applications

This research has significant implications for public health policy and decision-making. Accurate predictions of MPXV outbreaks can support the development of effective surveillance, prevention, and control strategies.

ANN models can help public health authorities and practitioners allocate resources more efficiently and respond more efficiently to emerging infectious diseases.

Additionally, the study's methodology is adaptable to other infectious diseases, potentially contributing to broader global health security efforts. The application of advanced neural network techniques could improve predictive capabilities and readiness for future outbreaks.

Conclusion

In summary, artificial intelligence (AI) models, especially ANNs, proved effective in predicting MPXV outbreaks. Advanced neural network techniques, including the LM algorithm and the ADAM optimizer, achieved high prediction accuracy and computational efficiency.

The researchers emphasized the importance of precise outbreak forecasting for public health preparedness and demonstrated how ANN models can enhance disease surveillance and control. Future work should focus on applying these models to other infectious diseases and refining prediction techniques to improve their accuracy and reliability further.

Journal Reference

Alnaji, L. A comprehensive analysis of the artificial neural networks model for predicting monkeypox outbreaks. Heliyon, 10, e37274, 2024. DOI: 10.1016/j.heliyon.2024.e37274, https://www.sciencedirect.com/science/article/pii/S2405844024133051

Disclaimer: The views expressed here are those of the author expressed in their private capacity and do not necessarily represent the views of AZoM.com Limited T/A AZoNetwork the owner and operator of this website. This disclaimer forms part of the Terms and conditions of use of this website.

Muhammad Osama

Written by

Muhammad Osama

Muhammad Osama is a full-time data analytics consultant and freelance technical writer based in Delhi, India. He specializes in transforming complex technical concepts into accessible content. He has a Bachelor of Technology in Mechanical Engineering with specialization in AI & Robotics from Galgotias University, India, and he has extensive experience in technical content writing, data science and analytics, and artificial intelligence.

Citations

Please use one of the following formats to cite this article in your essay, paper or report:

  • APA

    Osama, Muhammad. (2024, September 11). ANN Models Predict Monkeypox Outbreaks Accurately. AZoRobotics. Retrieved on October 09, 2024 from https://www.azorobotics.com/News.aspx?newsID=15249.

  • MLA

    Osama, Muhammad. "ANN Models Predict Monkeypox Outbreaks Accurately". AZoRobotics. 09 October 2024. <https://www.azorobotics.com/News.aspx?newsID=15249>.

  • Chicago

    Osama, Muhammad. "ANN Models Predict Monkeypox Outbreaks Accurately". AZoRobotics. https://www.azorobotics.com/News.aspx?newsID=15249. (accessed October 09, 2024).

  • Harvard

    Osama, Muhammad. 2024. ANN Models Predict Monkeypox Outbreaks Accurately. AZoRobotics, viewed 09 October 2024, https://www.azorobotics.com/News.aspx?newsID=15249.

Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type
Submit

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.