ºÚÁϳԹÏÍø

Home⇛International Journal of Multidisciplinary Educational Research and Innovation⇛vol. 2 no. 3 (2024)

Early Diagnosis Prediction from COVID-19 Symptoms Using Machine Learning Methods

Charlyn V. Rosales

Discipline: Education

 

Abstract:

This study proposes a new method for detecting COVID-19 using Artificial Neural Networks by analyzing a person’s current symptoms without requiring laboratory tests. The methodology utilized in this study includes the data collection of the dataset from Kaggle, then the Exploratory Data Analysis was performed for data pre-processing to attain a clean and comprehensive dataset to be used to train the prediction model. To determine the highest possible performance of the algorithm, GridSearchCV was used for hyperparameter tuning and 10-fold cross validation to optimize Artificial Neural Networks performance then a prediction model was developed using the optimal configuration. The results suggest that hidden layer sizes of (100,), (50, 100, 50), and (50, 50, 50), relu and tanh activation functions, adam solver, 0.05 and 0.0001 alpha values, and adaptive and constant learning rates were the values that achieved the best algorithm performance. Experimental results show that the developed prediction model attained 98.86% accuracy, 98.79% specificity, and 100% sensitivity. This prediction model can be utilized in applications that integrate prediction models to determine the presence of the COVID-19.



References:

  1. Azeli, Y., Fernández, A., Capriles, F., Rojewski, W., Lopez-Madrid, V., Sabaté-Lissner, D., Serrano, R. M., Rey-Reñones, C., Civit, M., Casellas, J., El Ouahabi-El Ouahabi, A., Foglia-Fernández, M., Sarrá, S., & Llobet, E. (2022). A machine learning COVID-19 mass screening based on symptoms and a simple olfactory test. Scientific Reports, 12.
  2. Bre, F., Gimenez, J. M., & Fachinotti, V. D. (2017). Prediction of wind pressure coefficients on building surfaces using artificial neural networks. Energy and Buildings, 158, 1429-1441.
  3. Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: Synthetic minority over-sampling technique. Journal of Artificial Intelligence Research, 16, 321–357.
  4. Great Learning. (2023). Hyperparameter tuning with GridSearchCV. Retrieved from
  5. Itano, F., de Abreu de Sousa, M. A., & Del-Moral-Hernandez, E. (2018). Extending MLP ANN hyper-parameters optimizations by using genetic algorithm. In International Joint Conference on Neural Networks (pp. 1-8). Brazil. [Note: Conference proceedings with no DOI]
  6. Narkhede, S. (2018). Understanding confusion matrix. Towards Data Science. Retrieved from
  7. Pandas Development Team. (2024). Pandas DataFrame corr. Retrieved from
  8. Solayman, S., Aumi, S. A., Mery, C. S., Mubassir, M., & Khan, R. (2023). Automatic COVID-19 prediction using explainable machine learning techniques. International Journal of Cognitive Computing in Engineering, 4, 36-46.
  9. Ul Haq, A., Li, J. P., Memon, M. H., Khan, J., Malik, A., Ahmad, T., Ali, A., Nazir, S., Ahad, I., & Shahid, M. (2019). Feature selection based on L1-norm support vector machine and effective recognition system for Parkinson’s disease using voice recordings. IEEE Access, 7, 37718-37734.
  10. Villavicencio, C. N., Macrohon, J. J. E., Inbaraj, X. A., Jeng, J.-H., & Hsieh, J.-G. (2021). COVID-19 prediction applying supervised machine learning algorithms with comparative analysis using WEKA. Algorithms, 7(14),
  11. Villavicencio, C. N., Macrohon, J. J. E., Inbaraj, X. A., Jeng, J.-H., & Hsieh, J.-G. (2022). Development of a machine learning based web application for early diagnosis of COVID-19 based on symptoms. Diagnostics, 12(4), 821.
  12. World Health Organization. (2024). Coronavirus. Retrieved from
  13. Worldometers Info. (2024). COVID live update. Retrieved from
  14. Zoabi, Y., Deri-Rozov, S., & Shomron, N. (2021). Machine learning-based prediction of COVID-19 diagnosis based on symptoms. npj Digital Medicine, 4(3).  

Tools


Copyright © 2025   ºÚÁϳԹÏÍø