Developing Generalized Models for COVID-19 Detection and Outbreak Prediction by AI Approach
Partha Pratim Debnath, Erona Moumita, Mursheda Nusrat Della, Md. Lincon Hasan
Abstract
The target of the research is to evaluate the performance of convolutional neural network architectures for medical image classification and artificial neural network for future prediction. Our focus is to create a generalized model from our own dataset by collecting it from different sources. We have also represented an artificial neural network (ANN) model which can estimate and forecast expansion of COVID-19 in a region based on several parameters. The outbreak prediction model worked with the accuracy of 98%. For CNN, system demonstrates an accuracy of 99.4%. Although, our system still has the scope to further improvement when more COVID-19 images become available. Our proposed model can be used for fast and reliable identification of COVID-19 from patient’s chest X-rays. Primary health workers in remote places where the proper diagnostic laboratory and expert doctor are not available, can use our automatic COVID-19 detection system. In addition to that, our ANN model can predict the future outbreak of COVID-19 for a country which can help any country to take precaution according to it.
Conclusion
The necessity for automatic diagnostic process is at the peak now as there are no effective manual toolkits found economical. Our focus is to detect COVID-19 automatically using AI. In our research paper, a model using simple CNN (Convolutional Neural Network) for the detection of COVID-19 infected person from their chest X-ray is illustrated. We were able to gain a training accuracy of 99.4% and testing accuracy of 95%.
We also tried to invent a model that can foretell future outbreak of COVID-19 for a country. Our model is based on Artificial Neural Network. Future risk analysis model achieved testing accuracy 98% and testing accuracy 97% -which is optimum. Since our model has been trained and tested on the data obtained from online sources, still it needs to be checked with manually driven real data.
References
[1]
Salama, A., Darwsih, A., & Hassanien, A. E. (2021). Artificial intelligence approach to predict the covid-19 patient’s recovery. Digital Transformation and Emerging Technologies for Fighting COVID-19 Pandemic: Innovative Approaches, 121-133.
[2]
Visit coronavirus.gov for the latest Coronavirus Disease (COVID-19) updates. [Online]. Available: https://www.healthypeople.gov/2020/leading-health-indicators/2020-lhi-topics/Access-to-Health-Services
[3]
Nuttall, <em>N. (2001). Clinical decision-making–can a computer aided learning package help?. British Dental Journal</em>, 190(10), 545-545.
[4]
“Numerous Unknowns and Uncertainties About Monkeypox, WHO Acknowledges”, [Online]. Available: https://healthpolicy-watch.news/numerous-unknowns-and-uncertainties-about-monkeypox/
[5]
Quiroz-Juárez, M. A., Torres-Gómez, A., Hoyo-Ulloa, I., León-Montiel, R. D. J., & U’Ren, A. B. (2021). Identification of high-risk COVID-19 patients using machine learning. Plos one, 16(9), e0257234.
[6]
Shinde, G. R., Kalamkar, A. B., Mahalle, P. N., Dey, N., Chaki, J., & Hassanien, <em>A. E. (2020). Forecasting models for coronavirus disease (COVID-19): a survey of the state-of-the-art. SN computer science</em>, 1, 1-15.
[7]
Organización para la Cooperación y el Desarrollo Económico. (2020). The territorial impact of COVID-19: Managing the crisis across levels of government. OECD Policy Responses to Coronavirus (COVID-19).
[8]
Tupetz, A. (2019). Scarf Injuries in Bangladesh: Exploring the Impact on Females who live with Spinal Cord Injuries.
[9]
Lundervold, A. S., & Lundervold, A. (2019). An overview of deep learning in medical imaging focusing on MRI. Zeitschrift für Medizinische Physik, 29(2), 102-127.
[10]
Quiroz-Juárez, M. A., Torres-Gómez, A., Hoyo-Ulloa, I., León-Montiel, R. D. J., & U’Ren, A. B. (2021). Identification of high-risk COVID-19 patients using machine learning. Plos one, 16(9), e0257234.
[11]
Budd, J., Miller, B. S., Manning, E. M., Lampos, V., Zhuang, M., Edelstein, M., ... & McKendry, R. A. (2020). Digital technologies in the public-health response to COVID-19. Nature medicine, 26(8), 1183-1192.
[12]
Vaishya, R., Javaid, M., Khan, I. H., & Haleem, <em>A. (2020). Artificial Intelligence (AI) applications for COVID-19 pandemic. Diabetes & Metabolic Syndrome: Clinical Research & Reviews</em>, 14(4), 337-339.
[13]
Kassania, S. H., Kassanib, P. H., Wesolowskic, M. J., Schneidera, K. A., & Detersa, <em>R. (2021). Automatic detection of coronavirus disease (COVID-19) in X-ray and CT images: a machine learning based approach. Biocybernetics and Biomedical Engineering</em>, 41(3), 867-879.
[14]
Patel, P. (2023). Information for persons who are immunocompromised regarding prevention and treatment of SARS-CoV-2 infection in the context of currently circulating omicron sublineages—United States, January 2023. MMWR. Morbidity and Mortality Weekly Report, 72.
[15]
Vandenberg, O., Martiny, D., Rochas, O., van Belkum, A., & Kozlakidis, <em>Z. (2021). Considerations for diagnostic COVID-19 tests. Nature Reviews Microbiology</em>, 19(3), 171-183.
[16]
"The species Severe acute respiratory syndrome-related coronavirus: classifying 2019-nCoV and naming it SARS-CoV-2." Nature microbiology 5, no. 4 (2020): 536-544.
[17]
Loeffelholz, M. J., & Tang, Y. W. (2020). Laboratory diagnosis of emerging human coronavirus infections–the state of the art. Emerging microbes & infections, 9(1), 747-756.
[18]
Islam, M. Z., Islam, M. M., & Asraf, A. (2020). A combined deep CNN-LSTM network for the detection of novel coronavirus (COVID-19) using X-ray images. Informatics in medicine unlocked, 20, 100412.
[19]
MacKay, M. J., Hooker, A. C., Afshinnekoo, E., Salit, M., Kelly, J., Feldstein, J. V., ... & Mason, C. E. (2020). The COVID-19 XPRIZE and the need for scalable, fast, <em>and widespread testing. Nature biotechnology</em>, 38(9), 1021-1024. [20] Hira, S., Bai, A., & Hira, S. (2021). An automatic approach based on CNN architecture to detect Covid-19 disease from chest X-ray images. Applied Intelligence, 51, 2864-2889.