Development of a Multi-modal Severity Prediction System for Covid-19 using Machine Learning Algorithms



Covid-19 diagnosis, Severity prediction, Machine learning, CNN, Deep learning, Multi-modal


Medical systems all over the world have been devastated by the covid19 pandemic. Even abundant and wealthy countries have struggled a lot. As of August, 2022, number of corona virus cases has been reached to almost 588 million worldwide reported to WHO. With automation at the level of covid19 severity prediction can improve healthcare delivery in parts of the world where access to skilled experts is limited. It can also help in resource management and reducing mortality rate.

Method: In this research, the researchers designed and developed a novel multimodal framework for covid19 severity prediction with a high precision capacity including decisions from medical imaging and clinical factors including patient details, co morbidities and blood results. The researchers explored oversampling methods SMOTE and ROC with SVM, Decision Tree, Random Forest and ANN classifiers for predicting severity using clinical factors. Image enhancement methods gamma correction and AHE explored with ChexNet model for severity prediction through X-ray images. Performance of the predictions has been evaluated using accuracy, precision, sensitivity, and F1-score.

Results: The researchers achieved superior prediction using RF classifier with SMOTE method for text dataset with accuracy of 96%. For X-ray image dataset ChexNet with AHE achieved 87% accuracy. Infection severity inversely proportional to clinical factors LYP, LY,MOP,CA, ALB and ALG where as it is directly proportional to AST, ALT,DD,CRP,LDH,BUN,CR,MCH,GLU,TBIL and WBC.

In the future, performance of the image model may be improved by concatenating multi scale features from different layers of CNN to increase representation power of the CNN model. Again channel attention may be beneficial to improve model performance.


Download data is not yet available.


John Elflein, Cumulative cases of COVID-19 worldwide, Accessed 17 April 2022

Thejeshwar, S.S., Chokkareddy, C. and Eswaran, K., Precise Prediction of COVID-19 in Chest X-Ray Images Using KE Sieve Algorithm.

Ahamad, M., Aktar, S., Uddin, S., Lió, P., Xu, H., Summers, M. A., ...&Moni, M. A. (2020). A machine learning model to identify early stage symptoms of SARS-Cov-2 infected patients. Expert Systems with Applications, 113661.

Soni, D. K. ., M. ‎, N. Kaushik, D. . Dhote, D. . Nigam, and K. G. . Krishna. “Website Redesign With Animation”. International Journal on Recent and Innovation Trends in Computing and Communication, vol. 10, no. 2, Mar. 2022, pp. 01-10, doi:10.17762/ijritcc.v10i2.5499.

Kang, H., Xia, L., Yan, F., Wan, Z., Shi, F., Yuan, H., Jiang, H., Wu, D., Sui, H., Zhang, C. and Shen, D., 2020. Diagnosis of corona virus disease 2019 (covid-19) with structured latent multi-view representation learning. IEEE transactions on medical Imaging.

Narin , A., Kaya, C. and Pamuk, Z., 2020. Automatic detection of coronavirus disease (covid-19) using x-ray images and deep convolutional neural networks. arXiv preprint arXiv:2003.10849.

Mayya, A. and Khozama, S., 2020, December. A Novel Medical Support Deep Learning Fusion Model for the Diagnosis of COVID-19. In 2020 IEEE International Conference on Advent Trends in Multidisciplinary Research and Innovation (ICATMRI) (pp. 1-6). IEEE.

Gupta, D. J. . (2022). A Study on Various Cloud Computing Technologies, Implementation Process, Categories and Application Use in Organisation. International Journal on Future Revolution in Computer Science &Amp; Communication Engineering, 8(1), 09–12.

Cohen, J.P., Dao, L., Roth, K., Morrison, P., Bengio, Y., Abbasi, A.F., Shen, B., Mahsa, H.K., Ghassemi, M., Li, H. and Duong, T., 2020. Predicting covid-19 pneumonia severity on chest x-ray with deep learning. Cureus, 12(7).

Ohata, E.F., Bezerra, G.M., das Chagas, J.V.S., Neto, A.V.L., Albuquerque, A.B., de Albuquerque, V.H.C. and ReboucasFilho, P.P., 2020. Automatic detection of COVID-19 infection using chest X-ray images through transfer learning. IEEE/CAA Journal of AutomaticaSinica, 8(1), pp.239-248.

Tabik, S., Gómez-Ríos, A., Martín-Rodríguez, J.L., Sevillano-García, I., Rey-Area, M., Charte, D., Guirado, E., Suárez, J.L., Luengo, J., Valero-González, M.A. and García-Villanova, P., 2020. COVIDGR dataset and COVID-SDNet methodology for predicting COVID-19 based on Chest X-Ray images. IEEE Journal of Biomedical and Health Informatics, 24(12), pp.3595-3605.

Ozturk, T., Talo, M., Yildirim, E.A., Baloglu, U.B., Yildirim, O. and Acharya, U.R., 2020. Automated detection of COVID-19 cases using deep neural networks with X-ray images. Computers in biology and medicine, 121, p.103792.

Ning, W., Lei, S., Yang, J., Cao, Y., Jiang, P., Yang, Q., Zhang, J., Wang, X., Chen, F., Geng, Z. and Xiong, L., 2020. Open resource of clinical data from patients with pneumonia for the prediction of COVID-19 outcomes via deep learning. Nature biomedical engineering, 4(12), pp.1197-1207.

Patil, V. N., & Ingle, D. R. (2022). A Novel Approach for ABO Blood Group Prediction using Fingerprint through Optimized Convolutional Neural Network. International Journal of Intelligent Systems and Applications in Engineering, 10(1), 60–68.

Rajpurkar, P., Irvin, J., Zhu, K., Yang, B., Mehta, H., Duan, T., Ding, D., Bagul, A., Langlotz, C., Shpanskaya, K. and Lungren, M.P., 2017. Chexnet: Radiologist-level pneumonia detection on chest x-rays with deep learning. arXiv preprint arXiv:1711.05225.

Zimmerman, J.B., Pizer, S.M., Staab, E.V., Perry, J.R., McCartney, W. and Brenton, B.C., 1988. An evaluation of the effectiveness of adaptive histogram equalization for contrast enhancement. IEEE Transactions on Medical Imaging, 7(4), pp.304-312.

Pizer, S.M., Amburn, E.P., Austin, J.D., Cromartie, R., Geselowitz, A., Greer, T., terHaarRomeny, B., Zimmerman, J.B. and Zuiderveld, K., 1987. Adaptive histogram equalization and its variations. Computer vision, graphics, and image processing, 39(3), pp.355-368.

Amiri, S.A. and Hassanpour, H., 2012. A preprocessing approach for image analysis using gamma correction. International Journal of Computer Applications, 38(12), pp.38-46.

Chawla, N.V., Bowyer, K.W., Hall, L.O. and Kegelmeyer, W.P., 2002. SMOTE: synthetic minority over-sampling technique. Journal of artificial intelligence research, 16, pp.321-357.

Sally Fouad Shady. (2021). Approaches to Teaching a Biomaterials Laboratory Course Online. Journal of Online Engineering Education, 12(1), 01–05. Retrieved from

Mohammed, R., Rawashdeh, J. and Abdullah, M., 2020, April. Machine learning with oversampling and undersampling techniques: overview study and experimental results. In 2020 11th international conference on information and communication systems (ICICS) (pp. 243-248). IEEE.

Rahman, S. S. M. M., Rahman, M. H., Sarker, K., Rahman, M. S., Ahsan, N., &Sarker, M. M. (2018). Supervised ensemble machine learning aided performance evaluation of sentiment classification. In Journal of Physics: Conference Series (Vol. 1060, No. 1, p. 012036).

Rajit Nair Premnarayan Arya, Amit Bhagat, Improved Performance of Machine Learning Algorithms via Ensemble Learning Methods of Sentiment Analysis, International Journal on Emerging Technologies, Volume-10, issue-2.

Chauhan, H., Modi, K. and Shrivastava, S., 2021. Development of a classifier with analysis of feature selection methods for COVID-19 diagnosis. World Journal of Engineering.

Severity RALE Score [9]




How to Cite

Chauhan, H. ., & Modi, K. . (2022). Development of a Multi-modal Severity Prediction System for Covid-19 using Machine Learning Algorithms. International Journal of Intelligent Systems and Applications in Engineering, 10(3), 314–321. Retrieved from



Research Article