The week's pick
Reseach Article
A Hybrid Two-Phase Machine Learning Model for Early COVID-19 Diagnosis Prediction
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 174 - Number 30 |
| Year of Publication: 2021 |
| Authors: Ahmed S. Salama |
10.5120/ijca2021921243
|
Ahmed S. Salama . A Hybrid Two-Phase Machine Learning Model for Early COVID-19 Diagnosis Prediction. International Journal of Computer Applications. 174, 30 ( Apr 2021), 38-49. DOI=10.5120/ijca2021921243
Abstract
Across the history, COVID-19 pandemic is considered one of the deadliest diseases that harvested more than one million souls and left thousands of patients with damaged fibrotic lungs that physicians called post COVID syndrome. The main aim of this study is to propose a hybrid two-phase machine learning model to early diagnose COVID-19 based on available laboratory tests results, clinical symptoms, CT results, and demographic data in case of the difficulty of applying or absence of PCR test. The proposed model employs unsupervised learning Scalable Expectation Maximization (SEM) soft clustering mining model in the first phase to identify the most relevant identifying clusters characteristics for the disease grades, and in phase two the proposed model applies two proposed supervised learning classification mining models which are Association Rules (AR) based on improved Apriori algorithm, and Multilayer Perceptron(MLP) Multiclass Artificial Neural Network (ANN) to predict the COVID-19 disease diagnosis. The implemented proposed ML hybrid COVID-19 prediction model has successfully classified COVID-19 patients into positive mild, positive severe patients and discriminated between COVID-19 and Influenza patients/normal cases (COVID-19 negative) with an overall accuracy of 97.3%, a sensitivity 96%, and specificity 98%. It outperforms other reviewed state-of-the art COVID-19 diagnosis prediction models.
References
- Sohrabi, C., AlsafiZ OfiNeill, N., Khan, M. and Kerwan A. et al. 2020. World health organization declares global emergency: a review of the 2019 novel coronavirus (COVID-19). International Journal of Surgery. vol. 76, 71-76.
- Barbat, MM., Wesche, C., Werhli, AV., and Mata, MM. 2019. An adaptive machine learning approach to improve automatic iceberg detection from SAR images . ISPRS Journal of Photogrammetry and Remote Sensing. vol. 156, 247–259.
- Shang, R., Qi, L., Jiao, L., Stolkin, R., and Li, Y. 2014. Change detection in SAR images by artificial immune multi-objective clustering. Engineering Applications of Artificial Intelligence. vol. 31, 53–67.
- Choi, S., Kang, M-G., Min, H., Chang, Y-S., and Yoon, S. 2017. Large-scale machine learning of media outlets for understanding public reactions to nation-wide viral infection outbreaks. Methods. vol. 129, 50–59.
- Vaka, AR., and Soni, B. 2020. Breast cancer detection by leveraging Machine Learning. ICT Express. vol. 6. no. 4, 320-324.
- Saxena, S., and Gyanchandani, M. 2019. Machine learning methods for computer-aided breast cancer diagnosis using histopathology: a narrative review. Journal of Medical Imaging and Radiation Science. vol. 51. no. 1, 182-193.
- Vaishya, R., Javaid, M., Khan, IH., and Haleem, A. 2020. Artificial Intelligence (AI) applications for COVID-19 pandemic. Diabetes & Metabolic Syndrome: Clinical Research & Reviews. vol.14. no. 4, 337–339.
- T. Ai, Z. Yang, H. Hou, C. Zhan, C. Chen, W. Lv, Q. Tao, Z. Sun, and L. Xia, “Correlation of chest CT and RT-PCR testing in coronavirus disease 2019 (COVID-19) in China: a report of 1014 cases”, Radiology, vol. 296, no. 2, pp. 32-40, 2020.
- Javor, D., Kaplan, A., Puchner, S.B., Krestan, C., and Baltzer, P. 2020. Deep learning analysis provides accurate COVID-19 diagnosis on chest computed tomography. European Journal of Radiology. vol. 133. no. 109402, 2020.
- Goodman-Meza, D., Adamson, PC., and Ebinger, J. et al. 2020. A machine learning algorithm to increase COVID-19 inpatient diagnostic capacity. PLOS ONE Journal. vol. 15. no. 9, e0239474.
- An, C., Lim, H., and Kim, DW. et al. 2020. Machine learning prediction for mortality of patients diagnosed with COVID-19: a nationwide Korean cohort study . Scientific Reports Journal. Vol. 10. no. 18716.
- Khanday, A.M.U.D., Rabani, S.T., and Khan, Q.R., et al. 2020. Machine learning based approaches for detecting COVID-19 using clinical text data. Int. Journal of Information Technology. vol. 12. 731–739.
- Banerjee, A., Ray, S., Vorselaars, B., and Kitson, J. et al. 2020. Use of Machine Learning and Artificial Intelligence to predict SARS-CoV-2 infection from Full Blood Counts in a population. Int. immunopharmacology. vol. 86. no. 106705.
- Bao, FS., He, Y., Liu, J., Chen, Y., Li, Q., and Zhang, CR. et al. 2020. Triaging moderate covid-19 and other viral pneumonias from routine blood tests. arXiv e-prints. arXiv:2005.06546.
- Barbosa, V., Gomes, JC., Santana, MA., and Almeida Albuquerque, JE. et al. Heg. ia: an intelligent system to support diagnosis of covid-19 based on blood tests. medRxiv, 2020.
- Nan, SN., Ya, Y., Ling, TL., and Nv, GH., et al. A prediction model based on machine learning for diagnosing the early covid-19 patients. medRxiv, 2020.
- Bayat, V., Phelps, S., and Ryono, R., et al. A Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) Prediction Model from Standard Laboratory Tests, Clinical Infectious Diseases. ciaa1175. 2020.
- Zoabi, Y., Deri-Rozov, S., and Shomron, N. 2021. Machine learning-based prediction of COVID-19 diagnosis based on symptoms. npj Digital Medical. vol. 4. no. 3.
- Prokop, M., van Everdingen, W., and Van Rees, VT. et al. 2020. CO‐RADS – a categorical CT assessment scheme for patients with suspected COVID‐19: definition and evaluation. Radiology. vol. 296. no. 2, 97-104.
- Bradley P., Fayyad, U., and Reina, C. 1998. Scaling EM (Expectation-Maximization) Clustering to Large Databases. MSR-TR-98-3.1998.
Index Terms
Keywords