Predicting Mortality COVID‑19 Model and Characterize the High Risk of Dying Based on Machine Learning Models

Manal  Ali Atiyah; Chra  Ali Kamal

doi:10.25098/7.1.4

Authors

Manal Ali Atiyah Database Department, Computer Scince Instuite, Sulaimani polytechnic university, Sulaimani, Iraq
Chra Ali Kamal Database Department, Computer Scince Instuite, Sulaimani polytechnic university, Sulaimani, Iraq

DOI:

https://doi.org/10.25098/7.1.4

Keywords:

COVID-19, healthcare, mortality, machine learning, pandemic, predictive model

Abstract

COVID-19 is a respiratory illness that the SARS-CoV-2 virus has caused. It has been declared a pandemic by the (WHO). The surprise increase in infections and the high mortality rates have strained the public healthcare system. Thus, it is fatal to recognize the most remarkable factors for mortality prediction to improve patient treatment strategy. We developed a predictive model using machine learning and AI to identify the health risks and predict the mortality rate of patients with COVID-19. In this study, 4.711 patients with confirmed SARS-CoV-2 infection were included the goal of this study is to develop an AI model that can help medical facilities identify which patients need immediate attention and which ones should be sent to the hospital first. It can also help them, triage patients, during times of overcrowding. various machine learning algorithms used to analyze the mortality rate of patients with COVID-19. These included Random Forests, K-Nearest Neighbors, Neural Networks, Support Vector Machines, and Decision Trees. We applied the feature selection method to identify to improve the machine learning algorithm achievement. the results showed that the Random Forests and Neural Networks approximated the best predictive model with a balanced accuracy of 85%. The model with the best performance supplies a tool to decrease mortality. We split the dataset of COVID-19 patients to analyze our model's accuracy Finally We used a confusion matrix to analyze the model’s accuracy and other evaluation metrics.

References

Worldometers. Covid-19 Coronavirus Pandemic [Online]. Available:

https://www.worldometers.info/coronavirus/?utm_campaign=homeAdvegas1

Accessed:2022, September 26.

R. Zagrouba, M.A. Khan, A.U. Rahman, M.A. Saleem, et al. (2021)." Modelling and simulation of covid-19 outbreak prediction using supervised machine learning " Computers, Materials, & Continua, vol.66, issue 3, pp.2397-2407.

N. Alballa, I. Al-Turaiki. (2021)." Machine learning approaches in COVID-19 diagnosis, mortality, and severity risk prediction: A review" Informatic in Medicine Unlocked, vol.24, pp. 100564.

W. Hou, Z. Zhao, A. Chen, H. Li, et al. (2021)" Machining learning predicts the need for escalated care and mortality in COVID-19 patients from clinical variables " International journal of medical sciences, vol.18.issue 8, pp. 1739-1745.

C. Gazzaruso, E. Paolozzi, C. Valenti, M. Brocchetta, et al. (2020). " Association between antithrombin and mortality in patients with COVID-19. A possible link with obesity " Nutrition, metabolism, and cardiovascular diseases, vol.30, issue 11, pp. 1914-1919.

S. Dargan, M. Kumar, M.R. Ayyagari, G. Kumar. (2020). "A Survey of Deep Learning and Its Applications: A New Paradigm to Machine Learning" Archives of Computational Methods in Engineering, Vol. 27, issue 4, pp.1071–1092.

S. Quazi, (2022). " Artificial intelligence and machine learning in precision and genomic medicine ", Med Oncol, vol. 39, issue 8. pp.120.

I.E. Agbehadji, B.O. Awuzie, A. B. Ngowi, R.C. Millham. (2020). "Review of Big Data Analytics, Artificial Intelligence and Nature-Inspired Computing Models towards Accurate Detection of COVID-19 Pandemic Cases and Contact Tracing." International Journal of Environmental Research and Public Health, vol. 17, issue 15, pp.5330.

M.Smith, F. Alvarez. (2021). " Identifying mortality factors from Machine Learning using Shapley values - a case of COVID19" Expert Syst Appl, vol. 176, pp. 114832.

C.Hu, Z. Liu, Y. Jiang, O. Shi, et al. (2020). "Early prediction of mortality risk among patients with severe COVID-19, using machine learning " International Journal of Epidemiology, vol. 49, issue 6, pp.1918-1929.

M.Daniyal, R. O. Ogundokun, K. Abid, M. D. Khan, et al. (2020)."Predictive modeling of COVID-19 death cases in Pakistan" Infectious Disease Modelling, 5, 897–904.

R.M. Arias Velásquez, J.V. Mejía Lara. (2020). "Forecast and evaluation of COVID-19 spreading in USA with reduced-space Gaussian process regression" Chaos, solitons, and fractals, vol. 136, pp.109924.

A.K. Das, S. Mishra, S. Saraswathy Gopalan. (2020). " Predicting CoVID-19 community mortality risk using machine learning and development of an online prognostic tool" Peer J, vol. 8, pp. 10083.

KC. Wong KC, Y. Xiang, L. Yin, HC.So.(2020) "Uncovering Clinical Risk Factors and Predicting Severe COVID-19 Cases Using UK Biobank Data: Machine Learning Approach" JMIR Public Health Surveill. vol.7, issue 9. pp. e29544.

MT. García-Ordás, N. Arias, C. Benavides, García-Olalla, et al. (2020). "Evaluation of Country Dietary Habits Using Machine Learning Techniques in Relation to Deaths from COVID-19" Healthcare (Basel, Switzerland), vol.8, issue 4, pp. 371.

T. Saba, I. Abunadi, MN. Shahzad, AR. Khan. (2021)." Machine learning techniques to detect and forecast the daily total COVID-19 infected and deaths cases under different lockdown types ", Microscopy research and technique, vol.84, issue 7, pp. 1462–1474.

M.Pourhomayoun, M. Shakibi. (2021). "Predicting mortality risk in patients with COVID-19 using machine learning to help medical decision-making" Smart Health (Amst), vol.20, pp.100178.

S. Subudhi, A. Verma, A.B. Patel, c. Hardin, et al. (2021). "Comparing machine learning algorithms for predicting ICU admission and mortality in COVID-19" NPJ Digit Med, vol.4, issue 1, pp.87.

Kaggle. (2022, January 20). Mortality risk clinical data of covid19 patients. [Online].

Available:https://www.kaggle.com/datasets/harshwalia/mortality-risk-clinincal-data-of-covid19-patients. Accessed:2022, March 19.

B. Abdollahzadeh, F.S. Gharehchopogh. (2021). " A multi-objective optimization algorithm for feature selection problems" Eng. with Comput, vol.38, issue suppl 1, pp. 1845–1863.

A.A. Ewees, L. Abualigah, D. Yousri, Z.Y. Algamal, et al. (2022). "Improved Slime Mould Algorithm based on Firefly Algorithm for feature selection: a case study on QSAR model" Eng. with Comput, vol.38, issue (Suppl 3), pp. 2407–2421.

T. Saba, (2021). " Computer vision for microscopic skin cancer diagnosis using handcrafted and non-handcrafted features " Microscopy research and technique, vol. 84, issue 6, pp. 1272-1283.

M.A. Khan, M. Sharif, T. Akram, M. Raza, et al. (2020)." Hand-crafted and deep convolutional neural network features fusion and selection strategy: An application to intelligent human action recognition "Applied Soft Computing, vol. 87, pp.105986.

H. Wang, p. Xu, J. Zhao. (2021)."Improved KNN Algorithm Based on Preprocessing of Center in Smart Cities " Complexity, vol. 2021, pp.

R. G. da Silva, M. Ribeiro, V. C. Mariani, L. Coelho. (2020). ."Forecasting Brazilian and American COVID-19 cases based on artificial intelligence coupled with climatic exogenous variables " Chaos, solitons, and fractals, vol.139, pp.110027.

S. A. Khan, M. Nazir, M. A. Khan, T. Saba, et al. (2019). " Lungs nodule detection framework from computed tomography images using support vector machine" Microsc Res Tech, vol.82, issue 8, pp.1256–1266.

B. Gaye, D. Zhang, A. Wulamu. (2021). " Improvement of Support Vector Machine Algorithm in Big Data Background ", Mathematical Problems in Engineering, vol.2021, issue 1 pp. 1-9.