Research of mortality risk prediction based on hospital admission data for COVID-19 patients

Qian Shen; Qian Shen

doi:10.3934/mbe.2023247

Mathematical Biosciences and Engineering

2023, Volume 20, Issue 3: 5333-5351. doi: 10.3934/mbe.2023247

Previous Article Next Article

Research article

Research of mortality risk prediction based on hospital admission data for COVID-19 patients

Qian Shen ^,

Department of Applied Statistics, School of Statistics, Xi'an University of Finance and Economics, Xi'an 710100, China

Academic Editor: Yang Kuang

Received: 13 October 2022 Revised: 02 December 2022 Accepted: 19 December 2022 Published: 11 January 2023

As COVID-19 continues to spread across the world and causes hundreds of millions of infections and millions of deaths, medical institutions around the world keep facing a crisis of medical runs and shortages of medical resources. In order to study how to effectively predict whether there are risks of death in patients, a variety of machine learning models have been used to learn and predict the clinical demographics and physiological indicators of COVID-19 patients in the United States of America. The results show that the random forest model has the best performance in predicting the risk of death in hospitalized patients with COVID-19, as the COVID-19 patients' mean arterial pressures, ages, C-reactive protein tests' values, values of blood urea nitrogen and their clinical troponin values are the most important implications for their risk of death. Healthcare organizations can use the random forest model to predict the risks of death based on data from patients admitted to a hospital due to COVID-19, or to stratify patients admitted to a hospital due to COVID-19 based on the five key factors this can optimize the diagnosis and treatment process by appropriately arranging ventilators, the intensive care unit and doctors, thus promoting the efficient use of limited medical resources during the COVID-19 pandemic. Healthcare organizations can also establish databases of patient physiological indicators and use similar strategies to deal with other pandemics that may occur in the future, as well as save more lives threatened by infectious diseases. Governments and people also need to take action to prevent possible future pandemics.
- COVID-19,
- death risk feature,
- machine learning,
- tree model,
- ensemble learning,
- emergency triage strategy
Citation: Qian Shen. Research of mortality risk prediction based on hospital admission data for COVID-19 patients[J]. Mathematical Biosciences and Engineering, 2023, 20(3): 5333-5351. doi: 10.3934/mbe.2023247

Related Papers:

Abstract

As COVID-19 continues to spread across the world and causes hundreds of millions of infections and millions of deaths, medical institutions around the world keep facing a crisis of medical runs and shortages of medical resources. In order to study how to effectively predict whether there are risks of death in patients, a variety of machine learning models have been used to learn and predict the clinical demographics and physiological indicators of COVID-19 patients in the United States of America. The results show that the random forest model has the best performance in predicting the risk of death in hospitalized patients with COVID-19, as the COVID-19 patients' mean arterial pressures, ages, C-reactive protein tests' values, values of blood urea nitrogen and their clinical troponin values are the most important implications for their risk of death. Healthcare organizations can use the random forest model to predict the risks of death based on data from patients admitted to a hospital due to COVID-19, or to stratify patients admitted to a hospital due to COVID-19 based on the five key factors this can optimize the diagnosis and treatment process by appropriately arranging ventilators, the intensive care unit and doctors, thus promoting the efficient use of limited medical resources during the COVID-19 pandemic. Healthcare organizations can also establish databases of patient physiological indicators and use similar strategies to deal with other pandemics that may occur in the future, as well as save more lives threatened by infectious diseases. Governments and people also need to take action to prevent possible future pandemics.

References

[1]	G. Gabutti, E. d'Anchera, F. De Motoli, M. Savio, A. Stefanati, The epidemiological characteristics of the COVID-19 pandemic in Europe: Focus on Italy, Int. J. Environ. Res. Public Health, 18 (2021), 2942. https://doi.org/10.3390/ijerph18062942 doi: 10.3390/ijerph18062942
[2]	Y. Mahendradhata, N. L. P. E. Andayani, E. T. Hasri, M. D. Arifi, R. G. M. S. Siahaan, D. A. Solikha, et al., The capacity of the Indonesian healthcare system to respond to COVID-19, Front. Public Health, 9 (2021), 887. https://doi.org/10.3389/fpubh.2021.649819 doi: 10.3389/fpubh.2021.649819
[3]	A. Johnson, A. B. Amin, A. R. Ali, B. Hoots, B. L. Cadwell, S. Arora, et al. COVID-19 incidence and death rates among unvaccinated and fully vaccinated adults with and without booster doses during periods of Delta and Omicron variant emergence-25 US Jurisdictions, April 4–December 25, 2021, Morb. Mortal. Wkly. Rep., 71 (2022). https://doi.org/10.15585/mmwr.mm7104e2
[4]	A. Notari, G. Torrieri, COVID-19 transmission risk factors, Pathog. Glob. Health, 116 (2020), 146–177. https://doi.org/10.1080/20477724.2021.1993676 doi: 10.1080/20477724.2021.1993676
[5]	M. Coccia, Optimal levels of vaccination to reduce COVID-19 infected individuals and deaths: A global analysis, Environ. Res., 204 (2022), 112314. https://doi.org/10.1016/j.envres.2021.112314 doi: 10.1016/j.envres.2021.112314
[6]	I. Benati, M. Coccia, Global analysis of timely COVID-19 vaccinations: improving governance to reinforce response policies for pandemic crises, Int. J. Health Governance, 27 (2022). https://doi.org/10.1108/IJHG-07-2021-0072
[7]	B. V. Duong, P. Larpruenrudee, T. Fang, S. I. Hossain, S. C. Saha, Y. Gu, et al., Is the SARS CoV-2 omicron variant deadlier and more transmissible than delta variant?, Int. J. Environ. Res. Public Health, 19 (2022), 4586. https://doi.org/10.3390/ijerph19084586 doi: 10.3390/ijerph19084586
[8]	M. Hung, B. Mennell, A. Christensen, A. Mohajeri, H. Azabache, R. Moffat, Trends in COVID-19 inpatient cases and hospital capacities during the emergence of the omicron variant in the United States, COVID, 2 (2022), 1207–1213. https://doi.org/10.3390/covid2090087 doi: 10.3390/covid2090087
[9]	M. E. Shipe, S. A. Deppen, F. Farjah, E. L. Grogan, Developing prediction models for clinical use using logistic regression: An overview, J. Thorac. Dis., 11 (2019), S574. https://doi.org/10.21037/jtd.2019.01.25 doi: 10.21037/jtd.2019.01.25
[10]	E. Christodoulou, J. Ma, G. S. Collins, E. W. Steyerberg, J. Y. Verbakel, B. V. Calster, A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models, J. Clin. Epidemiol., 110 (2019), 12–22. https://doi.org/10.1016/j.jclinepi.2019.02.004 doi: 10.1016/j.jclinepi.2019.02.004
[11]	W. Shaban, A. Rabie, A. Saleh, M. Abo-Elsoud, A new COVID-19 patients detection strategy (CPDS) based on hybrid feature selection and enhanced KNN classifier, Knowl.-Based Syst., 205 (2020), 106270. https://doi.org/10.1016/j.knosys.2020.106270 doi: 10.1016/j.knosys.2020.106270
[12]	V. Singh, R. C. Poonia, S. Kumar, P. Dass, P. Agarwal, V. Bhatnagar et al., Prediction of COVID-19 corona virus pandemic based on time series data using support vector machine, J. Discret. Math. Sci. Cryptogr., 23 (2020), 1583–1597. https://doi.org/10.1080/09720529.2020.1784535 doi: 10.1080/09720529.2020.1784535
[13]	L. Breiman, Random forests, in Machine learning, 45 (2001), 5–32. https://doi.org/10.1023/A:1010933404324
[14]	M. Khalilia, S. Chakraborty, M. Popescu, Predicting disease risks from highly imbalanced data using random forest, BMC Med. Inf. Decis. Making, 11 (2011), 1–13. https://doi.org/10.1186/1472-6947-11-51 doi: 10.1186/1472-6947-11-51
[15]	M. Ezzoddin, H. Nasiri, M. Dorrigiv, Diagnosis of COVID-19 cases from chest X-ray images using deep neural network and LightGBM, in 2022 International Conference on Machine Vision and Image Processing (MVIP), (2022), 1–7. https://doi.org/10.1109/MVIP53647.2022.9738760
[16]	T. Chen, C. Guestrin, Xgboost: A scalable tree boosting system, in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, (2016), 785–794. https://doi.org/10.1145/2939672.2939785
[17]	S. Li, X. Zhang, Research on orthopedic auxiliary classification and prediction model based on XGBoost algorithm, Neural Comput. Appl., 32 (2020), 1971–1979. https://doi.org/10.1007/s00521-019-04378-4 doi: 10.1007/s00521-019-04378-4
[18]	M. Covino, C. Sandroni, M. Santoro, L. Sabia, B. Simeoni, M. Bocci, et al., Predicting intensive care unit admission and death for COVID-19 patients in the emergency department using early warning scores, Resuscitation, 156 (2020), 84–91. https://doi.org/10.1016/j.resuscitation.2020.08.124 doi: 10.1016/j.resuscitation.2020.08.124
[19]	Y. Allenbach, D. Saadoun, G. Maalouf, M. Vieira, A. Hellio, J. Boddaert et al., Development of a multivariate prediction model of intensive care unit transfer or death: A French prospective cohort study of hospitalized COVID-19 patients, PloS one, 15 (2020), e0240711. https://doi.org/10.1371/journal.pone.0240711 doi: 10.1371/journal.pone.0240711
[20]	S. Mirri, G. Delnevo, M. Roccetti, Is a COVID-19 second wave possible in emilia-romagna (Italy)? Forecasting a future outbreak with particulate pollution and machine learning, Comput., 8 (2020), 74. https://doi.org/10.3390/computation8030074 doi: 10.3390/computation8030074
[21]	H. Estiri, Z. Strasser, S. Murphy, Individualized prediction of COVID-19 adverse outcomes with MLHO, Sci. Rep., 11 (2021), 5322. https://doi.org/10.1038/s41598-021-84781-x doi: 10.1038/s41598-021-84781-x
[22]	A. S. Yadaw, Y. Li, S. Bose, R. Iyengar, S. Bunyavanich, G. Pandey, Clinical features of COVID-19 mortality: Development and validation of a clinical prediction model, Lancet Digital Health, 2 (2020), 516–525. https://doi.org/10.1016/S2589-7500(20)30217-X doi: 10.1016/S2589-7500(20)30217-X
[23]	D. J. Altschul, S. R. Unda, J. Benton, R. de la Garza Ramos, P. Cezayirli, M. Mehler, et al. A novel severity score to predict inpatient mortality in COVID-19 patients, Sci. Rep., 10 (2020), 1–8. https://doi.org/10.1038/s41598-020-73962-9 doi: 10.1038/s41598-020-73962-9
[24]	H. Wang, H. Ai, Y. Fu, Q. Li, R. Cui, X. Ma, et al., Development of an early warning model for predicting the death risk of coronavirus disease 2019 based on data immediately available on admission, Front. Med., (2021), 1302. https://doi.org/10.3389/fmed.2021.699243
[25]	L. Zhang, A. Xu, L. An, M. Li, Bayesian inference of system reliability for multicomponent stress-strength model under marshall-olkin weibull distribution, Systems, (2022). https://doi.org/10.3390/systems10060196
[26]	Y. Wang, W. Wang, Y. Tang, A Bayesian semiparametric accelerate failure time mixture cure model, Int. J. Biostat., 18 (2021), 473–485. https://doi.org/10.1515/ijb-2021-0012 doi: 10.1515/ijb-2021-0012
[27]	L. Zhuang, A. Xu, B. Wang, Y. Xue, S. Zhang, Data analysis of progressive‐stress accelerated life tests with group effects, Qual. Technol. Quant. Manage., (2022), 1–21. https://doi.org/10.1080/16843703.2022.2147690
[28]	G. S. Rao, M. Aslam, Inspection plan for COVID-19 patients for weibull distribution using repetitive sampling under indeterminacy, BMC Med. Res. Methodol., 21 (2021). https://doi.org/10.1186/s12874-021-01387-7
[29]	A. Caillon, K. Zhao, K. O. Klein, C. M. T. Greenwood, Z. Lu, P. Paradis, et al., High systolic blood pressure at hospital admission is an important risk factor in models predicting outcome of COVID-19 patients, Am. J. Hypertens., 34 (2021), 282–290. https://doi.org/10.1093/ajh/hpaa225 doi: 10.1093/ajh/hpaa225
[30]	M. V. Blagosklonny, From causes of aging to death from COVID-19, Aging, 12 (2020), 10004–10021. https://doi.org/10.18632/aging.103493 doi: 10.18632/aging.103493
[31]	G. Wang, C. Wu, Q. Zhang, F. Wu, B. Yu, J. Lv et al., C-Reactive protein level may predict the risk of COVID-19 aggravation, Open Forum Infect. Dis., 7 (2020). https://doi.org/10.1093/ofid/ofaa153
[32]	F. Ok, O. Erdogan, E. Durmus, S. Carkci, A. Canik, Predictive values of blood urea nitrogen/creatinine ratio and other routine blood parameters on disease severity and survival of COVID‐19 patients, J. Med. Virol., 93 (2020), 786–793. https://doi.org/10.1002/jmv.26300 doi: 10.1002/jmv.26300
[33]	G. Lippi, C. Lavie, F. Sanchis-Gomar, Cardiac troponin I in patients with coronavirus disease 2019 (COVID-19): Evidence from a meta-analysis, Prog. Cardiovasc. Dis., 63 (2020), 390–391. https://doi.org/10.1016/j.pcad.2020.03.001 doi: 10.1016/j.pcad.2020.03.001
[34]	B. P. Nguyen, W. Tay, C. Chui, Robust biometric recognition from palm depth images for gloved hands, IEEE Trans. Hum.-Mach. Syst., 45 (2015), 799–804. https://doi.org/10.1109/THMS.2015.2453203 doi: 10.1109/THMS.2015.2453203
[35]	C. Chang, C. Lin, LIBSVM: A library for support vector machines, ACM Trans. Intell. Syst. Technol., 2 (2011), 1–27. https://doi.org/10.1145/1961189.1961199 doi: 10.1145/1961189.1961199
[36]	G. Ke, Q. Meng, T. Finley, T. Wang, W. Chen, W. Ma, et al., Lightgbm: A highly efficient gradient boosting decision tree, in Proceedings of the 31st International Conference on Neural Information Processing Systems, (2017), 3149–3157.
[37]	N. V. Chawla, K. W. Bowyer, L. O. Hall, W. P. Kegelmeyer, SMOTE: synthetic minority over-sampling technique, J. Artif. Intell. Res., 16 (2002), 321–357. https://doi.org/10.1613/jair.953 doi: 10.1613/jair.953
[38]	F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, et al., Scikit-learn: sklearn. preprocessing. robustscaler, J. Mach. Learn. Res., 12 (2011), 2825–2830.

Reader Comments

Your name:*

Email:*
© 2023 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)