Abstract
Uzbekistan as well as the rest of the world faces the third wave of COVID-19 and uses machine learning algorithms to predict the adverse outcome during the admission of new patients. We collected the dataset of 1145 patients admitted to the Republican Center for Emergency Medicine. We use different machine learning models to predict the COVID-19 severe course. This study uses feature selection procedures based on statistical tests and the elimination of linearly dependent features. The resulting multilayer perceptron yields a ROC AUC of 86.9% on the test set outperforming other machine learning algorithms and several competing works. The model relies on easily collected features without blood laboratory testing. It increases an availability of the reliable risk prediction to developing countries.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Pytorch.org v.1.9.0.
References
Robilotti, E., Babady, N., Mead, P., et al.: Determinants of COVID-19 disease severity in patients with cancer. Nat. Med. 26, 1218–1223 (2020). https://doi.org/10.1038/s41591-020-0979-0
Ikramov, A., Adilova, F., Anvarov, K., Khadjibaev, A.: COVID-19 severity prediction in patients based on anomaly detection approach. In: Yang, X.-S., Sherratt, S., Dey, N., Joshi, A. (eds.) Proceedings of Sixth International Congress on Information and Communication Technology. LNNS, vol. 235, pp. 611–618. Springer, Singapore (2022). https://doi.org/10.1007/978-981-16-2377-6_56
Statsenko, Y., Al Zahmi, F., Habuza, T., et al.: Prediction of COVID-19 severity using laboratory findings on admission: informative values, thresholds, ML model performance. BMJ Open,11, e044500 (2021). https://doi.org/10.1136/bmjopen-2020-044500
Cobre, A., Stremel, D., Noleto, G., et al.: Diagnosis and prediction of COVID-19 severity: can biochemical tests and machine learning be used as prognostic indicators? Comput. Biol. Med. 134, 104531 (2021). https://doi.org/10.1016/j.compbiomed.2021.104531, ISSN 0010-4825
Bats, M.-L., Rucheton, B., Fleur, T., et al.: Covichem: a biochemical severity risk score of COVID-19 upon hospital admission. PLoS One 16(5), e0250956 (2021). https://doi.org/10.1371/journal.pone.0250956
Yuanyuan, C., Xiaolin, Z., Huadong, Y., et al.: CANPT score: a tool to predict severe COVID-19 on admission. Front. Med. 8, 68 (2021). https://doi.org/10.3389/fmed.2021.608107
Zhou, J., Lee, S., Wang, X., et al.: Development of a multivariable prediction model for severe COVID-19 disease: a population-based study from Hong Kong. NPJ Digit. Med. 4, 66 (2021). https://doi.org/10.1038/s41746-021-00433-4
Aktar, S., Ahamad, M.M., Rashed-Al-Mahfuz, M., et al.: Machine learning approach to predicting COVID-19 disease severity based on clinical blood test data: statistical analysis and model development. JMIR Med. Inform. 9(4), e25884 (2021). https://doi.org/10.2196/25884
Estiri, H., Strasser, Z.H., Murphy, S.N.: Individualized prediction of COVID-19 adverse outcomes with MLHO. Sci. Rep. 11, 5322 (2021). https://doi.org/10.1038/s41598-021-84781-x
Dimitrova, D., Kaishev, V., Tan, S.: Computing the Kolmogorov–Smirnov distribution when the underlying CDF is purely discrete, mixed or continuous. J. Stat. Softw. 95(10), 1–42 (2020). https://doi.org/10.18637/jss.v095.i10
Sprinthall, R.C.: Basic Statistical Analysis, 9th edn. Pearson Education (2011). ISBN 978–0–205–05217–2
Daniel, W.W.: Kruskal–Wallis one-way analysis of variance by ranks. In: Applied Nonparametric Statistics, 2nd edn, pp. 226–234. PWS-Kent, Boston (1990). ISBN 0–534–91976–6
Chawla, N.V., Herrera, F., Garcia, S., et al.: SMOTE for learning from imbalanced data: progress and challenges, marking the 15-year anniversary. J. Artif. Intelligence Research. 61, 863–905 (2020). https://doi.org/10.1613/jair.1.11192
Acknowledgement
The authors would like to thank the staff of the Medical Centre involved in the study for collecting patients’ data, and Maksim Bolonkin for the discussion, ideas of possible models to use, edition, and language correction.
Funding
The study was fulfilled under project A-CC-2021–112/2 funded by Ministry of innovative development of the Republic of Uzbekistan.
Author information
Authors and Affiliations
Contributions
AI built and tested all ML models; KA and NI collected the data, analyzed the results; VS, AA, AA evaluated results of statistical tests.
Corresponding author
Editor information
Editors and Affiliations
Ethics declarations
Ethics and Privacy
Hospitals use the designed software to not miss the possible hard cases. If the software predicts a low risk of a hard course, but the examining doctor decides otherwise, the final decision on the admission of a patient is made by the doctor. The software does not use or disclose private information on patients. The database is available upon request but does not contain any information that can disclose the identity of the patients.
Conflict of Interests
The authors declare no conflict of interests.
Supplementary Materials
Supplementary Materials
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Ikramov, A., Anvarov, K., Sharipova, V., Iskhakov, N., Abdurakhmonov, A., Alimov, A. (2022). Machine Learning Algorithms in Application to COVID-19 Severity Prediction in Patients. In: Long, G., Yu, X., Wang, S. (eds) AI 2021: Advances in Artificial Intelligence. AI 2022. Lecture Notes in Computer Science(), vol 13151. Springer, Cham. https://doi.org/10.1007/978-3-030-97546-3_28
Download citation
DOI: https://doi.org/10.1007/978-3-030-97546-3_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-97545-6
Online ISBN: 978-3-030-97546-3
eBook Packages: Computer ScienceComputer Science (R0)