When an outbreak of COVID-19 occurs, it will cause a shortage of medical resources and the surge of demand for hospital beds. Predicting the length of stay (LOS) of COVID-19 patients is helpful to the overall coordination of hospital management and improves the utilization rate of medical resources. The purpose of this paper is to predict LOS for patients with COVID-19, so as to provide hospital management with auxiliary decision-making of medical resource scheduling. We collected the data of 166 COVID-19 patients in a hospital in Xinjiang from July 19, 2020, to August 26, 2020, and carried out a retrospective study. The results showed that the median LOS was 17.0 days, and the average of LOS was 18.06 days. Demographic data and clinical indicators were included as predictive variables to construct a model for predicting the LOS using gradient boosted regression trees (GBRT). The MSE, MAE and MAPE of the model are 23.84, 4.12 and 0.76 respectively. The importance of all the variables involved in the prediction of the model was analyzed, and the clinical indexes creatine kinase-MB (CK-MB), C-reactive protein (CRP), creatine kinase (CK), white blood cell count (WBC) and the age of patients had a higher contribution to the LOS. We found our GBRT model can accurately predict the LOS of COVID-19 patients, which will provide good assistant decision-making for medical management.
Citation: Zhihao Zhang, Ting Zeng, Yijia Wang, Yinxia Su, Xianghua Tian, Guoxiang Ma, Zemin Luan, Fengjun Li. Prediction Model of hospitalization time of COVID-19 patients based on Gradient Boosted Regression Trees[J]. Mathematical Biosciences and Engineering, 2023, 20(6): 10444-10458. doi: 10.3934/mbe.2023459
When an outbreak of COVID-19 occurs, it will cause a shortage of medical resources and the surge of demand for hospital beds. Predicting the length of stay (LOS) of COVID-19 patients is helpful to the overall coordination of hospital management and improves the utilization rate of medical resources. The purpose of this paper is to predict LOS for patients with COVID-19, so as to provide hospital management with auxiliary decision-making of medical resource scheduling. We collected the data of 166 COVID-19 patients in a hospital in Xinjiang from July 19, 2020, to August 26, 2020, and carried out a retrospective study. The results showed that the median LOS was 17.0 days, and the average of LOS was 18.06 days. Demographic data and clinical indicators were included as predictive variables to construct a model for predicting the LOS using gradient boosted regression trees (GBRT). The MSE, MAE and MAPE of the model are 23.84, 4.12 and 0.76 respectively. The importance of all the variables involved in the prediction of the model was analyzed, and the clinical indexes creatine kinase-MB (CK-MB), C-reactive protein (CRP), creatine kinase (CK), white blood cell count (WBC) and the age of patients had a higher contribution to the LOS. We found our GBRT model can accurately predict the LOS of COVID-19 patients, which will provide good assistant decision-making for medical management.
| [1] | Y. Zhang, The epidemiological characteristics of an outbreak of 2019 novel coronavirus diseases (COVID-19) in China, China CDC Wkly, 2 (2020), 113–122. |
| [2] | K. Li, C. Zhang, L. Qin, C. Zhang, A. Li, J. Sun, et al., A nomogram prediction of length of hospital stay in patients with COVID-19 pneumonia: A retrospective cohort study, Dis. Markers, 2021 (2021). https://doi.org/10.1155/2021/5598824 |
| [3] | R. Yaesoubi, S. You, Q. Xi, N. A. Menzies, A. Tuite, Y. H. Grad, et al., Simple decision rules to predict local surges in COVID-19 hospitalizations during the winter and spring of 2022, preprint, arXiv: 2021.12.13.21267657. https://doi.org/10.1101/2021.12.13.21267657 |
| [4] | X. Chen, W. Gao, J. Li, D. You, Z. Yu, M. Zhang, et al., A predictive paradigm for COVID-19 prognosis based on the longitudinal measure of biomarkers, Briefings Bioinf., 22 (2021). https://doi.org/10.1093/bib/bbab206 |
| [5] | L. Wynants, B. Van Calster, M. Bonten, G. Collins, T. Debray, M. De Vos, et al., Prediction models for diagnosis and prognosis of covid-19 infection: Systematic review and critical appraisal, Br. Med. J., 369 (2020). https://doi.org/10.1101/2020.03.24.20041020 |
| [6] | C. Bardelli, Inference on COVID-19 epidemiological parameters using bayesian survival analysis, Entropy, 23 (2021). https://doi.org/10.3390/e23101262 |
| [7] | Y. You, M. Chen, X. Chen, W. Yu, Diaphragm thickness on computed tomography for nutritional assessment and hospital stay prediction in critical COVID-19, Asia Pac. J. Clin. Nutr., 31 (2022), 33–40. |
| [8] | T. Chiam, K. Subedi, D. Chen, E. Best, F. B. Bianco, G. Dobler, et al., Hospital length of stay among COVID-19-positive patients, J. Clin. Transl. Res., 7 (2021), 377–385. |
| [9] |
M. G Usher, R. Tourani, G. Simon, C. Tignanelli, B. Jarabek, C. E Strauss, et al., Overcoming gaps: Regional collaborative to optimize capacity management and predict length of stay of patients admitted with COVID-19, J. Am. Med. Inf. Assoc., 4 (2021), ooab055. https://doi.org/10.1093/jamiaopen/ooab055 doi: 10.1093/jamiaopen/ooab055
|
| [10] |
E. Ahlstrand, S. Cajander, P. Cajander, E. Ingberg, E. Löf, M. Wegener, et al., Visual scoring of chest CT at hospital admission predicts hospitalization time and intensive care admission in Covid-19, Infect. Dis., 53 (2021), 622–632. https://doi.org/10.1080/23744235.2021.1910727 doi: 10.1080/23744235.2021.1910727
|
| [11] |
A. Lasbleiz, B. Cariou, P. Darmon, A. Soghomonian, P. Ancel, S. Boullu, et al., Phenotypic Characteristics and Development of a Hospitalization Prediction Risk Score for Outpatients with Diabetes and COVID-19: The DIABCOVID Study, J. Clin. Med., 9 (2020), 3726. https://doi.org/10.3390/jcm9113726 doi: 10.3390/jcm9113726
|
| [12] |
C. Eastin, T. Eastin, Clinical characteristics of coronavirus disease 2019 in China, J. Emerg. Med., 58 (2020), 711–712. https://doi.org/10.1016/j.jemermed.2020.04.004 doi: 10.1016/j.jemermed.2020.04.004
|
| [13] | Q. J. Leclerc, N. M. Fuller, R. H. Keogh, K. Diaz-Ordaz, R. Sekula, M. G. Semple, et al., Importance of patient bed pathways and length of stay differences in predicting COVID-19 hospital bed occupancy in England, BMC Health Serv. Res., 21 (2021). https://doi.org/10.1101/2021.01.14.21249791 |
| [14] |
J. Ebinger, M. Wells, D. Ouyang, T. Davis, N. Kaufman, S. Cheng, et al., A Machine learning algorithm predicts duration of hospitalization in COVID-19 patients, Intell. Based Med., 5 (2021), 100035. https://doi.org/10.1016/j.ibmed.2021.100035 doi: 10.1016/j.ibmed.2021.100035
|
| [15] | B. Mahboub, M. T. A. Bataineh, H. Alshraideh, R. Hamoudi, L. Salameh, A. Shamayleh, et al., Prediction of COVID-19 Hospital length of stay and risk of death using artificial intelligence-based modeling, Front. Med., 8 (2021). https://doi.org/10.3389/fmed.2021.592336 |
| [16] |
A. Lopez-Cheda, M. A. Jacome, R. Cao, P. M. De Salazar, Estimating lengths-of-stay of hospitalised COVID-19 patients using a non-parametric model: A case study in Galicia (Spain), Epidemiol. Infect., 149 (2021), e102. https://doi.org/10.1017/S0950268821000959 doi: 10.1017/S0950268821000959
|
| [17] | A. Henzi, G. Kleger, M. P. Hilty, P. D. W. Garcia, J. F. Ziegel, Probabilistic analysis of COVID-19 patients' individual length of stay in Swiss intensive care units, Plos One, 16 (2021). https://doi.org/10.1371/journal.pone.0247265 |
| [18] | T. Dan, Y. Li, Z. Zhu, X. Chen, W. Quan, Y. Hu, et al., Machine Learning to Predict ICU Admission, ICU mortality and survivors' length of stay among COVID-19 patients: Toward optimal allocation of ICU resources, in 2020 IEEE International Conference on Bioinformatics and Biomedicine, (2020), 555–561. https://doi.org/10.1109/BIBM49941.2020.9313292 |
| [19] |
H. Yue, Q. Yu, C. Liu, Y. Huang, Z. Jiang, C. Shao, et al., Machine learning-based CT radiomics model for predicting hospital stay in patients with pneumonia associated with SARS-CoV-2 infection: A multicenter study, Ann. Transl. Med., 8 (2020), 859. https://doi.org/10.21037/atm-20-3026 doi: 10.21037/atm-20-3026
|
| [20] |
D. Rozenbaum, J. Shreve, N. Radakovich, A. Duggal, L. Jehi, A. Nazha, Personalized prediction of hospital mortality in COVID-19-positive patients, Mayo Clin. Proc. Innovations Qual. Outcomes, 5 (2021), 795–801. https://doi.org/10.1016/j.mayocpiqo.2021.05.001 doi: 10.1016/j.mayocpiqo.2021.05.001
|
| [21] |
A. H. T. Chia, M. S. Khoo, A. Z. Lim, K. E. Ong, Y. Sun, B. P. Nguyen, et al., Explainable machine learning prediction of ICU mortality, Elsevier Ltd, 25 (2021), 100674. https://doi.org/10.1016/j.imu.2021.100674 doi: 10.1016/j.imu.2021.100674
|
| [22] | H. N. Pham, A. Chatterjee, B. Narasimhan, C. W. Lee, D. K. Jha, E. Y. F. Wong, et al., Predicting hospital readmission patterns of diabetic patients using ensemble model and cluster analysis, in 2019 International Conference on System Science and Engineering (ICSSE), (2019), 273–278. https://doi.org/10.1109/ICSSE.2019.8823441 |
| [23] |
Q. Li, Y. Miao, X. Zeng, C. S. Tarimo, C. Wu, J. Wu, Prevalence and factors for anxiety during the coronavirus disease 2019 (COVID-19) epidemic among the teachers in China, J. Affect. Disord., 277 (2020), 153–158. https://doi.org/10.1016/j.jad.2020.08.017 doi: 10.1016/j.jad.2020.08.017
|
| [24] |
Y. Ren, H. Jiang, N. Ji, H. Yu, TBSM: A traffic burst-sensitive model for short-term prediction under special events, Knowl-Based Syst., 240 (2020), 108120. https://doi.org/10.1016/j.knosys.2022.108120 doi: 10.1016/j.knosys.2022.108120
|
Figures(4) / Tables(8)
Zhihao Zhang, Ting Zeng, Yijia Wang, Yinxia Su, Xianghua Tian, Guoxiang Ma, Zemin Luan, Fengjun Li. Prediction Model of hospitalization time of COVID-19 patients based on Gradient Boosted Regression Trees[J]. Mathematical Biosciences and Engineering, 2023, 20(6): 10444-10458. doi: 10.3934/mbe.2023459
DownLoad: