Predicting hospital disposition for trauma patients: application of data-driven machine learning algorithms

Nasser Alrashidi; Musaed Alrashidi; Sara Mejahed; Ahmed A. Eltahawi; Nasser Alrashidi; Musaed Alrashidi; Sara Mejahed; Ahmed A. Eltahawi

doi:10.3934/math.2024376

AIMS Mathematics

2024, Volume 9, Issue 4: 7751-7769. doi: 10.3934/math.2024376

Previous Article Next Article

Research article Special Issues

Predicting hospital disposition for trauma patients: application of data-driven machine learning algorithms

1.
Department of Surgery, College of Medicine, Qassim University, Buraydah, Qassim, Saudi Arabia
2.
Department of Electrical Engineering, College of Engineering, Qassim University, Buraydah 52571, Saudi Arabia; malrashidi@qu.edu.sa
3.
Information System Department, Faculty of Computers and Informatics, Suez Canal University, Egypt; sara.mongy@ci.suez.edu.eg, a.othman@ci.suez.edu.eg

Received: 23 December 2023 Revised: 30 January 2024 Accepted: 06 February 2024 Published: 23 February 2024
MSC : 68Q30

As a consequence of road accidents, around 1.3 million people die, and between 20 to 50 million have nonfatal injuries. Therefore, hospitals are receiving a high volume of patients in their urgent care, and a quick decision must be made regarding their treatment plans. At the admission stage, there is no information or probability about the patient's final result, regardless of if the patient will mostly die or be safely discharged from the hospital. To address this issue, this study proposed a machine learning-based framework that can predict the hospital disposition for trauma patients. The framework was developed to anticipate whether the patient would be safely discharged from the hospital or die based on a set of features collected at the admission time. In this study, the data used was collected from the King Abdulaziz Medical City (KAMC) in Riyadh, Saudi Arabia, and the performance of different machine learning algorithms was investigated, including eXtreme gradient boost (XGBoost), K-nearest neighbor, random forest, logistic regression, BRR, and support vector machine. Results show that the XGBoost algorithm demonstrated a high degree of detection and prediction accuracy for disposed-to-home patients; of the 6059 patients that were sent home, the XGBoost correctly predicted 5944 (98%) of the total. Finally, the developed framework could accurately predict hospital disposition for trauma patients with high accuracy and sensitivity levels. This system can benefit healthcare teams and insurance companies by providing them with a quick decision-making tool to determine the best treatment plan for patients.
- health care,
- machine learning,
- time series forecasting,
- data mining,
- classification algorithms,
- bias-variance trade-off
Citation: Nasser Alrashidi, Musaed Alrashidi, Sara Mejahed, Ahmed A. Eltahawi. Predicting hospital disposition for trauma patients: application of data-driven machine learning algorithms[J]. AIMS Mathematics, 2024, 9(4): 7751-7769. doi: 10.3934/math.2024376

Related Papers:

Abstract

As a consequence of road accidents, around 1.3 million people die, and between 20 to 50 million have nonfatal injuries. Therefore, hospitals are receiving a high volume of patients in their urgent care, and a quick decision must be made regarding their treatment plans. At the admission stage, there is no information or probability about the patient's final result, regardless of if the patient will mostly die or be safely discharged from the hospital. To address this issue, this study proposed a machine learning-based framework that can predict the hospital disposition for trauma patients. The framework was developed to anticipate whether the patient would be safely discharged from the hospital or die based on a set of features collected at the admission time. In this study, the data used was collected from the King Abdulaziz Medical City (KAMC) in Riyadh, Saudi Arabia, and the performance of different machine learning algorithms was investigated, including eXtreme gradient boost (XGBoost), K-nearest neighbor, random forest, logistic regression, BRR, and support vector machine. Results show that the XGBoost algorithm demonstrated a high degree of detection and prediction accuracy for disposed-to-home patients; of the 6059 patients that were sent home, the XGBoost correctly predicted 5944 (98%) of the total. Finally, the developed framework could accurately predict hospital disposition for trauma patients with high accuracy and sensitivity levels. This system can benefit healthcare teams and insurance companies by providing them with a quick decision-making tool to determine the best treatment plan for patients.

References

[1]	M. K. Delgado, M. A. Yokell, K. L. Staudenmayer, D. A. Spain, T. Hernandez-Boussard, N. E. Wang, Factors associated with the disposition of severely injured patients initially seen at non-trauma center emergency departments: disparities by insurance status, JAMA Surg., 149 (2014), 422–430. https://doi.org/10.1001/jamasurg.2013.4398 doi: 10.1001/jamasurg.2013.4398
[2]	S. Y. Lee, R. B. Chinnam, E. Dalkiran, S. Krupp, M. Nauss, Prediction of emergency department patient disposition decision for proactive resource allocation for admission, Healthcare Manag. Sci., 23 (2020), 339–359. https://doi.org/10.1007/s10729-019-09496-y doi: 10.1007/s10729-019-09496-y
[3]	S. M. Fernando, B. Rochwerg, P. M. Reardon, K. Thavorn, A. J. Seely, J. J. Perry, et al., Emergency department disposition decisions and associated mortality and costs in ICU patients with suspected infection, Crit. Care, 22 (2018), 172. https://doi.org/10.1186/s13054-018-2096-8 doi: 10.1186/s13054-018-2096-8
[4]	A. G. Rapsang, D. C. Shyam, Scoring systems of severity in patients with multiple trauma, Cir. Esp., 93 (2015), 213–221. https://doi.org/10.1016/j.ciresp.2013.12.021 doi: 10.1016/j.ciresp.2013.12.021
[5]	J. Plummer, H. Brown, K. Jones, D. Fearon-Boothe, N. Meeks-Aitken, A. McDonald, Trauma: the burden of a preventable problem, West Indian Med. J., 59 (2010), 26.
[6]	M. Graham, P. Parikh, S. Hirpara, M. C. McCarthy, E. R. Haut, P. P. Parikh, Predicting discharge disposition in trauma patients: development, validation, and generalization of a model using the national trauma data bank, Am. Surg., 86 (2020), 1703–1709. https://doi.org/2010.1177/0003134820949523
[7]	D. Cuadrado, A. Valls, D. Riaño, Predicting intensive care unit patients' discharge date with a hybrid machine learning model that combines length of stay and days to discharge, Mathematics, 11 (2023), 4773. https://doi.org/10.3390/math11234773 doi: 10.3390/math11234773
[8]	B. Stocker, H. K. Weiss, N. Weingarten, K. E. Engelhardt, M. Engoren, J. Posluszny, Challenges in predicting discharge disposition for trauma and emergency general surgery patients, J. Surg. Res., 256 (2021), 278–288. https://doi.org/10.1016/j.jss.2021.03.014 doi: 10.1016/j.jss.2021.03.014
[9]	C. F. Mickle, D. Deb, Early prediction of patient discharge disposition in acute neurological care using machine learning, BMC Health Serv. Res., 22 (2022), 1281. https://doi.org/10.1186/s12913-022-08615-w doi: 10.1186/s12913-022-08615-w
[10]	M. A. Abd-Elrazek, A. A. Eltahawi, M. H. Abd Elaziz, M. N. Abd-Elwhab, Predicting length of stay in hospitals intensive care unit using general admission features, Ain Shams Eng. J., 12 (2021), 3691–3702. https://doi.org/10.1016/j.asej.2021.02.018 doi: 10.1016/j.asej.2021.02.018
[11]	H. Zhong, B. Wang, D. Wang, Z. Liu, C. Xing, Y. Wu, et al., The application of machine learning algorithms in predicting the length of stay following femoral neck fracture, Int. J. Med. Inf., 155 (2021), 104572. https://doi.org/10.1016/j.ijmedinf.2021.104572 doi: 10.1016/j.ijmedinf.2021.104572
[12]	J. Liu, C. M. M. Lin, F. Chao, Gradient boost with convolution neural network for stock forecast, Proceedings of the Advances in Computational Intelligence Systems: Contributions Presented at the 19th UK Workshop on Computational Intelligence, Springer, 2020,155–165. https://doi.org/10.1007/978-3-030-29933-0_13
[13]	J. Friedman, T. Hastie, R. Tibshirani, Additive logistic regression: a statistical view of boosting (with discussion and a rejoinder by the authors), Ann. Stat., 28 (2000), 337–340. https://doi.org/10.1214/aos/1016218223 doi: 10.1214/aos/1016218223
[14]	M. Steinbach, P. N. Tan, kNN: k-nearest neighbors, The Top Ten Algorithms in Data Mining, 2009,151–162.
[15]	S. Dhanabal, S. Chandramathi, A review of various k-nearest neighbor query processing techniques, Int. J. Comput. Appl., 31 (2011), 14–22. https://doi.org/10.5120/3836-5332 doi: 10.5120/3836-5332
[16]	L. Breiman, Random forests, Mach. Learn., 45 (2001), 5–32. https://doi.org/10.1023/A:1010933404324 doi: 10.1023/A:1010933404324
[17]	T. K. Ho, Random decision forests, Proceedings of the 3rd International Conference on Document Analysis and Recognition, 1995,278–282. https://doi.org/10.1109/ICDAR.1995.598994 doi: 10.1109/ICDAR.1995.598994
[18]	A. Cutler, D. R. Cutler, J. R. Stevens, Random forests, In: C. Zhang, Y. Ma, Ensemble machine learning, Springer, 2012,157–175. http://doi.org/10.1007/978-1-4419-9326-7_5
[19]	Ö. Çokluk, Logistic regression: concept and application, Educ. Sci. Theory Pract., 10 (2010), 1397–1407.
[20]	A. Y. Ng, M. I. Jordan, On discriminative vs. generative classifiers: a comparison of logistic regression and naive bayes, Adv. Neural Inf. Process. Syst., 14 (2001), 841–848. https://doi.org/10.5555/2980539.2980648 doi: 10.5555/2980539.2980648
[21]	G. C. McDonald, Ridge regression, Wiley Interdiscip. Rev. Comput. Stat., 1 (2009), 93–100. https://doi.org/10.1002/wics.14 doi: 10.1002/wics.14
[22]	C. M. Bishop, M. E. Tipping, Bayesian regression and classification, Adv. Learn. Theory, 190 (2003), 267–288.
[23]	C. Cortes, V. Vapnik, Support-vector networks, Mach. Learn., 20 (1995), 273–297. https://doi.org/10.1007/BF00994018 doi: 10.1007/BF00994018
[24]	M. Awad, R. Khanna, Support vector machines for classification, Springer, 2015, 39–66. https://doi.org/10.1007/978-1-4302-5990-9_3
[25]	S. Ghosh, A. Dasgupta, A. Swetapadma, A study on support vector machine-based linear and non-linear pattern classification, 2019 International Conference on Intelligent Sustainable Systems (ICISS), 2019, 24–28. https://doi.org/10.1109/ISS1.2019.8908018 doi: 10.1109/ISS1.2019.8908018
[26]	A. Mansoori, M. Zeinalnezhad, L. Nazarimanesh, Optimization of tree-based machine learning models to predict the length of hospital stay using genetic algorithm, J. Healthcare Eng., 2023 (2023), 9673395. https://doi.org/10.1155/2023/9673395 doi: 10.1155/2023/9673395
[27]	M. M. Alam, An efficient random forest algorithm-based telemonitoring framework to predict mortality and length of stay of patients in ICU, Multimedia Tools Appl., 2023. https://doi.org/10.1007/s11042-023-17239-z
[28]	B. Eftekhar, K. Mohammad, H. E. Ardebili, M. Ghodsi, E. Ketabchi, Comparison of artificial neural network and logistic regression models for prediction of mortality in head trauma based on initial clinical data. BMC Med. Inf. Decis. Mak., 5 (2005), 3. https://doi.org/10.1186/1472-6947-5-3
[29]	K. Li, H. Wu, F. Pan, L. Chen, C. Feng, Y. Liu, et al., A machine learning-based model to predict acute traumatic coagulopathy in trauma patients upon emergency hospitalization, Clin. Appl. Thromb. Hemost., 26 (2020), 1076029619897827. https://doi.org/10.1177/1076029619897827 doi: 10.1177/1076029619897827
[30]	S. Lee, W. S. Kang, S. Seo, D. W. Kim, H. Ko, J. Kim, et al., Model for predicting in-hospital mortality of physical trauma patients using artificial intelligence techniques: nationwide population-based study in Korea, J. Med. Int. Res., 24 (2022), e43757. https://doi.org/10.2196/43757 doi: 10.2196/43757
[31]	S. D. Hsu, E. Chao, S. J. Chen, D. Y. Hueng, H. Y. Lan, H. H. Chiang, Machine learning algorithms to predict in-hospital mortality in patients with traumatic brain injury, J. Pers. Med., 11 (2021), 1144. https://doi.org/10.3390/jpm11111144 doi: 10.3390/jpm11111144
[32]	R. Wang, L. Wang, J. Zhang, M. He, J. Xu, XGBoost machine learning algorism performed better than regression models in predicting mortality of moderate-to-severe traumatic brain injury, World Neurosurg., 163 (2022), 617–622. https://doi.org/10.1016/j.wneu.2022.04.044 doi: 10.1016/j.wneu.2022.04.044
[33]	J. S. Kong, K. H. Lee, O. H. Kim, H. Y. Lee, C. Y. Kang, D. Choi, et al., Machine learning-based injury severity prediction of level 1 trauma center enrolled patients associated with car-to-car crashes in Korea, Comput. Biol. Med., 153 (2023), 106393. https://doi.org/10.1016/j.compbiomed.2022.106393 doi: 10.1016/j.compbiomed.2022.106393
[34]	C. S. Rau, S. C. Wu, J. F. Chuang, C. Y. Huang, H. T. Liu, P. C. Chien, et al., Machine learning models of survival prediction in trauma patients, J. Clin. Med., 8 (2019), 799. https://doi.org/10.3390/jcm8060799 doi: 10.3390/jcm8060799
[35]	I. H. Witten, E. Frank, M. A. Hall, C. J. Pal, Appendix B-the WEKA workbench, In: Data mining, 4 Eds., Morgan Kaufmann, 2017,553–571. https://doi.org/10.1016/B978-0-12-804291-5.00024-6
[36]	W. S. Hong, A. D. Haimovich, R. A. Taylor, Predicting hospital admission at emergency department triage using machine learning, PloS One, 13 (2018), 0201016. https://doi.org/10.1371/journal.pone.0201016 doi: 10.1371/journal.pone.0201016
[37]	A. K. Zalikha, T. Court, F. Nham, M. M. El-Othmani, R. P. Shah, Improved performance of machine learning models in predicting length of stay, discharge disposition, and inpatient mortality after total knee arthroplasty using patient-specific variables, Arthroplasty, 5 (2023), 31. https://doi.org/10.1186/s42836-023-00187-2

Reader Comments

Your name:*

Email:*
© 2024 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)