USING MACHINE LEARNING TO DEVELOP A RISK PREDICTION MODEL FOR ACUTE MOUNTAIN SICKNESS
DOI:
https://doi.org/10.17501/24246735.2023.8106Keywords:
Acute Mountain Sickness, machine learning, prediction model, workersAbstract
Background: Acute Mountain Sickness (AMS) is a syndrome caused by individuals who are unacclimatized at high altitudes, AMS can threaten health and decrease productivity. By predicting AMS risk, workers can take measures in advance to prevent AMS. The main objective of this study was to use machine learning techniques to develop an AMS risk prediction model. Methods: A retrospective cohort study was conducted to capture AMS monitor data for State Grid workers in the Tibet-Ali project from 1 January 2019 to 31 December 2020. The data was assigned to the training and test sets in 7:3. 10-fold cross-validation was used to improve generalization abilities. Four models including Random Forest (RF) were developed and compared. Area Under the Curve (AUC) and accuracy were used to measure the performance of models. Results: The cohort consisted of 10956 workers, 10438 (95.27%) were male, and the mean age was 36.13 ± 10.49 years. The AMS incidence was 15.58% (n = 1707). The RF model was superior to others in predicting AMS risk. In the test set, the accuracy was 80.32%. After parameter optimization of all models, the RF model still outperformed others, with the best AUC and accuracy were 0.76 and 78.12% ± 7.21%, respectively. Twelve features including demographics, clinical, and altitude were included in the RF model. Conclusions: This study aimed to develop a machine learning-based model for predicting AMS risk among workers at high altitudes. The RF model was found to be the best performer among the four models, based on 12 features known before workers entered plateaus. This model can be an effective tool for estimating AMS risk and guiding decisions regarding AMS primary prevention.
Downloads
References
Afrash, M. R., Shafiee, M., & Kazemi-Arpanahi, H. (2023). Establishing machine learning models to predict the early risk of gastric cancer based on lifestyle factors. BMC Gastroenterol, 23(1), 6. doi:10.1186/s12876-022-02626-x
Ahluwalia, A., & Underwood, P. J. (2022). Acute Mountain Sickness Score: StatPearls Publishing, Treasure Island (FL).
Beidleman, B. A., Fulco, C. S., Muza, S. R., Rock, P. B., Staab, J. E., Forte, V. A., . . . Cymerman, A. (2009). Effect of six days of staging on physiologic adjustments and acute mountain sickness during ascent to 4300 meters. High Alt Med Biol, 10(3), 253-260. doi:10.1089/ham.2009.1004
Boos, C. J., Bass, M., O'Hara, J. P., Vincent, E., Mellor, A., Sevier, L., . . . Woods, D. R. (2018). The relationship between anxiety and acute mountain sickness. PLoS One, 13(6), e0197147. doi:10.1371/journal.pone.0197147
Cawley, G. C., & Talbot, N. L. (2010). On over-fitting in model selection and subsequent selection bias in performance evaluation. The Journal of Machine Learning Research, 11, 2079-2107.
Clarke, C. (2006). Acute mountain sickness: medical problems associated with acute and subacute exposure to hypobaric hypoxia. Postgrad Med J, 82(973), 748-753. doi:10.1136/pgmj.2006.047662
Delen, D., Walker, G., & Kadam, A. (2005). Predicting breast cancer survivability: a comparison of three data mining methods. Artif Intell Med, 34(2), 113-127. doi:10.1016/j.artmed.2004.07.002
Garrido, E., Botella de Maglia, J., & Castillo, O. (2021). Acute, subacute and chronic mountain sickness. Rev Clin Esp (Barc), 221(8), 481-490. doi:10.1016/j.rceng.2019.12.009
Habehh, H., & Gohel, S. (2021). Machine Learning in Healthcare. Curr Genomics, 22(4), 291-300. doi:10.2174/1389202922666210705124359
Imray, C., Wright, A., Subudhi, A., & Roach, R. (2010). Acute mountain sickness: pathophysiology, prevention, and treatment. Prog Cardiovasc Dis, 52(6), 467-484. doi:10.1016/j.pcad.2010.02.003
Jin, J. (2017). Acute Mountain Sickness. JAMA, 318(18), 1840-1840. doi:10.1001/jama.2017.16077
Li, Y., Zhang, Y., & Zhang, Y. (2018). Research advances in pathogenesis and prophylactic measures of acute high altitude illness. Respir Med, 145, 145-152. doi:10.1016/j.rmed.2018.11.004
Luks, A. M., Swenson, E. R., & Bärtsch, P. (2017). Acute high-altitude sickness. Eur Respir Rev, 26(143). doi:10.1183/16000617.0096-2016
Luo, Y., Yang, X., & Gao, Y. (2013). Strategies for the prevention of acute mountain sickness and treatment for large groups making a rapid ascent in China. Int J Cardiol, 169(2), 97-100. doi:10.1016/j.ijcard.2013.08.059
Mei, S., & Montanari, A. (2022). The generalization error of random features regression: Precise asymptotics and the double descent curve. Communications on Pure and Applied Mathematics, 75(4), 667-766.
Meier, D., Collet, T. H., Locatelli, I., Cornuz, J., Kayser, B., Simel, D. L., & Sartori, C. (2017). Does This Patient Have Acute Mountain Sickness?: The Rational Clinical Examination Systematic Review. JAMA, 318(18), 1810-1819. doi:10.1001/jama.2017.16192
Ried, L. D., Carter, K. A., & Ellsworth, A. (1994). Acetazolamide or dexamethasone for prevention of acute mountain sickness: a meta-analysis. Journal of Wilderness Medicine, 5(1), 34-48.
Roach, R. C., Hackett, P. H., Oelz, O., Bärtsch, P., Luks, A. M., MacInnis, M. J., & Baillie, J. K. (2018). The 2018 Lake Louise Acute Mountain Sickness Score. High Alt Med Biol, 19(1), 4-6. doi:10.1089/ham.2017.0164
Uddin, S., Khan, A., Hossain, M. E., & Moni, M. A. (2019). Comparing different supervised machine learning algorithms for disease prediction. BMC Med Inform Decis Mak, 19(1), 281. doi:10.1186/s12911-019-1004-8
Vinnikov, D., Brimkulov, N., & Blanc, P. D. (2015). Smoking increases the risk of acute mountain sickness. Wilderness Environ Med, 26(2), 164-172. doi:10.1016/j.wem.2014.10.006
Wang, D., Li, J., Sun, Y., Ding, X., Zhang, X., Liu, S., . . . Sun, T. (2021). A Machine Learning Model for Accurate Prediction of Sepsis in ICU Patients. Front Public Health, 9, 754348. doi:10.3389/fpubh.2021.754348
Wei, C. Y., Chen, P. N., Lin, S. S., Huang, T. W., Sun, L. C., Tseng, C. W., & Lin, K. F. (2022). Using machine learning to determine the correlation between physiological and environmental parameters and the induction of acute mountain sickness. BMC Bioinformatics, 22(Suppl 5), 628. doi:10.1186/s12859-022-04749-0
Wu, T. Y., Ding, S. Q., Liu, J. L., Jia, J. H., Chai, Z. C., & Dai, R. C. (2012). Who are more at risk for acute mountain sickness: a prospective study in Qinghai-Tibet railroad construction workers on Mt. Tanggula. Chin Med J (Engl), 125(8), 1393-1400.
Wu, T. Y., Ding, S. Q., Liu, J. L., Yu, M. T., Jia, J. H., Chai, Z. C., . . . Kayser, B. (2007). Who should not go high: chronic disease and work at altitude during construction of the Qinghai-Tibet railroad. High Alt Med Biol, 8(2), 88-107. doi:10.1089/ham.2007.1015
Yang, M., Wu, Y., Yang, X. B., Liu, T., Zhang, Y., Zhuo, Y., . . . Zhang, N. (2023). Establishing a prediction model of severe acute mountain sickness using machine learning of support vector machine recursive feature elimination. Sci Rep, 13(1), 4633. doi:10.1038/s41598-023-31797-0
Zhang, S. L. (2010). [Interpretation on diagnostic criteria of occupational high altitude disease 2008 edition]. Zhonghua Lao Dong Wei Sheng Zhi Ye Bing Za Zhi, 28(12), 950-951.
Zhou, C., Hu, J., Wang, Y., Ji, M. H., Tong, J., Yang, J. J., & Xia, H. (2021). A machine learning-based predictor for the identification of the recurrence of patients with gastric cancer after operation. Sci Rep, 11(1), 1571. doi:10.1038/s41598-021-81188-6
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 Ranyi Ding, Ping Liu, Quanquan Gong
This work is licensed under a Creative Commons Attribution 4.0 International License.
The Conference Proceedings of International Conference on Public Health is entirely Open Access, which means that all published content is freely available without charge to the user or his/her institution. Users are allowed to read, download, copy, distribute, print, search, or link to the full texts of the articles in this Proceedings journal without asking prior permission from the publisher or the author. This is in accordance with the BOAI definition of open access.
Authors who publish with Conference Proceedings agree to the following terms:
- Authors retain copyright and grant the Proceedings of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this conference proceedings.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the proceeding's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this conference proceedings.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
Licensing
Published articles are licensed under a Creative Commons Attribution 4.0 International License.
