Abstract
War trauma data, a core element of military research, have been attracting significant attention from several countries, despite limited availability. In this study, we propose a data augmentation method for war trauma that combines a trauma scoring system and deep learning to generate large-scale and effective synthetic data. First, the Abbreviated War Trauma Scale (AWTS), including the trauma scoring table and the vital signs scoring table, was developed by collecting information on battlefield environment injuries. Second, a new war trauma severity scoring (NWTSS) equation evaluating injury severity was proposed using multiple linear regression analysis on manually labelled synthetic samples. Then, based on the AWTS and NWTSS, we formulated a synthetic algorithm for generating large-scale automatically labelled cases. Finally, to verify the effectiveness of the synthetic data, we trained deep-learning classifiers with these data and tested them using real data. The experimental results show that the classifiers performed best when the size of the synthetic data scale was around 50,000. Furthermore, the text classification model designed in this study for war trauma data achieved 85.59% accuracy, outperforming the current popular text classifiers, indicating that the synthetic data effectively reflected the real situation.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Data availability
Availability of data and materials Enquiries about data availability should be directed to the corresponding author.
References
Almaghrabi F, Xu DL, Yang JB (2019) A new machine learning technique for predicting traumatic injuries outcomes based on the vital signs. In: 2019 25th International Conference on Automation and Computing (ICAC), IEEE, pp 1–5, https://doi.org/10.23919/IConAC.2019.8895012
Amodeo M, Abbate V, Arpaia P et al (2021) Transfer learning for an automated detection system of fractures in patients with maxillofacial trauma. Appl Sci. https://doi.org/10.3390/app11146293
Antoniou A, Storkey A, Edwards H (2017) Data augmentation generative adversarial networks. arXiv preprint arXiv:1711.04340https://doi.org/10.48550/arXiv.1711.04340
Bohannon J (2011) War as a laboratory for trauma research. Science 331(6022):1261–1263. https://doi.org/10.1126/science.331.6022.1261
Bruschetta R, Tartarisco G, Lucca LF et al (2022) Predicting outcome of traumatic brain injury: Is machine learning the best way? Biomedicines. https://doi.org/10.3390/biomedicines10030686
Camino R, Hammerschmidt C, State R (2018) Generating multi-categorical samples with generative adversarial networks. arXiv preprint arXiv:1807.01202https://doi.org/10.48550/arXiv.1807.01202
Clark K, Luong MT, Le QV, et al (2020) Electra: Pre-training text encoders as discriminators rather than generators. arXiv preprint arXiv:2003.10555https://doi.org/10.48550/arXiv.2003.10555
Devlin J, Chang MW, Lee K, et al (2018) Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805https://doi.org/10.48550/arXiv.1810.04805
Dube K, Gallagher T (2014) Approach and method for generating realistic synthetic electronic healthcare records for secondary use. In: Gibbons J, MacCaull W (eds) Foundations of Health Information Engineering and Systems. Springer Berlin Heidelberg, Berlin, Heidelberg, pp 69–86, https://doi.org/10.1007/978-3-642-53956-5_6
Esteva A, Chou K, Yeung S et al (2021) Deep learning-enabled medical computer vision. NPJ digital medicine 4(1):5. https://doi.org/10.1038/s41746-020-00376-2
Farda NA, Lai JY, Wang JC et al (2021) Sanders classification of calcaneal fractures in ct images with deep learning and differential data augmentation techniques. Injury 52(3):616–624. https://doi.org/10.1016/j.injury.2020.09.010
Frid-Adar M, Klang E, Amitai M, et al (2018) Synthetic data augmentation using gan for improved liver lesion classification. In: 2018 IEEE 15th international symposium on biomedical imaging (ISBI 2018), IEEE, pp 289–293, https://doi.org/10.1109/ISBI.2018.8363576
Gao Z, Feng A, Song X et al (2019) Target-dependent sentiment classification with bert. Ieee Access 7:154290–154299. https://doi.org/10.1109/ACCESS.2019.2946594
González-Carvajal S, Garrido-Merchán EC (2020) Comparing bert against traditional machine learning text classification. arXiv:2005.13012. https://doi.org/10.48550/arXiv.2005.13012
Howard JT, Stewart IJ, Amuan M et al (2022) Association of Traumatic Brain Injury With Mortality Among Military Veterans Serving After September 11, 2001. JAMA Netw Open. https://doi.org/10.1001/jamanetworkopen.2021.48150
Hsu SY, Wu SC, Rau CS et al (2019) Impact of adapting the abbreviated injury scale (ais)-2005 from ais-1998 on injury severity scores and clinical outcome. Int J Environ Res Public Health. https://doi.org/10.3390/ijerph16245033
Javali RH, Patil A, Srinivasarangan M et al (2019) Comparison of injury severity score, new injury severity score, revised trauma score and trauma and injury severity score for mortality prediction in elderly trauma patients. Indian journal of critical care medicine: peer-reviewed, official publication of Indian Society of Critical Care Medicine 23(2):73. https://doi.org/10.5005/jp-journals-10071-23120
Jeong JH, Park YJ, Kim DH et al (2017) The new trauma score (nts): a modification of the revised trauma score for better trauma mortality prediction. BMC Surg 17:1–9. https://doi.org/10.1186/s12893-017-0272-4
Kang T, Perotte A, Tang Y et al (2020) UMLS-based data augmentation for natural language processing of clinical research literature. J Am Med Inform Assoc 28(4):812–823. https://doi.org/10.1093/jamia/ocaa309
Kathryn L, Loftis JP, Gillich PJ (2018) Evolution of the abbreviated injury scale: 1990–2015. Traffic Inj Prev 19(sup2):S109–S113. https://doi.org/10.1080/15389588.2018.1512747
Kato C, Uemura O, Sato Y et al (2023) Functional outcome prediction after spinal cord injury using ensemble machine learning. Arch Phys Med Rehabil. https://doi.org/10.1016/j.apmr.2023.08.011
Kim SK (2017) Third-party intervention in civil wars and the prospects for postwar development. J Conflict Resolut 61(3):615–642. https://doi.org/10.1177/0022002715590873
Kim Y (2014) Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882https://doi.org/10.48550/arXiv.1408.5882
Kingma DP, Ba J (2014) Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980https://doi.org/10.48550/arXiv.1412.6980
Kobayashi S (2018) Contextual augmentation: Data augmentation by words with paradigmatic relations. arXiv preprint arXiv:1805.06201https://doi.org/10.48550/arXiv.1805.06201
Lai S, Xu L, Liu K, et al (2015) Recurrent convolutional neural networks for text classification. In: Proceedings of the AAAI conference on artificial intelligence, https://doi.org/10.1609/aaai.v29i1.9513
Lan Z, Chen M, Goodman S, et al (2019) Albert: A lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942https://doi.org/10.48550/arXiv.1909.11942
Lauriola I, Lavelli A, Aiolli F (2022) An introduction to deep learning in natural language processing: Models, techniques, and tools. Neurocomputing 470:443–456. https://doi.org/10.1016/j.neucom.2021.05.103
Lefering R (2012) Trauma scoring systems. Curr Opin Crit Care 18(6):637–640. https://doi.org/10.1097/MCC.0b013e3283585356
Li H, Ma YF (2021) New injury severity score (niss) outperforms injury severity score (iss) in the evaluation of severe blunt trauma patients. Chin J Traumatol 24(05):261–265. https://doi.org/10.1016/j.cjtee.2021.01.006
Li S, Ao X, Pan F et al (2022) Learning policy scheduling for text augmentation. Neural Netw 145:121–127. https://doi.org/10.1016/j.neunet.2021.09.028
Liu Y, Ott M, Goyal N, et al (2019) Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692https://doi.org/10.48550/arXiv.1907.11692
Luo Y, Zhu LZ, Wan ZY et al (2020) Data augmentation for enhancing eeg-based emotion recognition with deep generative models. J Neural Eng 17(5):056021. https://doi.org/10.1088/1741-2552/abb580
McIntyre J (2020) Syrian civil war: a systematic review of trauma casualty epidemiology. BMJ Mil Health 166(4):261–265. https://doi.org/10.1136/jramc-2019-001304
Phipps H, Mondello S, Wilson A, et al (2020) Characteristics and impact of u.s. military blast-related mild traumatic brain injury: A systematic review. Frontiers in Neurology https://doi.org/10.3389/fneur.2020.559318
Rau CS, Wu SC, Chuang JF et al (2019) Machine learning models of survival prediction in trauma patients. J Clin Med 8(6):799. https://doi.org/10.3390/jcm8060799
Saldanha J, Chakraborty S, Patil S et al (2022) Data augmentation using variational autoencoders for improvement of respiratory disease classification. PLoS ONE. https://doi.org/10.1371/journal.pone.0266467
Sankaranarayanan S, Balaji Y, Jain A, et al (2018) Learning from synthetic data: Addressing domain shift for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3752–3761
Subramanian AS, Weng C, Watanabe S et al (2022) Deep learning based multi-source localization with source splitting and its effectiveness in multi-talker speech recognition. Computer Speech & Language 75:101360. https://doi.org/10.1016/j.csl.2022.101360
Sugiyama A, Yoshinaga N (2019) Data augmentation using back-translation for context-aware neural machine translation. In: Proceedings of the Fourth Workshop on Discourse in Machine Translation (DiscoMT 2019). Association for Computational Linguistics, Hong Kong, China, pp 35–44, https://doi.org/10.18653/v1/D19-6504
Tabakan I, Eser C, Gencel E et al (2021) Reconstruction of firearm and blast injuries in syrian war refugees. Int J Clin Pract. https://doi.org/10.1111/ijcp.13995
Theodoraki EM, Koukouvinos C, Parpoula C (2010) Neural networks for prediction of trauma victims’ outcome. comparison with the triss and revised trauma score. In: Proceedings of the 10th IEEE International Conference on Information Technology and Applications in Biomedicine, IEEE, pp 1–4, https://doi.org/10.1109/ITAB.2010.5687802
Tremblay J, Prakash A, Acuna D, et al (2018) Training deep networks with synthetic data: Bridging the reality gap by domain randomization. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 969–977
Umer M, Sadiq S, Missen MMS et al (2021) Scientific papers citation analysis using textual features and smote resampling techniques. Pattern Recogn Lett 150:250–257. https://doi.org/10.1016/j.patrec.2021.07.009
Van Ditshuizen JC, Sewalt CA, Palmer CS et al (2021) The definition of major trauma using different revisions of the abbreviated injury scale. Scandinavian journal of trauma, resuscitation and emergency medicine 29(1):1–10. https://doi.org/10.1186/s13049-021-00873-7
Vaswani A, Shazeer N, Parmar N, et al (2017) Attention is all you need. In: Advances in Neural Information Processing Systems, https://proceedings.neurips.cc/paper_files/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf
Walonoski J, Kramer M, Nichols J et al (2018) Synthea: An approach, method, and software mechanism for generating synthetic patients and the synthetic electronic health care record. J Am Med Inform Assoc 25(3):230–238. https://doi.org/10.1093/jamia/ocx147
Wei J, Zou K (2019) Eda: Easy data augmentation techniques for boosting performance on text classification tasks. arXiv preprint arXiv:1901.11196https://doi.org/10.48550/arXiv.1901.11196
Wei N, Zhao S, Liu J et al (2022) A novel textual data augmentation method for identifying comparative text from user-generated content. Electron Commer Res Appl 53:101143. https://doi.org/10.1016/j.elerap.2022.101143
Xie Z, Wang SI, Li J, et al (2017) Data noising as smoothing in neural network language models. arXiv preprint arXiv:1703.02573https://doi.org/10.48550/arXiv.1703.02573
Yin J, Zhao P, Zhang Y et al (2021) A data augmentation method for war trauma using the war trauma severity score and deep neural networks. Electronics 10(21):2657. https://doi.org/10.3390/electronics10212657
Yu S, Yang J, Liu D et al (2019) Hierarchical data augmentation and the application in text classification. IEEE Access 7:185476–185485. https://doi.org/10.1109/ACCESS.2019.2960263
Zhang J, Cormode G, Procopiuc CM et al (2017) Privbayes: Private data release via bayesian networks. ACM Transactions on Database Systems (TODS) 42(4):1–41. https://doi.org/10.1145/3134428
Zhang Z (2018) Improved adam optimizer for deep neural networks. In: 2018 IEEE/ACM 26th international symposium on quality of service (IWQoS), Ieee, pp 1–2, https://doi.org/10.1109/IWQoS.2018.8624183
Funding
This study was funded by the National Natural Science (grant number 61741206). This work was supported by the National Natural Science Fund, sponsor: Jibin Yin, funding number: 61741206.
Author information
Authors and Affiliations
Contributions
G.L. conceived the presented idea and verified the analytical methods. J.Y. provided the experimental environment, supervised and validated the findings of this work. Y.Z. provided the research topic, medical theoretical and technical support. Writing, editing, and formatting the manuscript was carried out by G.L. with support from Y.Z. and P.S. Funding acquisition was carried out by S.G. All authors have read and agreed to the published version of the manuscript.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Ethical approval
This article does not contain any studies with human participants performed by any of the authors.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Yin, J., Liao, G., Zhang, Y. et al. A data augmentation method for war trauma based on the regression model and deep neural networks. Soft Comput 28, 13527–13540 (2024). https://doi.org/10.1007/s00500-024-10317-w
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-024-10317-w