Skip to main content

Advertisement

SpringerLink
Log in

Intelligent injury prediction for traumatic airway obstruction

  • Original Article
  • Published:
Medical & Biological Engineering & Computing Aims and scope Submit manuscript

Abstract

Airway obstruction is one of the crucial causes of death in trauma patients during the first aid. It is extremely challenging to accurately treat a great deal of casualties with airway obstruction in hospitals. The diagnosis of airway obstruction in an emergency mostly relies on the medical experience of physicians. In this paper, we propose the feature selection approach genetic algorithm-mean decrease impurity (GA-MDI) to effectively minimize the number of features as well as ensure the accuracy of prediction. Furthermore, we design a multi-modal neural network, called fully convolutional network with squeeze-and-excitation and multilayer perceptron (FCN-SE + MLP), to help physicians to predict the severity of airway obstruction. We validate the effectiveness of the proposed feature selection approach and multi-modal model on the emergency medical database from the Chinese General Hospital of the PLA. The experimental results show that GA-MDI outperforms the existing feature selection algorithms, while it is also validated that the model FCN-SE + MLP can effectively and accurately achieve the prediction of the severity of airway obstruction, which can assist clinicians in making treatment decisions for airway obstruction casualties.

Graphical Abstract

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

Data availability

The data underlying this article cannot be shared publicly due to the privacy of the patients in the study. The data will be shared on reasonable request to the corresponding author.

References

  1. Petrucelli E, States JD, Hames Lee N (1981) The abbreviated injury scale: evolution, usage and future adaptability [J]. Accid Anal Prev 13(1):29–35

    Article  Google Scholar 

  2. Baker SP et al (1974) The injury severity score: a method for describing patients with multiple injuries and evaluating emergency care [J]. J Trauma 14(3):187–196

    Article  Google Scholar 

  3. Gilpin DA, Nelson PG (1991) Revised trauma score: a triage tool in the accident and emergency department [J]. Injury 22(1):35–37

    Article  Google Scholar 

  4. Boyd CR, Tolson MA, Copes WS (1987) Evaluating trauma care: the TRISS method [J]. J Trauma Inj Infect Crit Care 27(27):370–378

    Article  Google Scholar 

  5. Darras KE, Roston AT, Yewchuk LK (2015) Imaging acute airway obstruction in infants and children [J]. Radiographics 35(7):2064–2079

    Article  Google Scholar 

  6. Amaral JL, Lopes AJ, Faria AC, Melo PL (1995) Machine learning algorithms and forced oscillation measurements to categorize the airway obstruction severity in chronic obstructive pulmonary disease [J]. Comput Methods Programs Biomed 118(2):186–197

    Article  Google Scholar 

  7. Singer G, Ratnovsky A, Naftali S (2021) Classification of severity of trachea stenosis from EEG signals using ordinal decision-tree based algorithms and ensemble-based ordinal and non-ordinal algorithms [J]. Expert Syst Appl 173(114707):1–15

    Google Scholar 

  8. Jena OP, Bhushan B, Kose U (2022) Machine learning and deep learning in medical data analytics and healthcare applications [M]. CRC Press, pp 1–20

  9. Chai Hua et al (2021) Integrating multi-omics data through deep learning for accurate cancer prognosis prediction [J]. Comput Biol Med 134:1–8

  10. Zhang M, Flores KB, Tran HT (2021) Deep learning and regression approaches to forecasting blood glucose levels for type 1 diabetes [J]. Biomed Signal Process Control 69(102923):1–10

  11. Oudah M, Al-Naji A, Chahl J (2021) Computer vision for elderly care based on deep learning CNN and SVM [C]. IOP Conf Ser: Mater Sci Eng 1105(1):812–822

  12. Sato N et al (2021) Prediction and visualization of acute kidney injury in intensive care unit using one-dimensional convolutional neural networks based on routinely collected data [J]. Comput Methods Programs Biomed 206:1–8

  13. da Silva DB et al (2021) DeepSigns: a predictive model based on deep learning for the early detection of patient health deterioration [J]. Expert Syst Appl 165(113905):1–14

  14. Gao J, Li P, Chen Z, Zhang J (2020) A survey on deep learning for multimodal data fusion [J]. Neural Comput 32(5):829–864

    Article  Google Scholar 

  15. Vale Silva Luís A, Rohr K (2021) Long-term cancer survival prediction using multimodal deep learning [J]. Sci Rep 11(1):1–12

  16. Menegotto AB, Becker CD, Cazella SC (2021) Computer-aided diagnosis of hepatocellular carcinoma fusing imaging and structured health data [J]. Health Inf Sci Syst 9(1):20

    Article  Google Scholar 

  17. Venugopalan J et al (2021) Multimodal deep learning models for early detection of Alzheimer’s disease stage. Sci Rep 11(1):1–13

  18. Wang Z, Yan W, Oates T (2017) Time series classification from scratch with deep neural networks: a strong baseline [C]. Int Joint Conf Neural Netw (IJCNN) 3:1578–1585

  19. Jie H, Li S, Gang S et al (2020) Squeeze-and-excitation networks [J]. IEEE Trans Pattern Anal Mach Intell 42:2011–2023

    Article  Google Scholar 

  20. Freedman D, Pisani R, Purves R (2007) Statistics [M]. W. W. Norton & Company, pp 1–720

  21. Rahman MM, Davis DN (2012) Machine learning-based missing value imputation method for clinical datasets [C]. Int Conf Adv Eng Technol Phys Sci 1:245–257

  22. Breiman L (2001) Random forests [J]. Mach Learn 45(1):5–32

    Article  Google Scholar 

  23. Holland JH (1976) Adaptation in natural and artificial systems [J]. SIAM Rev 18(3):529–530

    Article  Google Scholar 

  24. Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift [C]. Int Conf Mach Learn 1:676–685

  25. Glorot X, Bordes A, Bengio Y (2011) Deep sparse rectifier neural networks [J]. J Mach Learn Res 15:315–323

    Google Scholar 

  26. Srivastava N, Hinton G, Krizhevsky A et al (2014) Dropout: a simple way to prevent neural networks from overfitting [J]. J Mach Learn Res 15(1):1929–1958

    Google Scholar 

  27. Lecun Y, Boser B, Denker J et al (1989) Backpropagation applied to handwritten zip code recognition [J]. Neural Comput 1(4):541–551

    Article  Google Scholar 

  28. Zaremba W, Sutskever I, Vinyals O (1990) Finding structure in time [J]. Cogn Sci 14(2):179–211

    Article  Google Scholar 

  29. Hochreiter S, Schmidhuber J (1997) Long short-term memory [J]. Neural Comput 9:1735–1780

    Article  Google Scholar 

  30. Cho K, Merrienboer BV, Gulcehre C et al (2014) Learning phrase representations using RNN encoder-decoder for statistical machine translation [C]. EMNLP 3:1724–1734

  31. Bai S, Kolter JZ, Koltun V (2018) An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. ArXiv preprint. https://arxiv.org/abs/1803.01271. Accessed 4 Mar 2018

  32. Sunde GA, Kottmann A, Heltne JK et al (2018) Standardised data reporting from pre-hospital advanced airway management: a nominal group technique update of the Utstein-style airway template [J]. Scand J Trauma Resuscitation Emerg Med 26(1):46

    Article  Google Scholar 

  33. Li K, Wu H, Pan F et al (2020) A machine learning based model to predict acute traumatic coagulopathy in trauma patients upon emergency hospitalization [J]. Clin Appl Thrombosis/Hemostasis 26:1–10

  34. Bernhard M, Sönke B et al (2019) Airway management in the emergency department: a prospective single center observational cohort study [J]. Scand J Trauma Resuscitation Emerg Med 27(1):20–28

  35. Hubble MW, Wilfong DA, Brown LH et al (2010) A meta-analysis of prehospital airway control techniques part II: alternative airway devices and cricothyrotomy success rates [J]. Prehosp Emerg Care 14(4):515–530

    Article  Google Scholar 

  36. Drges V, Wenzel V, Neubert E et al (2000) Emergency airway management by intensive care unit nurses with the intubating laryngeal mask airway and the laryngeal tube [J]. Crit Care 4(6):1–8

    Google Scholar 

  37. Higginson R, Parry A, Williams M (2016) Airway management in the hospital environment [J]. British Journal of Nursing 25(2):94

    Article  Google Scholar 

  38. Raatiniemi L et al (2013) Pre-hospital airway management by non-physicians in northern Finland: a cross-sectional survey [J]. Acta Anaesthesiol Scand 57(5):654–659

    Article  Google Scholar 

  39. Adams BD, Cuniowski PA, Muck A et al (2008) Registry of emergency airways arriving at combat hospitals [J]. J Trauma 64(6):1548

    Google Scholar 

  40. Schalk R, Meininger D, Ruesseler M et al (2011) Emergency airway management in trauma patients using laryngeal tube suction [J]. Prehosp Emerg Care 15(3):347–350

    Article  Google Scholar 

  41. Meng H, Zheng J, Zhang S (2012) Development of upper airway obstruction asphyxia model in beagle dogs with severe multiple injuries [C]. The Chinese 8th National Biomedical Stereology Academic Conference 1:184

  42. Kovacs G, Law A et al (2007) Airway management in emergencies [M]. McGraw Hill / Medical, pp 1–298

  43. Davis DP et al (2022) Optimizing physiology during prehospital airway management: an NAEMSP position statement and resource document [J]. Prehosp Emerg Care 26(Sup1):72–79

    Article  Google Scholar 

  44. An-Nuo L et al (2017) Correlation between posttraumatic growth and posttraumatic stress disorder symptoms based on Pearson correlation coefficient: a meta-analysis [J]. J Nerv Ment Dis 205(5):380–389

    Article  Google Scholar 

  45. Vaswani S et al (2017) Attention is all you need. In Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS) [C]. 6000–6010

  46. Che Z et al (2018) Recurrent neural networks for multivariate time series with missing values [J]. Sci Rep 8(1):581–592

    Article  Google Scholar 

Download references

Author information

Author notes

  1. Youfang Han, Fei Pan, and Hainan Song contributed equally to this work

Authors and Affiliations

  1. School of Software, Tsinghua University, Beijing, China

    Youfang Han, Ruihong Luo & Chunping Li

  2. Emergency Department, The First Medical Center of PLA General Hospital, Beijing, China

    Fei Pan, Hainan Song & Tanshi Li

  3. Nursing Department, PLA General Hospital, Beijing, China

    Hongying Pi & Jianrong Wang

Authors
  1. Youfang Han
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Fei Pan
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hainan Song
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ruihong Luo
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Chunping Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Hongying Pi
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Jianrong Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Tanshi Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Youfang Han designed the algorithms and implemented the predictive model and experiment. Fei Pan and Hainan Song designed the experiments and provided the clinical expertise and context. Ruihong Luo pre-processed the data and analyzed the data. Chunping Li and Tanshi Li supervised the experiment and revised the paper. Hongying Pi and Jianrong Wang provided relevant knowledge of airway obstruction nursing and datasets for experiment.

Corresponding authors

Correspondence to Chunping Li, Hongying Pi or Jianrong Wang.

Ethics declarations

Ethics approval and consent to participate

The use of relevant de-identified data from the trauma database has been reviewed by the Medical Ethics Committee of the PLA General Hospital; the ethical batch number is 2021–540 and written informed consent was waived due to the study design and the harmless use of retrospective data.

Competing interests

The authors declare no competing interests.

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.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Han, Y., Pan, F., Song, H. et al. Intelligent injury prediction for traumatic airway obstruction. Med Biol Eng Comput 61, 139–153 (2023). https://doi.org/10.1007/s11517-022-02706-w

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11517-022-02706-w

Keywords

Search

Navigation