Detection of difficult airway using deep learning

A Correction to this article is available

This article has been updated

Abstract

Whenever a patient needs to enter the operating room, in case the surgery requires general anesthesia, he/she must be intubated, and an anesthesiologist has to make a previous check to the patient in order to evaluate his/her airway. This process should be done to the patient to anticipate any problem, such as a difficult airway at the time of being anesthetized. In fact, the inadequate detection of a difficult airway can cause serious complications, even death. This research work proposes a mobile app that uses a convolutional neural network to detect a difficult airway. This model classifies two classes of the Mallampati score, namely Mallampati 1–2 (with low risk of difficult airway) and Mallampati 3–4 (with higher risk of difficult airway). The average accuracy of the predictive model is 88.5% for classifying pictures. A total of 240 pictures were used for training the model. The results of sensitivity and specificity were 90% in average.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Change history

  • 27 February 2020

    The articles listed below were published in Issue January 2020, Issue 1, instead of Issue February 2020, Issues 1–2.

Notes

  1. 1.

    https://www.tensorflow.org.

  2. 2.

    https://www.anaconda.com/distribution/#download-section.

  3. 3.

    http://bit.ly/tensorflow-retrain.

  4. 4.

    https://developer.android.com/studio#downloads.

  5. 5.

    http://bit.ly/tensorflow-android-demo.

References

  1. 1.

    Apfelbaum, J.L., Hagberg, C.A., Caplan, R.A., Blitt, C.D., Connis, R.T., Nickinovich, D.G., Hagberg, C.A., Caplan, R.A., Benumof, J.L., Berry, F.A., Blitt, C.D., Bode, R.H., Cheney, F.W., Connis, R.T., Guidry, O.F., Nickinovich, D.G., Ovassapian, A.: Practice guidelines for management of the difficult airway. Anesthesiology 118(2), 251–270 (2013)

    Article  Google Scholar 

  2. 2.

    García, B.: Valoración preoperatoria de la vía aérea difícil “hay algo nuevo? https://anestesiar.org/2015/valoracion-preoperatoria-de-la-via-aerea-dificil-hay-algo-nuevo/ (2015). Accessed 11 May 2018

  3. 3.

    Baker, P.: Assessment before airway management. Anesthesiol. Clin. 33(2), 257–278 (2015)

    Article  Google Scholar 

  4. 4.

    Khandekar, R., Diwan, R., Shah, A., Patel, B.: Validation of modified Mallampati test with addition of thyromental distance and sternomental distance to predict difficult endotracheal intubation in adults. Indian J. Anaesth. 58(2), 171 (2014)

    Article  Google Scholar 

  5. 5.

    Bair, A .E., Caravelli, R., Tyler, K., Laurin, E .G.: Feasibility of the preoperative mallampati airway assessment in emergency department patients. J. Emerg. Med. 38(5), 677–680 (2010)

    Article  Google Scholar 

  6. 6.

    Campos, J.: Guías, algoritmos y recomendaciones durante el manejo de la vía aérea difícil en el paciente sometido a cirugía torácica: ¿están respaldados por la evidencia cientifica? Rev. Esp. Anestesiol. Reanim. 65(1), 1–4 (2018)

    Article  Google Scholar 

  7. 7.

    Kovacs, G.: Airway Management in Emergencies. McGraw-Hill Education, New York (2011)

    Google Scholar 

  8. 8.

    Rubio-Martínez, R., Espino-Núñez, S., Espinoza-Tadeo, A., Romero-Guillén, P., Medina-Pérez, M.E., Coronado-Ávila, S.: Sesgos cognitivos en anestesia, una causa latente de error humano. Rev. Mex. Anestesiol. 42(2), 118–121 (2019)

    Google Scholar 

  9. 9.

    Gómez-Ríos, M., Gaitini, L., Matter, I., Somri, M.: Guías y algoritmos para el manejo de la vía aérea difícil. Rev. Esp. Anestesiol. Reanim. 65(1), 41–48 (2018)

    Article  Google Scholar 

  10. 10.

    Cook, T., Woodall, N., Frerk, C.: Major complications of airway management in the UK: results of the Fourth National Audit Project of the Royal College of Anaesthetists and the Difficult Airway Society. Part 1: anaesthesia. Br. J. Anaesth. 106(5), 617–631 (2011)

    Article  Google Scholar 

  11. 11.

    Marín, C., Alférez, G.H., Córdova, J., González, V.: Detection of melanoma through image recognition and artificial neural networks. In: IFMBE Proceedings. Springer International Publishing, Cham, pp. 832–835 (2015)

  12. 12.

    Espinoza, M., Alférez, G.H., Castillo, J.: Prediction of glaucoma through convolutional neural networks. In: Proceedings of the 2018 International Conference on Health Informatics and Medical Systems, pp. 90–95 (2018)

  13. 13.

    Alférez, G.H., Jiménez, J., Hernández-Navarro, H., González, M., Domínguez, R., Briones, A., Hernández-Villalvazo, H.: Application of data science to discover the relationship between dental caries and diabetes in dental records. In: Arabnia, H.R., Deligiannidis, L. (eds.) International Conference on Health Informatics and Medical Systems (HIMS 2016). CSREA Press, pp. 176–181 (2016)

  14. 14.

    Shanahan, E., Huang, J.H.-C., Chen, A., Narsimhan, A., Tang, R.: Difficultintubationapp.com—a difficult airway electronic record. Can. J. Anesth. 63(11), 1299–1300 (2016)

    Article  Google Scholar 

  15. 15.

    Duggan, L.V., Lockhart, S.L., Cook, T.M., O’Sullivan, E.P., Dare, T., Baker, P.A.: The airway app: exploring the role of smartphone technology to capture emergency front-of-neck airway experiences internationally. Anaesthesia 73(6), 703–710 (2018)

    Article  Google Scholar 

  16. 16.

    Law, J.A.: From the journal archives: Mallampati in two millennia—its impact then and implications now. Can. J. Anesth. 61(5), 480–484 (2014)

    Article  Google Scholar 

  17. 17.

    Green, S.M., Roback, M.G.: Is the mallampati score useful for emergency department airway management or procedural sedation? Ann. Emerg. Med. 74(2), 251–259 (2019)

    Article  Google Scholar 

  18. 18.

    Adamus, M., Fritscherova, S., Hrabalek, L., Gabrhelik, T., Zapletalova, J., Janout, V.: Mallampati test as a predictor of laryngoscopic view. Biomed. Pap. Med. Fac. Univ. Palacky Olomouc Czechoslov. 154, 339–343 (2010)

    Article  Google Scholar 

  19. 19.

    Lee, A., Fan, L.T.Y., Gin, T., Karmakar, M.K., Ngan Kee, W.D.: A systematic review (meta-analysis) of the accuracy of the Mallampati tests to predict the difficult airway. Anesth. Analg. 102, 1867–1878 (2006)

    Article  Google Scholar 

  20. 20.

    Rodríguez, A.M., Pascual, J.N., Ferrer, L.P., Domínguez, J.F., Chaves, J.B., González, E.M.: Validez de los predictores de vía aérea difícil en medicina extrahospitalaria. An. Sist. Sanit. Navar. 37(1), 91–98 (2014)

    Article  Google Scholar 

  21. 21.

    García, E.R., Cedeño, J.R.: Valor predictivo de las evaluaciones de la vía aérea difícil. Trauma 8(3), 63–70 (2005)

    Google Scholar 

  22. 22.

    Géron, A.: Hands-On Machine Learning with Scikit-Learn and TensorFlow. O’Reilly UK Ltd., Farnham (2017)

    Google Scholar 

  23. 23.

    Michalski, R.S., Carbonell, J.G., Mitchell, T.M. (eds.): Machine Learning. Springer, Berlin (1983)

    Google Scholar 

  24. 24.

    Kim, K.G.: Book review: Deep learning. Healthc. Inform. Res. 22(4), 351 (2016)

    Article  Google Scholar 

  25. 25.

    Saha, S.: A comprehensive guide to convolutional neural networks—the ELI5 way. https://bit.ly/2JyfxpT (2018). Accessed 14 Mar 2019

  26. 26.

    Zerium, A.: Demystifying convolutional neural networks. https://medium.com/@eternalzer0dayx/demystifying-convolutional-neural-networks-ca17bdc75559 (2018). Accessed 16 Sept 2018

  27. 27.

    Google, Tensors. https://www.tensorflow.org/guide/tensors. Accessed 14 Mar 2019

  28. 28.

    Howard, A.G., Zhu, M.: Mobilenets: open-source models for efficient on-device vision. https://ai.googleblog.com/2017/06/mobilenets-open-source-models-for.html (2017). Accessed 16 Sept 2018

  29. 29.

    Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.-C.: Mobilenetv2: inverted residuals and linear bottlenecks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June (2018)

  30. 30.

    Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., Adam, H.: Mobilenets: efficient convolutional neural networks for mobile vision applications (2017). arXiv:1704.04861

  31. 31.

    Sandler, M., Howard, A.: Mobilenetv2: the next generation of on-device computer vision networks. https://ai.googleblog.com/2018/04/mobilenetv2-next-generation-of-on.htmlnetv2-next-generation-of-on.html (2018). Accessed 14 Mar 2019

  32. 32.

    Pröve, P.-L.: Mobilenetv2: inverted residuals and linear bottlenecks. https://towardsdatascience.com/mobilenetv2-inverted-residuals-and-linear-bottlenecks-8a4362f4ffd5 (2018). Accessed 14 Mar 2019

  33. 33.

    Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June (2016)

  34. 34.

    Greenfield, Y.: Precision, recall, sensitivity and specificity. http://yuvalg.com/blog/2012/01/01/precision-recall-sensitivity-and-specificity/ (2012). Accessed 21 Mar 2019

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Germán H. Alférez.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Aguilar, K., Alférez, G.H. & Aguilar, C. Detection of difficult airway using deep learning. Machine Vision and Applications 31, 4 (2020). https://doi.org/10.1007/s00138-019-01055-3

Download citation

Keywords

  • Difficult airway
  • Deep learning
  • Convolutional neural networks