Advertisement

A Machine Learning Approach for Colles’ Fracture Treatment Diagnosis

Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 1248)

Abstract

Wrist fractures (e.g. Colles’ fracture) are the most common injuries in the upper extremity treated in Emergency Departments. Treatment for most patients is an intervention called Manipulation under Anaesthesia (MUA). Surgical treatment would be needed for complex fractures or if the wrist stability is not restored. In addition, an unsuccessful treatment via MUA may also require subsequent surgical operation causing inefficiency in constrained medical resources and patients’ inconvenience. Previous geometric measurements in X-ray images [21] were found to provide statistical differences between healthy controls and patients with fractures, as well as pre- and post-intervention images. The most discriminating measurements were associated with the texture analysis of the radial bone. This work presents further analysis of these measurements and applying them as features to identify an appropriate machine learning model for Colles’ fracture treatment diagnosis. Random forest was evaluated to be the best model based on classification accuracy among the selected models commonly used in similar research. The non-linearity of the measurement features has attributed to the superior performance of an ensembled tree-based model. It is also interesting that the most important features (i.e. texture and swelling) required in the optimised random forest model are consistent with previous findings [21].

Keywords

Fracture Radiography Feature analysis Random forest 

References

  1. 1.
    Arora, R., Gabl, M., Gschwentner, M., Deml, C., Krappinger, D., Lutz, M.: A comparative study of clinical and radiologic outcomes of unstable colles type distal radius fractures in patients older than 70 years: nonoperative treatment versus volar locking plating. J. Orthop. Trauma 23(4), 237–242 (2009).  https://doi.org/10.1097/BOT.0b013e31819b24e9CrossRefGoogle Scholar
  2. 2.
    Barai, A., Lambie, B., Cosgrave, C., Baxter, J.: Management of distal radius fractures in the emergency department: a long-term functional outcome measure study with the Disabilities of Arm, Shoulder and Hand (DASH) scores. Emerg. Med. Australasia 30(4), 530–537 (2018).  https://doi.org/10.1111/1742-6723.12946CrossRefGoogle Scholar
  3. 3.
    Bartl, C., et al.: Open reduction and internal fixation versus casting for highly comminuted and intra-articular fractures of the distal radius (ORCHID): protocol for a randomized clinical multi-center trial. Trials 12(1), 84 (2011).  https://doi.org/10.1186/1745-6215-12-84MathSciNetCrossRefGoogle Scholar
  4. 4.
    Bidgood, W.D., Horii, S.C.: Introduction to the ACR-NEMA DICOM standard. Radiographics: A Review Publication of the Radiological Society of North America, Inc 12(2), 345–355 (Mar 1992).  https://doi.org/10.1148/radiographics.12.2.1561424
  5. 5.
    Bishop, C.: Pattern Recognition and Machine Learning. In: Information Science and Statistics. Springer-Verlag, New York (2006). https://www.springer.com/gp/book/9780387310732
  6. 6.
    Bloom, R.A., Laws, J.W.: Humeral cortical thickness as an index of osteoporosis in women. Br. J. Radiol. 43(512), 522–527 (1970).  https://doi.org/10.1259/0007-1285-43-512-522CrossRefGoogle Scholar
  7. 7.
    Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001).  https://doi.org/10.1023/A:1010933404324CrossRefzbMATHGoogle Scholar
  8. 8.
    Colles, A.: On the fracture of the carpal extremity of the radius. N. Engl. J. Medi. Surg. Collateral Branches Sci. 3(4), 368–372 (1814).  https://doi.org/10.1056/NEJM181410010030410CrossRefGoogle Scholar
  9. 9.
    Cooney, W.P., Dobyns, J.H., Linscheid, R.L.: Complications of colles’ fractures. J. Bone Joint Surg. Am. 62(4), 613–619 (1980)CrossRefGoogle Scholar
  10. 10.
    Criminisi, A., Shotton, J.: Decision Forests for Computer Vision and Medical Image Analysis. Springer, London (2013).  https://doi.org/10.1007/978-1-4471-4929-3CrossRefGoogle Scholar
  11. 11.
    Grewal, R., MacDermid, J.C., King, G.J.W., Faber, K.J.: Open reduction internal fixation versus percutaneous pinning with external fixation of distal radius fractures: a prospective, randomized clinical trial. J. Hand Surg. 36(12), 1899–1906 (2011).  https://doi.org/10.1016/j.jhsa.2011.09.015CrossRefGoogle Scholar
  12. 12.
    Hastie, T., Tibshirani, R., Friedman, J.: The Elements of Statistical Learning. SSS. Springer, New York (2009).  https://doi.org/10.1007/978-0-387-84858-7CrossRefzbMATHGoogle Scholar
  13. 13.
    Hsu, H., Fahrenkopf, M.P., Nallamothu, S.V.: Wrist fracture. In: StatPearls. StatPearls Publishing, Treasure Island (FL) (2020). http://www.ncbi.nlm.nih.gov/books/NBK499972/
  14. 14.
    Jantzen, C., Cieslak, L.K., Barzanji, A.F., Johansen, P.B., Rasmussen, S.W., Schmidt, T.A.: Colles’ fractures and osteoporosis-a new role for the emergency department. Injury 47(4), 930–933 (2016).  https://doi.org/10.1016/j.injury.2015.11.029CrossRefGoogle Scholar
  15. 15.
    Kapoor, H., Agarwal, A., Dhaon, B.K.: Displaced intra-articular fractures of distal radius: a comparative evaluation of results following closed reduction, external fixation and open reduction with internal fixation. Injury 31(2), 75–79 (2000).  https://doi.org/10.1016/S0020-1383(99)00207-7CrossRefGoogle Scholar
  16. 16.
    Laseter, G.F., Carter, P.R.: Management of distal radius fractures. J. Hand Ther. 9(2), 114–128 (1996).  https://doi.org/10.1016/S0894-1130(96)80070-6CrossRefGoogle Scholar
  17. 17.
    Marshall, R.J.: The use of classification and regression trees in clinical epidemiology. J. Clin. Epidemiol. 54(6), 603–609 (2001).  https://doi.org/10.1016/S0895-4356(00)00344-9CrossRefGoogle Scholar
  18. 18.
    Muller, R., Möckel, M.: Logistic regression and cart in the analysis of multimarker studies. Clin. Chim. Acta 394(1), 1–6 (2008).  https://doi.org/10.1016/j.cca.2008.04.007CrossRefGoogle Scholar
  19. 19.
    Ojala, T., Pietikäinen, M., Harwood, D.: A comparative study of texture measures with classification based on featured distributions. Pattern Recognit. 29(1), 51–59 (1996).  https://doi.org/10.1016/0031-3203(95)00067-4CrossRefGoogle Scholar
  20. 20.
    Podgorelec, V., Kokol, P., Stiglic, B., Rozman, I.: Decision trees: an overview and their use in medicine. J. Med. Syst. 26(5), 445–463 (2002).  https://doi.org/10.1023/A:1016409317640CrossRefGoogle Scholar
  21. 21.
    Reyes-Aldasoro, C.C., Ngan, K.H., Ananda, A., Garcez, A.d., Appelboam, A., Knapp, K.M.: Geometric semi-automatic analysis of colles’ fractures, Feb 2020 medRxiv p. 2020.02.18.20024562. https://www.medrxiv.org/content/10.1101/2020.02.18.20024562v1
  22. 22.
    Shaikhina, T., Lowe, D., Daga, S., Briggs, D., Higgins, R., Khovanova, N.: Decision tree and random forest models for outcome prediction in antibody incompatible kidney transplantation. Biomed. Sig. Proc. Control 52, 456–462 (2019).  https://doi.org/10.1016/j.bspc.2017.01.012CrossRefGoogle Scholar
  23. 23.
    Simic, P.M., Weiland, A.J.: Fractures of the distal aspect of the radius: changes in treatment over the past two decades. JBJS 85(3), 552–564 (2003)CrossRefGoogle Scholar
  24. 24.
    Webber, T., Patel, S.P., Pensak, M., Fajolu, O., Rozental, T.D., Wolf, J.M.: Correlation between distal radial cortical thickness and bone mineral density. J. Hand Surg. 40(3), 493–499 (2015).  https://doi.org/10.1016/j.jhsa.2014.12.015CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.School of Mathematics, Computer Science and Engineering CityUniversity of LondonLondonUK
  2. 2.College of Medicine and HealthUniversity of ExeterExeterUK
  3. 3.Royal Devon and Exeter HospitalExeterUK

Personalised recommendations