Abstract

Hip fractures are a major cause of morbidity and mortality in the elderly, and incur high health and social care costs. Given projected population ageing, the number of incident hip fractures is predicted to increase globally. As fracture classification strongly determines the chosen surgical treatment, differences in fracture classification influence patient outcomes and treatment costs. We aimed to create a machine learning method for identifying and classifying hip fractures, and to compare its performance to experienced human observers. We used 3659 hip radiographs, classified by at least two expert clinicians. The machine learning method was able to classify hip fractures with 19% greater accuracy than humans, achieving overall accuracy of 92%.

Details

Title
Machine learning outperforms clinical experts in classification of hip fractures
Author
Murphy, E A 1 ; Ehrhardt, B 1 ; Gregson, C L 2 ; von Arx O A 3 ; Hartley, A 2 ; Whitehouse, M R 4 ; Thomas, M S 3 ; Stenhouse, G 3 ; Chesser, T J, S 5 ; Budd, C J 6 ; Gill, H S 7 

 University of Bath, Institute for Mathematical Innovation, Bath, UK (GRID:grid.7340.0) (ISNI:0000 0001 2162 1699) 
 University of Bristol, Musculoskeletal Research Unit, Bristol Medical School, Bristol, UK (GRID:grid.5337.2) (ISNI:0000 0004 1936 7603); University of Bristol, MRC Integrative Epidemiology Unit, Bristol Medical School, Bristol, UK (GRID:grid.5337.2) (ISNI:0000 0004 1936 7603) 
 Royal United Hospital NHS Foundation Trust, Bath, UK (GRID:grid.413029.d) (ISNI:0000 0004 0374 2907) 
 University of Bristol, Musculoskeletal Research Unit, Bristol Medical School, Bristol, UK (GRID:grid.5337.2) (ISNI:0000 0004 1936 7603); North Bristol NHS Trust, Department of Trauma and Orthopaedics, Bristol, UK (GRID:grid.418484.5) (ISNI:0000 0004 0380 7221) 
 North Bristol NHS Trust, Department of Trauma and Orthopaedics, Bristol, UK (GRID:grid.418484.5) (ISNI:0000 0004 0380 7221) 
 University of Bath, Institute for Mathematical Innovation, Bath, UK (GRID:grid.7340.0) (ISNI:0000 0001 2162 1699); University of Bath, Department of Mathematical Sciences, Bath, UK (GRID:grid.7340.0) (ISNI:0000 0001 2162 1699) 
 University of Bath, Department of Mechanical Engineering, Bath, UK (GRID:grid.7340.0) (ISNI:0000 0001 2162 1699); University of Bath, Centre for Therapeutic Innovation, Bath, UK (GRID:grid.7340.0) (ISNI:0000 0001 2162 1699) 
Publication year
2022
Publication date
2022
Publisher
Nature Publishing Group
e-ISSN
20452322
Source type
Scholarly Journal
Language of publication
English
ProQuest document ID
2626564669
Copyright
© The Author(s) 2022. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.