Machine learning outperforms clinical experts in classification of hip fractures

E A  Murphy; Beate Ehrhardt; Celia L Gregson; April E Hartley; Michael R Whitehouse; M S  Thomas; G Stenhouse; Timothy J Chesser; C J Budd; H S Gill; O. A Von Arx

doi:10.1038/s41598-022-06018-9

Machine learning outperforms clinical experts in classification of hip fractures

E A Murphy, Beate Ehrhardt, Celia L Gregson, April E Hartley, Michael R Whitehouse, M S Thomas, G Stenhouse, Timothy J Chesser, C J Budd, H S Gill^*, O. A Von Arx

^*Corresponding author for this work

Research output: Contribution to journal › Article (Academic Journal) › peer-review

32 Citations (Scopus)

107 Downloads (Pure)

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 3,659 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%.

Original language	English
Article number	2058
Number of pages	11
Journal	Scientific Reports
Volume	12
Issue number	1
Early online date	8 Feb 2022
DOIs	https://doi.org/10.1038/s41598-022-06018-9
Publication status	E-pub ahead of print - 8 Feb 2022

Bibliographical note

Funding Information:
This study was funded by Arthroplasty for Arthritis Charity, and the NVIDIA Corporation provided the Titan X GPU through their academic grant scheme. We acknowledge the critical assistance of Mr Rich Wood, PACS Manager at Royal United Hospital NHS Foundation Trust in Bath, in identifying, anonymising and extracting the appropriate radiographs. We are also grateful to Professors Carola-Bibiane Schönlieb and Michael Tipping for their insight and advice on machine learning.

Publisher Copyright:
© 2022, The Author(s).

Keywords

Computational science
Trauma

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1038/s41598-022-06018-9

Full-text PDF (final published version)
This is the final published version of the article (version of record). It first appeared online via Nature Research at https://doi.org/10.1038/s41598-022-06018-9. Please refer to any applicable terms of use of the publisher.
Final published version, 1.16 MBLicence: CC BY

Handle.net

Persistent link

Embargoed Document

Full-text PDF (accepted author manuscript)
Accepted author manuscript, 655 KB

Cite this

Murphy, E. A., Ehrhardt, B., Gregson, C. L., Hartley, A. E., Whitehouse, M. R., Thomas, M. S., Stenhouse, G., Chesser, T. J., Budd, C. J., Gill, H. S., & Von Arx, O. A. (2022). Machine learning outperforms clinical experts in classification of hip fractures. Scientific Reports, 12(1), Article 2058 . Advance online publication. https://doi.org/10.1038/s41598-022-06018-9

@article{dafee9867c1d486ca6fa273d05421b4c,

title = "Machine learning outperforms clinical experts in classification of hip fractures",

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 3,659 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\%.",

keywords = "Computational science, Trauma",

author = "Murphy, \{E A\} and Beate Ehrhardt and Gregson, \{Celia L\} and Hartley, \{April E\} and Whitehouse, \{Michael R\} and Thomas, \{M S\} and G Stenhouse and Chesser, \{Timothy J\} and Budd, \{C J\} and Gill, \{H S\} and \{Von Arx\}, \{O. A\}",

note = "Funding Information: This study was funded by Arthroplasty for Arthritis Charity, and the NVIDIA Corporation provided the Titan X GPU through their academic grant scheme. We acknowledge the critical assistance of Mr Rich Wood, PACS Manager at Royal United Hospital NHS Foundation Trust in Bath, in identifying, anonymising and extracting the appropriate radiographs. We are also grateful to Professors Carola-Bibiane Sch{\"o}nlieb and Michael Tipping for their insight and advice on machine learning. Publisher Copyright: {\textcopyright} 2022, The Author(s).",

year = "2022",

month = feb,

day = "8",

doi = "10.1038/s41598-022-06018-9",

language = "English",

volume = "12",

journal = "Scientific Reports",

issn = "2045-2322",

publisher = "Nature Research",

number = "1",

}

TY - JOUR

T1 - Machine learning outperforms clinical experts in classification of hip fractures

AU - Murphy, E A

AU - Ehrhardt, Beate

AU - Gregson, Celia L

AU - Hartley, April E

AU - Whitehouse, Michael R

AU - Thomas, M S

AU - Stenhouse, G

AU - Chesser, Timothy J

AU - Budd, C J

AU - Gill, H S

AU - Von Arx, O. A

N1 - Funding Information: This study was funded by Arthroplasty for Arthritis Charity, and the NVIDIA Corporation provided the Titan X GPU through their academic grant scheme. We acknowledge the critical assistance of Mr Rich Wood, PACS Manager at Royal United Hospital NHS Foundation Trust in Bath, in identifying, anonymising and extracting the appropriate radiographs. We are also grateful to Professors Carola-Bibiane Schönlieb and Michael Tipping for their insight and advice on machine learning. Publisher Copyright: © 2022, The Author(s).

PY - 2022/2/8

Y1 - 2022/2/8

N2 - 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 3,659 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%.

AB - 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 3,659 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%.

KW - Computational science

KW - Trauma

U2 - 10.1038/s41598-022-06018-9

DO - 10.1038/s41598-022-06018-9

M3 - Article (Academic Journal)

C2 - 35136091

SN - 2045-2322

VL - 12

JO - Scientific Reports

JF - Scientific Reports

IS - 1

M1 - 2058

ER -

Machine learning outperforms clinical experts in classification of hip fractures

Abstract

Bibliographical note

Keywords

UN SDGs

Access to Document

Handle.net

Embargoed Document

Fingerprint

Cite this