Machine learning outperforms clinical experts in classifying hip fractures
IMI Fellow Prof Richie Gill leads a research team who have developed a machine learning tool to help clinicians identify and classify hip fractures more efficiently.
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%.
The machine learning process implemented by the Mathematical Innovation Research Associate Beate Ehrhardt and former colleague Ellen Murphy trained two convolutional neural networks: one to locate the hip, the other to classify fractures. CNN1 was able to correctly locate and extract hip joints in the vast majority of cases where the Jaccard Index J was 0.87 (SD 0.06), all samples scored values of J > 0.5 and 98% of the hip joints scored J > 0.7 (indicating better than good agreement). CNN2 predicted the correct fracture type in 92% (which represents the overall accuracy) of the test set (κ = 0.87 [95%CI: 0.84 to 0.90]: NB Cohen’s kappa, κ, varies from κ = 1 for complete agreement to κ = 0 if the agreement is no better than expected by chance). This represents an 18.7 (= 100*[92–77.5]/77.5) percentage points increased accuracy over the original hospital diagnosis accuracy.
Read the full article here
See also the article in the Washington Post