AI for Hip Fracture Detection

Yan Yet Yen, Changi General Hospital
Goh Siang Hiong, Changi General Hospital
Cheng Tim-Ee Lionel, Singapore General Hospital
Liu Nan, Centre for Quantitative Medicine (CQM)

Hip fractures are a major public health problem, with global incidence increasing due to population ageing and estimated to reach 6.3 million by 2050. Researchers from Changi General Hospital (CGH), Singapore General Hospital (SGH) and Duke-NUS Medical School approximated the real-world application of a deep learning hip fracture detection model by including more than 40,000 Pelvis AP radiographs with sub-optimal image quality, other non-hip fractures, and metallic implants. They also explored the effect of ethnicity on model performance, as well as the accuracy of visualization algorithm for fracture localization. Moving forward, they plan to work on explainability of the deep learning model and implement the model in the Emergency Department.

Gao Y, Soh NYT, Liu N, Lim G, Ting D, Cheng LTE, Wong KM, Liew C, Oh HC, Tan JR, Venkataraman N, Goh SH, Yan YY. Application of a deep learning algorithm in the detection of hip fractures. iScience 2023 Aug; 26(8): 107350. DOI:https://doi.org/10.1016/j.isci.2023.107350