Establishment of hip fracture prediction model using radiomics texture analysis of dual-energy x-ray absorptiometry images with machine learning application

Abstract

Dual-energy X-ray absorptiometry (DXA)-based bone mineral density testing is standard to diagnose osteoporosis to detect individuals at high risk of fracture. A radiomics approach to extract quantifiable texture features from DXA hip images may improve hip fracture prediction without additional costs. Here, I investigated whether bone radiomics scores from DXA hip images could improve hip fracture prediction in a community-based cohort of older women. The derivation set (143 women who sustained hip fracture [mean age 73, time to fracture median 2.1 years] vs. 290 age-matched women [mean age 73] who did not sustain hip fracture during follow-up [median 5.5 years]) were split to train set (75%) and test set (25% hold -out set). Among various models using 14 selected features out of 300 texture features mined from DXA hip images in train set, random forest model was selected as best model to build bone radiomics score (range 0 to 100) based on the performance in the test set. In a community-based cohort (2029 women, mean age 71) as clinical validation set, bone radiomics score was calculated using model fitted in train set. A total of 34 participants (1.7%) sustained hip fracture during median follow-up of 5.4 years (mean bone radiomics score 40±16 vs. 28±12 in non-fractured, p<0.001). A one-point bone radiomics score increment was associated with an 4% elevated risk of incident hip fracture (adjusted hazard ratio [aHR] 1.04, p=0.001) after adjustment for age, BMI, previous history of fracture, and femoral neck T-score, with improved model fit when added to covariates (likelihood ratio χ2 10.74, p=0.001). The association between bone radiomics score with incident hip fracture remained robust (adjusted HR 1.06, p<0.001) after adjustment for FRAX hip fracture probability. Bone radiomics scores estimated from texture features of DXA hip images have the potential to improve hip fracture prediction.