Experts create AI system that can accurately diagnose osteoporosis using routine X-rays
Experts have developed an artificial intelligence tool they believe could enhance the opportunistic diagnosis of osteoporosis.
Bone density measurements are typically conducted during dedicated dual-energy X-ray absorptiometry exams. Although the scans are accurate, their utilization rates are low, leaving many patients unknowingly vulnerable to major fractures.
This latest system can estimate bone mineral density using lumbar spine and femur X-rays, which are routinely (and often) completed for other clinical indications. Experts involved in its development are optimistic their tool could help providers identify patients who may be at risk of developing osteoporosis sooner, thus enabling earlier treatment.
Researchers detailed their efforts in the Journal of Orthopaedic Research.
“Bone mineral density measurement is essential for screening and diagnosing osteoporosis, but limited access to diagnostic equipment means that millions of people worldwide may remain undiagnosed,” corresponding author Toru Moro, MD, PhD, of the University of Tokyo, and colleagues noted. “This AI system has the potential to transform routine clinical X-rays into a powerful tool for opportunistic screening, enabling earlier, broader and more efficient detection of osteoporosis.”
The system uses a deep neural network to categorize patients based on their bone mineral density. It was trained using dual-energy X-ray absorptiometry-derived lumbar and femoral bone mineral density values (for ground truth) and preprocessed X-ray images and tested on an additional 1,454 lumbar spine and femur radiographs.
For identifying bone density loss and osteopenia, the system yielded sensitivities of 86.4% and 84.1%, while specificity was slightly lower at 80.4% and 76.3%, respectively. Of note, AI was able to identify osteoporosis in both hospitalized and seemingly healthy patients. The group also noted that AI was more accurate when analyzing femur X-rays compared to those of the lower back.
“Our AI-assisted osteoporosis diagnostic system using lumbar X-ray images is expected to increase opportunities to (a) identify potential patients with osteopenia and osteoporosis, (b) facilitate early detection of high-risk individuals, and (c) help prevent bone loss and fragility fractures in areas, such as the lumbar spine and femur, by encouraging improvements in lifestyle habits, including diet and exercise,” the group concluded, adding that while their findings represent a positive first step, more work needs to be done before similar tools can be trusted in clinical settings.
Learn more about the study here.
In addition to her background in journalism, Hannah also has patient-facing experience in clinical settings, having spent more than 12 years working as a registered rad tech. She began covering the medical imaging industry for Innovate Healthcare in 2021.