AI repurposes routine chest X-rays to catch silent bone loss before fracture

Osteoporosis is a silent disease where bone loss develops gradually before fractures occur. Current clinical screening recommendations mainly focus on older women and selected high-risk groups, leaving some men, younger adults, and individuals with normal body weight completely outside routine screening pathways.

To close this care gap, researchers from St. Paul’s Hospital and National Taiwan University have demonstrated how AI can leverage routine chest X-rays to detect asymptomatic bone loss, closing critical gaps in screening healthy Asian populations. Their paper is published in the journal npj Digital Medicine.

Strikingly, the study found that more than half of the confirmed abnormal bone-density cases occurred in people with a normal body mass index (BMI). This reveals a severe diagnostic blind spot in conventional, guideline-based screening. By relying strictly on traditional criteria, health care systems routinely overlook healthy-weight individuals, younger adults, and men who are secretly losing bone density but remain completely off the clinical radar.

Since chest X-rays are already universally performed during routine health examinations across Asia, this AI approach provides a practical, infrastructure-light strategy to expand opportunistic screening. It actively flags at-risk men and younger individuals outside standard guidelines without adding patient burden or cost.

“Under Taiwan’s National Health Insurance system, we often rely on strict guideline-based criteria to decide who qualifies for DXA testing,” said Shu-Han Chen, MD, first author of the study, a family medicine physician, leader of the Health Management Center at St. Paul’s Hospital, and an alumnus of the Graduate Institute of Health Policy and Management at National Taiwan University.

“Our findings suggest that AI-assisted chest X-ray analysis could help identify individuals who may otherwise be overlooked and who may benefit from confirmatory DXA testing.”

“This study demonstrates how artificial intelligence can transform existing health care workflows into scalable preventive-health strategies while supporting more equitable access to osteoporosis screening,” said co-corresponding author Prof. Ray-E Chang at the Institute of Health Policy and Management at National Taiwan University.

Who’s behind this story?

Lisa Lock

BA art history, MA material culture. Former museum editor, paramedic, and transplant coordinator. Editing for Science X since 2021.

Full profile →

Advertisements

Robert Egan

Bachelor’s in mathematical biology, Master’s in creative writing. Well-traveled with unique perspectives on science and language.

Full profile →