Diagnostic accuracy of an artificial intelligence-based osteoporosis screening system on portable chest radiographs
Jee Hyun Kim, So Hyun Ahn, Rena Lee, Sungho Cho, Soeun Choi, Kwan-Chang Kim · 2026
Read Diagnostic accuracy of an artificial intelligence-based osteoporosis screening system on portable chest radiographs by Jee Hyun Kim, So Hyun Ahn, Rena Lee, Sungho Cho, Soeun Choi, Kwan-Chang Kim (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13559357.txt.
Description
Jee Hyun Kim and colleagues tested a commercial artificial intelligence system that screens for osteoporosis from portable chest X-rays taken outside hospitals. Their 2026 prospective pilot enrolled older adults in a Korean mobile tuberculosis screening program who agreed to bone testing. The AI produced a risk score for each image, and participants then had DXA scans, the reference bone-density test, within about a week.
Fifty-two participants had both results to compare, and 20 of them, 38.5 percent of the group, met the DXA definition of osteoporosis. At a score threshold of 0.2, the system caught 90 percent of true cases, though its specificity was modest. Most false alarms came from people with osteopenia, the milder stage of bone loss. Overall discrimination reached an area under the curve of 0.86 in this small group. The authors call the tool promising for referral screening but insist on larger, externally checked cohorts.
Catalog record
| CREATOR | Jee Hyun Kim, So Hyun Ahn, Rena Lee, Sungho Cho, Soeun Choi, Kwan-Chang Kim |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 42 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |