A feature-efficient dual-task machine learning framework for predicting bone mineral density and osteoporosis stratification in resource-constrained environments

Alina Maryum, Arslan Shaukat, Ehsan Yousaf, Ayesha Haque, Shazia Yusuf, Saif ul Haque, Humaira Ali, Soyiba Jawed · 2026

Read A feature-efficient dual-task machine learning framework for predicting bone mineral density and osteoporosis stratification in resource-constrained environments by Alina Maryum, Arslan Shaukat, Ehsan Yousaf, Ayesha Haque, Shazia Yusuf, Saif ul Haque, Humaira Ali, Soyiba Jawed (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/plos-pone-0354038.txt.

Description

Alina Maryum and seven colleagues build a cheap machine-learning screen for osteoporosis, in this 2026 PLOS ONE study aimed at clinics with few resources. The standard bone scan is costly and often unavailable where patients are poorest. Instead, their model uses records from two Pakistani hospitals and leans on simple inputs: blood group, blood calcium and potassium, weight, and vitamin D levels.

An ensemble of classifiers sorted patients by osteoporosis severity with accuracy around nine in ten. A second model estimated spine bone density moderately well from age, weight, blood group, and vitamin D. If confirmed in larger samples, screening from routine blood tests could flag at-risk patients long before a fracture.

Catalog record

CREATORAlina Maryum, Arslan Shaukat, Ehsan Yousaf, Ayesha Haque, Shazia Yusuf, Saif ul Haque, Humaira Ali, Soyiba Jawed
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE40307
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0354038

Browse the full library · About the Tower of Babel