Calcium2026

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

Maryum Alina, Shaukat Arslan, Yousaf Ehsan, Haque Ayesha et al. — PloS one

Summary

This study explored a new way to identify osteoporosis and predict bone density, especially in places without expensive diagnostic equipment. Researchers developed a machine learning tool that uses common, inexpensive tests like blood calcium and potassium levels, along with weight and vitamin D, to assess bone health. This approach could make early screening for bone problems more accessible and affordable for many people.

AI-generated summary — read the original

Key points

Osteoporosis is often hard to detect early with current standard methods.
A new machine learning tool uses basic blood tests, including calcium and potassium levels, along with weight and vitamin D, to predict bone health.
This method aims to make osteoporosis screening more affordable and accessible, especially in areas with limited resources.
It offers a radiation-free way to pre-screen for bone density issues and fracture risk.

What the study looked at

What question the study asked: This research aimed to find a more affordable and accessible way to detect osteoporosis and predict bone mineral density, particularly in settings where advanced diagnostic equipment like DXA scans are not readily available. How it was studied (design/participants): Researchers collected data from 159 patients, including their age, weight, blood type, medical history, and results from common lab tests such as serum calcium and potassium levels. They then used this information to develop a machine learning model designed to identify key indicators of bone health without relying on expensive imaging. What it found: The study successfully developed a model that could predict the severity of osteoporosis with about 90% accuracy, using factors like weight, potassium, calcium, and vitamin D levels. It also showed promise in estimating lumbar spine bone mineral density using age, weight, blood group, and vitamin D. These findings suggest that simple, inexpensive lab tests could be effectively used as a preliminary, non-invasive screening tool for bone health.

Dietary takeaway

While this study highlights new ways to *detect* bone issues, it reinforces the importance of maintaining adequate calcium intake for strong bones. Including calcium-rich foods like dairy products, leafy greens, and fortified foods in your daily diet remains a key strategy for bone health, though this study doesn't directly measure dietary impact. Remember, this is one study, and more research is needed to confirm these findings and their broader application.

Abstract

Osteoporosis is a chronic skeletal disorder characterized by progressive bone mineral density (BMD) loss and structural deterioration, significantly increasing fracture risk. Despite its high prevalence, early detection remains challenging due to its asymptomatic progression and the limitations of conventional diagnostic techniques, such as Dual-Energy X-ray Absorptiometry (DXA). While DXA remains the clinical benchmark for BMD assessment, its high cost, limited accessibility, and inability to directly detect vertebral fractures necessitate the development of alternative, cost-effective, and widely deployable diagnostic methodologies. A dataset of 159 patient records was collected from NORI and CDA Hospital, incorporating 17 input features spanning demographics, genetic/blood type, clinical history and lab tests parameters. To bridge this gap, we developed a practical machine learning model tailored for clinics with limited resources. Instead of relying on expensive imaging, our framework uses only basic, highly accessible clinical markers-specifically ABO blood groups, serum calcium, and potassium levels. Because these tests are inexpensive and easily processed in standard laboratories, our approach removes the financial and technical hurdles of advanced diagnostics, making early screening possible in remote or underfunded healthcare settings. Data preprocessing involved rigorous feature selection, standardization, hyper-parameters tuning, clinically relevant features derivation and biomarker combinations. For classification, ensemble voting classifier was trained on key biomarkers- Weight, Potassium, Calcium and Total Vitamin D-achieving an accuracy of 90% and an AU-ROC score of 0.93 in predicting osteoporosis severity. In parallel, extreme gradient boosting Regressor trained on Age, Weight, ABO Group and Total Vitamin D demonstrated an R2 of 0.536 for lumbar spine BMD estimation. The proposed framework demonstrates the viability of leveraging machine learning for non-invasive osteoporosis screening and fracture risk assessment, offering a radiation-free and clinically accessible complementary pre-screening tool.

View on PubMed →DOI: 10.1371/journal.pone.0354038