Search Results (3)

Objectives: The early detection of low bone mineral density (BMD) is essential for preventing osteoporosis and related complications. While dual-energy X-ray absorptiometry (DXA) remains the gold standard for diagnosis, its cost and limited availability restrict its use in large-scale screening. This study investigated whether raw bioelectrical impedance analysis (BIA) data combined with explainable machine learning (ML) models could accurately classify osteopenia in women aged 40 to 55. Methods: In a cross-sectional design, 138 women underwent same-day BIA and DXA assessments. Participants were categorized as osteopenic (T-score between −1.0 and −2.5; n = 33) or normal (T-score ≥ −1.0) based on DXA results. Overall, 24.1% of the sample were classified as osteopenic, and 32.85% were postmenopausal. Raw BIA outputs were used as input features, including impedance values, phase angles, and segmental tissue parameters. A sequential forward feature selection (SFFS) algorithm was employed to optimize input dimensionality. Four ML classifiers were trained using stratified five-fold cross-validation, and SHapley Additive exPlanations (SHAP) were applied to interpret feature contributions. Results: The neural network (NN) model achieved the highest classification accuracy (92.12%) using 34 selected features, including raw impedance measurements, derived body composition indices such as regional lean mass estimates and the edema index, as well as a limited number of categorical variables, including self-reported physical activity status. SHAP analysis identified muscle mass indices and fluid distribution metrics, features previously associated with bone health, as the most influential predictors in the current model. Other classifiers performed comparably but with lower precision or interpretability. Conclusions: ML models based on raw BIA data can classify osteopenia with high accuracy and clinical transparency. This approach provides a cost-effective and interpretable alternative for the early identification of individuals at risk for low BMD in resource-limited or primary care settings. Full article

The aims of this study were to investigate age-related changes in total body skeletal muscle mass (TBSMM) and the between-limb asymmetry in lean mass in a large sample of adults. Demographic, anthropometric, and DXA-derived data of National Health and Nutrition Examination Survey participants were considered. The sample included 10,014 participants of two ethnic groups (Caucasians and African Americans). The age-related decline of TBSMM absolute values was between 5% and 6% per decade in males and between 4.5% and 5.0% per decade in females. The adjustment of TBSMM for body surface area (TB-MAXI) showed that muscle mass peaked in the second decade and decreased progressively during the subsequent decades. The following thresholds were identified to distinguish between low and normal TB-MAXI: (i) 10.0 kg/m² and 11.0 kg/m² in Caucasian and African American females; and (ii) 12.5 kg/m² and 14.5 kg/m² in Caucasian and African American males. The lean asymmetry indices were higher for the lower limbs compared with the upper limbs and were higher for males compared with females. In conclusion, the present study proposes the TB-MAXI and lean asymmetry index, which can be used (and included in DXA reports) as clinically relevant markers for muscle amount and lean distribution. Full article

Sarcopenia is linked with increased risk of falls, osteoporosis and mortality. No consensus exists about a gold standard “dual-energy X-ray absorptiometry (DXA) index for muscle mass determination” in sarcopenia diagnosis. Thus, many indices exist, but data on sarcopenia diagnosis agreement are scarce. Regarding sarcopenia diagnosis reliability, the impact of influencing factors on sarcopenia prevalence, diagnosis agreement and reliability are almost completely missing. For nine DXA-derived muscle mass indices, we aimed to evaluate sarcopenia prevalence, diagnosis agreement and diagnosis reliability, and investigate the effects of underlying parameters, presence or type of adjustment and cut-off values on all three outcomes. The indices were analysed in the BioPersMed cohort (58 ± 9 years), including 1022 asymptomatic subjects at moderate cardiovascular risk. DXA data from 792 baselines and 684 follow-up measurements (for diagnosis agreement and reliability determination) were available. Depending on the index and cut-off values, sarcopenia prevalence varied from 0.6 to 36.3%. Height-adjusted parameters, independent of underlying parameters, showed a relatively high level of diagnosis agreement, whereas unadjusted and adjusted indices showed low diagnosis agreement. The adjustment type defines which individuals are recognised as sarcopenic in terms of BMI and sex. The investigated indices showed comparable diagnosis reliability in follow-up examinations Full article