Interpretable Machine Learning for Osteopenia Detection: A Proof-of-Concept Study Using Bioelectrical Impedance in Perimenopausal Women

Abstract

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.

Keywords: perimenopause; preventive medicine; public health screening.

Figure 1

Agreement between DXA and BIA measurements for fat-free mass (FFM) and fat mass (FM). Panels (A,B) show Bland–Altman plots comparing FFM and FM values obtained from dual-energy X-ray absorptiometry (DXA) and bioelectrical impedance analysis (BIA), illustrating the mean difference and limits of agreement. Panels (C,D) display scatterplots with linear regression lines showing the strong correlations between the two methods for FFM and FM, respectively, across the total sample.

Figure 2

Confusion matrices for the machine learning (ML) classifiers used in the study. (a–d) represent the performance of the (a) XGBoost, (b) LR, (c) SVM, and (d) NN classifiers, respectively. Each matrix displays the number of true positives, true negatives, false positives, and false negatives, providing a visual summary of each model’s ability to correctly classify cases and non-cases of osteopenia. Sensitivity and specificity values are derived from these matrices.

Figure 3

SHAP analysis of feature importance based on the NN classifier. Figure (a) shows the mean absolute SHAP values for each predictor, indicating their overall contribution to the model’s output. Figure (b) presents the SHAP summary plot, which displays both the magnitude and direction of each feature’s impact on individual predictions across the dataset. Higher SHAP values correspond to a stronger influence on model decisions, with color gradients indicating the magnitude of feature values.