Scholarlink

Summary <p>Rationale: Existing osteoporosis screening tools are inaccurate and inconvenient, prompting the need for a better alternative.</p> <p>Main result: A machine learning tool (Gradient Boosting) with key factors (weight, age, height) outperformed OST (AUC 0.828 vs 0.781, <i>p</i> &lt; 0.0001) in validation.</p> Significance <p>The validated, clinically applicable tool improves osteoporosis screening accessibility and accuracy.</p> Background <p>As the first “line of defence” for osteoporosis detection, existing screening tools have low accuracy and are inconvenient to use. Therefore, this study aims to develop a machine-learning-based, clinically applicable, and interpretable osteoporosis screening tool.</p> Methods <p>This study included 9405 American participants aged 50&#xa0;years and older (with the average age of the osteoporosis population in the training set and test set being 72 ± 9&#xa0;years and 73 ± 8&#xa0;years, respectively). The study selected 13 clinically accessible indicators as candidate predictive variables, divided the data into a training set and a test set at a ratio of 7:3, used the Lasso for feature selection, compared six statistical and machine learning models, evaluated model performance through metrics such as the Area Under the Receiver Operating Characteristic Curve (AUC), Sensitivity, specificity, F1-score, decision curve, calibration curve, and clinical impact curve, employed the SHAP (Shapley Additive exPlanations) method to enhance model interpretability, and conducted external validation based on an independent dataset from the Second Hospital of Lanzhou University.</p> Results <p>“Weight,” “age,” and “height” are the most critical predictive factors. Gradient Boosting Machine (GB) showed optimal results, with training and test set AUC (0.850, 0.841), sensitivity (0.757, 0.737), specificity (0.793, 0.779), and F1-score (0.336, 0.316), respectively. External validation (3500 subjects) showed that the GB-based screening tool had an AUC of 0.828, which was significantly higher than that of the traditional Osteoporosis Self-Assessment Tool (OST, AUC = 0.781) via the DeLong test (z = 10.880, <i>p</i> &lt; 0.0001).</p> Conclusion <p>A clinically applicable osteoporosis screening tool based on machine learning algorithms was developed and validated.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A machine-learning-based osteoporosis screening tool integrating the Shapley Additive exPlanation (SHAP) method: model development and validation study

  • 期刊论文

  • 发表日期：

    2025年10月22日

查看全文
  • Yuji Zhang,
  • Ming Ma,
  • Cong Tian,
  • Jinmin Liu,
  • Zhenkun Duan,
  • Xingchun Huang,
  • Bin Geng

摘要

Summary

Rationale: Existing osteoporosis screening tools are inaccurate and inconvenient, prompting the need for a better alternative.

Main result: A machine learning tool (Gradient Boosting) with key factors (weight, age, height) outperformed OST (AUC 0.828 vs 0.781, p < 0.0001) in validation.

Significance

The validated, clinically applicable tool improves osteoporosis screening accessibility and accuracy.

Background

As the first “line of defence” for osteoporosis detection, existing screening tools have low accuracy and are inconvenient to use. Therefore, this study aims to develop a machine-learning-based, clinically applicable, and interpretable osteoporosis screening tool.

Methods

This study included 9405 American participants aged 50 years and older (with the average age of the osteoporosis population in the training set and test set being 72 ± 9 years and 73 ± 8 years, respectively). The study selected 13 clinically accessible indicators as candidate predictive variables, divided the data into a training set and a test set at a ratio of 7:3, used the Lasso for feature selection, compared six statistical and machine learning models, evaluated model performance through metrics such as the Area Under the Receiver Operating Characteristic Curve (AUC), Sensitivity, specificity, F1-score, decision curve, calibration curve, and clinical impact curve, employed the SHAP (Shapley Additive exPlanations) method to enhance model interpretability, and conducted external validation based on an independent dataset from the Second Hospital of Lanzhou University.

Results

“Weight,” “age,” and “height” are the most critical predictive factors. Gradient Boosting Machine (GB) showed optimal results, with training and test set AUC (0.850, 0.841), sensitivity (0.757, 0.737), specificity (0.793, 0.779), and F1-score (0.336, 0.316), respectively. External validation (3500 subjects) showed that the GB-based screening tool had an AUC of 0.828, which was significantly higher than that of the traditional Osteoporosis Self-Assessment Tool (OST, AUC = 0.781) via the DeLong test (z = 10.880, p < 0.0001).

Conclusion

A clinically applicable osteoporosis screening tool based on machine learning algorithms was developed and validated.