Department of Family Medicine, CHA Bundang Medical Center, CHA University School of Medicine, Seongnam, 13496, Republic of Korea.
Department of AI and Big Data, Swiss School of Management, 6500, Bellinzona, Switzerland.
Sci Rep. 2024 Aug 13;14(1):18792. doi: 10.1038/s41598-024-69090-3.
Machine learning (ML) models have been increasingly employed to predict osteoporosis. However, the incorporation of hair minerals into ML models remains unexplored. This study aimed to develop ML models for predicting low bone mass (LBM) using health checkup data and hair mineral analysis. A total of 1206 postmenopausal women and 820 men aged 50 years or older at a health promotion center were included in this study. LBM was defined as a T-score below - 1 at the lumbar, femur neck, or total hip area. The proportion of individuals with LBM was 59.4% (n = 1205). The features used in the models comprised 50 health checkup items and 22 hair minerals. The ML algorithms employed were Extreme Gradient Boosting (XGB), Random Forest (RF), Gradient Boosting (GB), and Adaptive Boosting (AdaBoost). The subjects were divided into training and test datasets with an 80:20 ratio. The area under the receiver operating characteristic curve (AUROC), accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and an F1 score were evaluated to measure the performances of the models. Through 50 repetitions, the mean (standard deviation) AUROC for LBM was 0.744 (± 0.021) for XGB, the highest among the models, followed by 0.737 (± 0.023) for AdaBoost, and 0.733 (± 0.023) for GB, and 0.732 (± 0.021) for RF. The XGB model had an accuracy of 68.7%, sensitivity of 80.7%, specificity of 51.1%, PPV of 70.9%, NPV of 64.3%, and an F1 score of 0.754. However, these performance metrics did not demonstrate notable differences among the models. The XGB model identified sulfur, sodium, mercury, copper, magnesium, arsenic, and phosphate as crucial hair mineral features. The study findings emphasize the significance of employing ML algorithms for predicting LBM. Integrating health checkup data and hair mineral analysis into these models may provide valuable insights into identifying individuals at risk of LBM.
机器学习（ML）模型已被越来越多地用于预测骨质疏松症。然而，将头发矿物质纳入 ML 模型的研究仍有待探索。本研究旨在使用健康检查数据和头发矿物质分析开发用于预测低骨量（LBM）的 ML 模型。共有 1206 名 50 岁或以上在健康促进中心就诊的绝经后女性和 820 名男性被纳入本研究。LBM 定义为腰椎、股骨颈或总髋区的 T 评分低于-1。患有 LBM 的个体比例为 59.4%（n=1205）。模型中使用的特征包括 50 项健康检查项目和 22 项头发矿物质。所使用的 ML 算法包括极端梯度提升（XGB）、随机森林（RF）、梯度提升（GB）和自适应提升（AdaBoost）。研究对象按 80:20 的比例分为训练数据集和测试数据集。使用受试者工作特征曲线（ROC）下面积（AUROC）、准确率、敏感度、特异性、阳性预测值（PPV）、阴性预测值（NPV）和 F1 评分来评估模型的性能。通过 50 次重复，XGB 模型的 LBM AUROC 平均值（标准偏差）为 0.744（±0.021），是所有模型中最高的，其次是 AdaBoost 的 0.737（±0.023），GB 的 0.733（±0.023）和 RF 的 0.732（±0.021）。XGB 模型的准确率为 68.7%，敏感度为 80.7%，特异性为 51.1%，PPV 为 70.9%，NPV 为 64.3%，F1 得分为 0.754。然而，这些性能指标在模型之间没有表现出明显差异。XGB 模型确定了硫、钠、汞、铜、镁、砷和磷酸盐作为头发矿物质的关键特征。研究结果强调了使用 ML 算法预测 LBM 的重要性。将健康检查数据和头发矿物质分析纳入这些模型可能为识别 LBM 风险个体提供有价值的见解。
