■骨质疏松症,以低骨密度(BMD)为特征,是一个日益严重的公共卫生问题。到目前为止,已经提出了几种传统的回归模型和机器学习(ML)算法来预测骨质疏松症的风险。然而,这些模型在临床应用中显示出相对较低的准确性.最近提出的深度学习(DL)方法,如深度神经网络(DNN),它可以从复杂的隐藏互动中发现知识,提供了提高预测性能的新机会。在这项研究中,我们旨在评估DNN在骨质疏松风险预测中是否能取得更好的效果.
■通过利用来自路易斯安那州骨质疏松症研究(LOS)的8,134名年龄超过40岁的受试者的髋部BMD和广泛的人口统计学和常规临床数据,我们开发并构建了一个预测骨质疏松症风险的新DNN框架,并将其在骨质疏松症风险预测中的性能与四种常规ML模型进行了比较。即随机森林(RF),人工神经网络(ANN),k-最近邻(KNN),和支持向量机(SVM),以及称为骨质疏松症自我评估工具(OST)的传统回归模型。通过接收器工作曲线下面积(AUC)和准确性评估模型性能。
■通过使用16个判别变量,我们观察到DNN方法在对骨质疏松症(髋部BMDT评分≤-1.0)和非骨质疏松症风险(髋部BMDT评分>-1.0)受试者进行分类方面取得了最佳预测性能(AUC=0.848),与其他方法相比。特征重要性分析表明,DNN模型确定的前10个最重要的变量是权重,年龄,性别,握力,高度,喝啤酒,舒张压,饮酒,烟雾年,和经济水平。此外,我们进行了子抽样分析,以评估不同数量的样本量和变量对这些测试模型的预测性能的影响.值得注意的是,我们观察到,DNN模型的表现同样良好(AUC=0.846),即使仅利用了预测骨质疏松风险的前10个最重要变量.同时,当样本量减少到原始数据集的50%时,DNN模型仍然可以实现高预测性能(AUC=0.826)。
■总而言之,我们开发了一种新的DNN模型,该模型被认为是老年人群骨质疏松症早期诊断和干预的有效算法。
UNASSIGNED: Osteoporosis, characterized by low bone mineral density (BMD), is an increasingly serious public health issue. So far, several traditional regression models and machine learning (ML) algorithms have been proposed for predicting osteoporosis risk. However, these models have shown relatively low accuracy in clinical implementation. Recently proposed deep learning (DL) approaches, such as deep neural network (DNN), which can discover knowledge from complex hidden interactions, offer a new opportunity to improve predictive performance. In this study, we aimed to assess whether DNN can achieve a better performance in osteoporosis risk prediction.
UNASSIGNED: By utilizing hip BMD and extensive demographic and routine clinical data of 8,134 subjects with age more than 40 from the Louisiana Osteoporosis Study (LOS), we developed and constructed a novel DNN framework for predicting osteoporosis risk and compared its performance in osteoporosis risk prediction with four conventional ML models, namely random forest (RF), artificial neural network (ANN), k-nearest neighbor (KNN), and support vector machine (SVM), as well as a traditional regression model termed osteoporosis self-assessment tool (OST). Model performance was assessed by area under \'receiver operating curve\' (AUC) and accuracy.
UNASSIGNED: By using 16 discriminative variables, we observed that the DNN approach achieved the best predictive performance (AUC = 0.848) in classifying osteoporosis (hip BMD T-score ≤ -1.0) and non-osteoporosis risk (hip BMD T-score > -1.0) subjects, compared to the other approaches. Feature importance analysis showed that the top 10 most important variables identified by the DNN model were weight, age, gender, grip strength, height, beer drinking, diastolic pressure, alcohol drinking, smoke years, and economic level. Furthermore, we performed subsampling analysis to assess the effects of varying number of sample size and variables on the predictive performance of these tested models. Notably, we observed that the DNN model performed equally well (AUC = 0.846) even by utilizing only the top 10 most important variables for osteoporosis risk prediction. Meanwhile, the DNN model can still achieve a high predictive performance (AUC = 0.826) when sample size was reduced to 50% of the original dataset.
UNASSIGNED: In conclusion, we developed a novel DNN model which was considered to be an effective algorithm for early diagnosis and intervention of osteoporosis in the aging population.