Development of non-invasive diabetes risk prediction models as decision support tools designed for application in the dental clinical environment.
Development of non-invasive diabetes risk prediction models as decision support tools designed for application in the dental clinical environment.
复制标题
DOI：
10.1016/j.imu.2019.100254
复制
发表时间：
2019-01-01
影响因子：
--
通讯作者：
Acharya, Amit
中科院分区：
文献类型：
--
作者：
Hegde, Harshad;Shimpi, Neel;Acharya, Amit
目的是开发一种预测模型，使用来自综合电子健康记录（iEHR）的医疗-牙科数据来识别牙科环境中未确诊的糖尿病（DM）患者。在进行分析之前，对从Marshfield Clinic Health System数据仓库检索的回顾性数据进行了预处理。从预处理的数据集中提取一个子集，用于衍生预测模型的外部评估（Nvalidation）。此外，还创建了30%-70%、40%-60%和50%-50%病例对照比的子集用于培训/测试。对所有数据集进行特征选择。评估了四种机器学习（ML）分类器：逻辑回归（LR），多层感知器（MLP），支持向量机（SVM）和随机森林（RF）。在Nvalidation上评价模型性能。我们共检索到5319例病例和36,224例对照。从最初的116个医疗和牙科特征中，在进行特征选择后使用了107个。RF应用于50%-50%的病例对照比优于其他预测模型，Nvalidation达到总准确度（94.14%），灵敏度（0.941），特异性（0.943），F-测量（0.941），Mathews相关系数（0.885）和受试者工作曲线下面积（0.972）。未来的发展方向包括将这种预测模型纳入iEHR作为临床决策支持工具，以筛选和检测有DM风险的患者，从而触发随访和牙科医生和医生之间的综合护理提供转诊。
The objective was to develop a predictive model using medical-dental data from an integrated electronic health record (iEHR) to identify individuals with undiagnosed diabetes mellitus (DM) in dental settings. Retrospective data retrieved from Marshfield Clinic Health System's data-warehouse was pre-processed prior to conducting analysis. A subset was extracted from the preprocessed dataset for external evaluation (Nvalidation) of derived predictive models. Further, subsets of 30%-70%, 40%-60% and 50%-50% case-to-control ratios were created for training/testing. Feature selection was performed on all datasets. Four machine learning (ML) classifiers were evaluated: logistic regression (LR), multilayer perceptron (MLP), support vector machines (SVM) and random forests (RF). Model performance was evaluated on Nvalidation. We retrieved a total of 5319 cases and 36,224 controls. From the initial 116 medical and dental features, 107 were used after performing feature selection. RF applied to the 50%-50% case-control ratio outperformed other predictive models over Nvalidation achieving a total accuracy (94.14%), sensitivity (0.941), specificity (0.943), F-measure (0.941), Mathews-correlation-coefficient (0.885) and area under the receiver operating curve (0.972). Future directions include incorporation of this predictive model into iEHR as a clinical decision support tool to screen and detect patients at risk for DM triggering follow-ups and referrals for integrated care delivery between dentists and physicians.