Department of Preventive Dentistry, School and Hospital of Stomatology, China Medical University, Liaoning Provincial Key Laboratory of Oral Diseases, Shenyang 110002, China.
Department of Epidemiology, School of Public Health, China Medical University, Shenyang 110122, China.
Biomed Res Int. 2020 Dec 7;2020:5348730. doi: 10.1155/2020/5348730. eCollection 2020.
Dental caries is one of the most common chronic diseases observed in elderly patients. The development of preventive strategies for dental caries in elderly individuals is vital.
The objective of the present study was to construct a generalized regression neural network (GRNN) prediction model for the risk assessment of dental caries among the geriatric residents of Liaoning, China.
A stratified equal-capacity random sampling method was used to randomly select 1144 elderly (65-74 years) residents (gender ratio 1 : 1) of Liaoning, China. Data for the oral assessment, including caries characteristics, and questionnaire survey from each participant were collected. Multivariate logistic regression analysis was then performed to identify the independent predictors. GRNN was applied to establish a prediction model for dental caries. The accuracy of the unconditional logistic regression and the GRNN early warning model was compared.
A total of 1144 patients fulfilled the requirements and completed the questionnaires. The caries rate was 68.5%, and the main associated factors were toothache history, residence area, smoking, and drinking. We randomly divided the data for the 1144 participants into a training set (915 cases) and a test set (229 cases). The optimal smoothing factor was 0.7, and the area under the receiver operating characteristic curve for the GRNN model was 0.626 (95% confidence interval, 0.544 to 0.708), with a value of 0.002. In terms of consistency, sensitivity, and specificity, the GRNN model was better than the traditional unconditional multivariate logistic regression model.
Geriatric (65-74 years) residents of Liaoning, China, have a high rate of dental caries. Residents with a history of toothache and smoking habits are more susceptible to the disease. The GRNN early warning model is an accurate and meaningful tool for screening, early diagnosis, and treatment planning for geriatric individuals with a high risk of caries.
龋齿是老年患者中最常见的慢性疾病之一。制定针对老年人龋齿的预防策略至关重要。
本研究旨在构建中国辽宁老年居民龋齿风险的广义回归神经网络（GRNN）预测模型。
采用分层等容量随机抽样方法，随机抽取中国辽宁 1144 名（男女比例 1:1）65-74 岁的老年居民。收集每位参与者的口腔评估数据，包括龋齿特征和问卷调查。然后进行多变量逻辑回归分析，以确定独立预测因素。应用 GRNN 建立龋齿预测模型。比较无条件逻辑回归和 GRNN 预警模型的准确性。
共纳入 1144 例患者，完成问卷。龋齿发生率为 68.5%，主要相关因素为牙痛史、居住区域、吸烟和饮酒。我们将 1144 名参与者的数据随机分为训练集（915 例）和测试集（229 例）。最佳平滑因子为 0.7，GRNN 模型的受试者工作特征曲线下面积为 0.626（95%置信区间，0.544 至 0.708），P 值为 0.002。在一致性、敏感性和特异性方面，GRNN 模型优于传统的无条件多变量逻辑回归模型。
中国辽宁的老年（65-74 岁）居民龋齿发生率较高。有牙痛史和吸烟习惯的居民更容易患病。GRNN 预警模型是一种准确且有意义的工具，可用于筛选、早期诊断和治疗高龋齿风险的老年个体。
