简介:AbstractBackground:There are an increasing number of patients with oral sensory complaints (OSCs) presenting to our dental clinic. For most dentists, it is difficult to distinguish burning mouth syndrome (BMS) from other oral mucosal diseases that may cause symptoms such as burning mouth. It is beneficial to effectively distinguish OSC patients to reduce misdiagnosis and eliminate burning symptoms as much as possible.Methods:Patients with oral burning sensations in the oral mucosal disease clinic were collected from the Peking University Hospital of Stomatology between September 1, 2014 and December 31, 2018. After excluding oral candidiasis, anemic stomatitis, dental material allergy, and other diseases from patients with oral sensory complaints, basic conditions such as gender, age, education level, job status, hyperglycemia, hypertension, hyperlipidemia, history of brain abnormalities, history of cervical spondylitis, history of thyroid disease, history of thyroid disease and insomnia were obtained. The BMS patients were compared with the control group. The t test and Chi-square test were used for statistical analysis to compare the clinical symptoms of these diseases and explore the risk factors for BMS.Results:In this case-control study, 395 patients (321 females and 74 males, mean age 55.26 ± 10.51 years) with oral sensory complaints and 391 healthy controls (281 females and 110 males, mean age 47.11 ± 13.10 years) were enrolled, among which, 8.4% (33/395) had oral candidiasis, 1.3% (5/395) had dental material allergy, 0.8% (3/395) had anemic stomatitis and 0.5% (2/395) had lichen planus. A total of 352 patients were eventually diagnosed with BMS. Anxiety and depression were more severe in BMS patients, as were the incidences of sleep disorders and brain abnormalities. Logistic regression analysis showed that age (odds ratio [OR]= 2.79, 95% confidence interval [CI]: 1.61-4.83, P < 0.001), total cholesterol level (OR= 2.92, 95% CI: 1.32-6.50, P = 0.009) and anxiety score (OR = 1.75, 95% CI: 1.01-2.77, P = 0.017) significantly increased the incidence of BMS. Patients with hyperglycemia (OR = 0.46, 95% CI: 0.23-0.89, P = 0.022), low body mass index (BMI: OR = 0.57, 95% CI: 0.34-0.93, P = 0.026) and low education level (OR = 3.43, 95% CI: 1.91-6.15, P < 0.001) were more likely to suffer from BMS.Conclusions:Oral candidiasis, anemic stomatitis, and dental material allergy with burning symptoms should be excluded from patients with BMS. It is recommended to conduct a questionnaire survey (including anxiety and depression), blood cell analysis, and salivary fungus culture for all patients with an oral burning sensation. It is necessary to conduct a patch test on patients with oral burning sensations and metal restorations.
简介:AbstractBackground:Blood glucose control is closely related to type 2 diabetes mellitus (T2DM) prognosis. This multicenter study aimed to investigate blood glucose control among patients with insulin-treated T2DM in North China and explore the application value of combining an elastic network (EN) with a machine-learning algorithm to predict glycemic control.Methods:Basic information, biochemical indices, and diabetes-related data were collected via questionnaire from 2787 consecutive participants recruited from 27 centers in six cities between January 2016 and December 2017. An EN regression was used to address variable collinearity. Then, three common machine learning algorithms (random forest [RF], support vector machine [SVM], and back propagation artificial neural network [BP-ANN]) were used to simulate and predict blood glucose status. Additionally, a stepwise logistic regression was performed to compare the machine learning models.Results:The well-controlled blood glucose rate was 45.82% in North China. The multivariable analysis found that hypertension history, atherosclerotic cardiovascular disease history, exercise, and total cholesterol were protective factors in glycosylated hemoglobin (HbA1c) control, while central adiposity, family history, T2DM duration, complications, insulin dose, blood pressure, and hypertension were risk factors for elevated HbA1c. Before the dimensional reduction in the EN, the areas under the curve of RF, SVM, and BP were 0.73, 0.61, and 0.70, respectively, while these figures increased to 0.75, 0.72, and 0.72, respectively, after dimensional reduction. Moreover, the EN and machine learning models had higher sensitivity and accuracy than the logistic regression models (the sensitivity and accuracy of logistic were 0.52 and 0.56; RF: 0.79, 0.70; SVM: 0.84, 0.73; BP-ANN: 0.78, 0.73, respectively).Conclusions:More than half of T2DM patients in North China had poor glycemic control and were at a higher risk of developing diabetic complications. The EN and machine learning algorithms are alternative choices, in addition to the traditional logistic model, for building predictive models of blood glucose control in patients with T2DM.