Villa Alessandro, Nordio Francesco, Gohel Anita
Division of Oral Medicine and Dentistry, Brigham and Women's Hospital, Boston, MA, USA.
Department of Oral Medicine, Infection and Immunity, Harvard School of Dental Medicine, Boston, MA, USA.
Gerodontology. 2016 Dec;33(4):562-568. doi: 10.1111/ger.12214. Epub 2015 Nov 17.
We investigated the prevalence of xerostomia in dental patients and built a xerostomia risk prediction model by incorporating a wide range of risk factors.
Socio-demographic data, past medical history, self-reported dry mouth and related symptoms were collected retrospectively from January 2010 to September 2013 for all new dental patients. A logistic regression framework was used to build a risk prediction model for xerostomia. External validation was performed using an independent data set to test the prediction power.
A total of 12 682 patients were included in this analysis (54.3%, females). Xerostomia was reported by 12.2% of patients. The proportion of people reporting xerostomia was higher among those who were taking more medications (OR = 1.11, 95% CI = 1.08-1.13) or recreational drug users (OR = 1.4, 95% CI = 1.1-1.9). Rheumatic diseases (OR = 2.17, 95% CI = 1.88-2.51), psychiatric diseases (OR = 2.34, 95% CI = 2.05-2.68), eating disorders (OR = 2.28, 95% CI = 1.55-3.36) and radiotherapy (OR = 2.00, 95% CI = 1.43-2.80) were good predictors of xerostomia. For the test model performance, the ROC-AUC was 0.816 and in the external validation sample, the ROC-AUC was 0.799.
The xerostomia risk prediction model had high accuracy and discriminated between high- and low-risk individuals. Clinicians could use this model to identify the classes of medications and systemic diseases associated with xerostomia.
我们调查了牙科患者中口干症的患病率，并通过纳入多种风险因素建立了口干症风险预测模型。
回顾性收集2010年1月至2013年9月期间所有新牙科患者的社会人口统计学数据、既往病史、自我报告的口干及相关症状。采用逻辑回归框架建立口干症风险预测模型。使用独立数据集进行外部验证以测试预测能力。
本分析共纳入12682例患者（54.3%为女性）。12.2%的患者报告有口干症。服用更多药物的患者（OR = 1.11，95%CI = 1.08 - 1.13）或使用消遣性药物的患者（OR = 1.4，95%CI = 1.1 - 1.9）中报告口干症的比例更高。风湿性疾病（OR = 2.17，95%CI = 1.88 - 2.51）、精神疾病（OR = 2.34，95%CI = 2.05 - 2.68）、饮食失调（OR = 2.28，95%CI = 1.55 - 3.36）和放疗（OR = 2.00，95%CI = 1.43 - 2.80）是口干症的良好预测因素。对于测试模型性能，ROC-AUC为0.816，在外部验证样本中，ROC-AUC为0.799。
口干症风险预测模型具有较高的准确性，能够区分高风险和低风险个体。临床医生可使用该模型识别与口干症相关的药物类别和全身性疾病。
