METHODS: The retrospective cohort data of 56 patients with unilateral MD who underwent ESD surgery were recorded. A stepwise regression method was used to select optimal modeling variables, and we established a logistic regression model with the outcome of vertigo after ESD. The bootstrap method was used for internal validation.
RESULTS: Potential predictors included sex, age, follow-up duration, disease course, attack duration, frequency of attack, pure-tone threshold average (PTA) of the patient\'s speech frequency, audiogram type, glycerin test results, MD subtype, and 10-year atherosclerotic cardiovascular disease risk classification. Using the stepwise regression method, we found that the optimal modeling variables were the audiogram type and PTA of the patient\'s speech frequency. The prediction model based on these two variables exhibited good discrimination [area under the receiver operating characteristic curve: 0.72 (95% confidence interval: 0.57-0.86)] and acceptable calibration (Brier score 0.21).
CONCLUSIONS: The present model based on the audiogram type and PTA of the patient\'s speech frequency was found to be useful in guidance of ESD efficacy prediction and surgery selection.
方法:记录56例接受ESD手术的单侧MD患者的回顾性队列数据。采用逐步回归方法选择最优建模变量,建立了ESD术后眩晕结局的Logistic回归模型。Bootstrap方法用于内部验证。
结果:潜在预测因素包括性别,年龄,随访持续时间,病程,攻击持续时间,攻击的频率,患者语音频率的纯音阈值平均值(PTA),听力图类型,甘油测试结果,MD亚型,和10年动脉粥样硬化性心血管疾病风险分类。使用逐步回归方法,我们发现,最佳建模变量是患者语音频率的听力图类型和PTA。基于这两个变量的预测模型表现出良好的判别[受试者工作特征曲线下面积:0.72(95%置信区间:0.57-0.86)]和可接受的校准(Brier评分0.21)。
结论:发现基于患者语音频率的听力图类型和PTA的当前模型可用于指导ESD疗效预测和手术选择。