慢性阻塞性肺疾病稳定期患者吸入装置使用不依从风险预测模型的建立与验证

目的 建立和验证慢性阻塞性肺疾病（COPD）稳定期患者吸入装置使用不依从风险预测列线图模型，为筛选高危人群、减少吸入装置使用不依从提供参考。方法 采用方便取样法，收集215例COPD稳定期患者人口学、疾病和治疗相关资料，并评估其吸入装置使用依从性。应用Lasso回归模型筛选预测因子,构建风险预测模型，采用R软件生成风险预测列线图。分别采用C-index、校正曲线和决策曲线分析模型的预测能力、预测值与实际观测值之间的一致性以及临床应用价值，通过ROC曲线下面积对模型进行内部验证。结果 215例患者中，117例（54.4%）吸入装置使用不依从。性别、文化程度、病程、急性加重次数、住院史和mMRC分级6个因子构成风险预测模型。模型C-index为0.842，校正曲线表现出良好的一致性。决策曲线表明阈值概率超过21%时模型的净获益更高。内部验证得到ROC曲线下面积为0.824。结论 COPD稳定期患者吸入装置使用不依从发生率较高；性别、文化程度、病程、急性加重次数、住院史和mMRC分级构成的列线图模型可较好地预测COPD稳定期患者吸入装置使用的不依从风险，为临床筛查高危患者提供评估工具。

Establishment of incompliance risk prediction model for inhalation device use among patients at stable phase of chronic obstructive pulmonary disease

Objective To establish and verify an incompliance risk prediction model for inhalation device use among patients at stable phase of chronic obstructive pulmonary disease (COPD). Methods Through convenient sampling method, 215 patients at stable phase of COPD were included and their demographic information, disease and treatment related data were collected. Patient compliance with inhalation device use was also measured. Lasso regression model was applied to screen predictors to establish the incompliance risk prediction model. Furthermore, R software was used to generate an incompliance risk prediction nomogram. C-index, calibration curve, and decision curve were applied to respectively analyze the prediction ability of the model, the consistency between the predicted outcomes and the actual observed outcomes, and to evaluate the clinical application value. Internal verification for the established model was performed based on the areas under the ROC curve. Results Among the 215 patients, 117 were incompliant with inhalation device use. Such 6 factors as genders, education levels, length of disease course, times of acute aggravation, history of hospitalization, mMRC levels formed the incompliance risk prediction model for inhalation device use. The C-index of this model was 0.842. The calibration curve showed good consistency. The decision curve indicated that when the threshold probability exceeded 21%, the risk score model would have higher net gains. The internal verification showed that the area under ROC curve was 0.824. Conclusion Incompliance with inhalation device use in patients at stable phase of COPD is high. The nomogram based on such 6 factors as genders,education levels,length of disease course,times of acuteaggravation, history of hospitalization, mMRC levels can well predict the incompliance risk in patients at stable phase of COPD, and serve as a tool to screen high risk patients.