Abstract: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.