Objective In an effort to establish a reference framework for the prevention and treatment of disorders of consciousness (DOC) in patients with chronic obstructive pulmonary disease (COPD), we aimed to create and validate a nomogram prediction model for the risk of developing DOC in this specific population.
Methods Two hundred and twenty patients who were hospitalized and discharged in the Lu'an People's Hospital from January 2016 to August 2023 were retrospectively analyzed. 154 patients were randomly selected according to the 7:3 ratio to establish the model, and the remaining 66 cases were internally validated. Referring to the definition of DOC in the guidelines issued by the American Academy of Rehabilitation Medicine, they were divided into COPD group and COPD + DOC group, and logistic regression was used to analyze the factors influencing COPD combined with DOC. Following this, a nomogram model was developed using R to predict the likelihood of DOC within this specific population. The model's predictive performance was then evaluated, including the assessment of the area under the curve (AUC) of the receiver operating characteristic (ROC) and decision curve analysis (DCA). Additionally, the model was internally validated using the Bootstrap resampling method with 1000 iterations.
Results The results of multifactorial analysis showed PaCO2, HCT, Smoking index≥400, Hospital acute exacerbation≥2/year, and Hypertension as the influencing factors of COPD + DOC. The nomogram created by the above influencing factors showed good performance in both the training set (AUC of 0.890) and the validation set (AUC of 0.873), in addition the calibration curves represented a good calibration of the model.
Conclusion The nomogram prediction model built based on the above mentioned influencing factors of COPD combined with DOC has good performance and provides a reference for the prevention and control of DOC in COPD patients who are at high risk of DOC.