To explore the predictive value of HACOR score [heart rate (H), acidosis (A), consciousness (C), oxygenation (O), and respiratory rate (R)] on the clinical outcome of non-invasive positive pressure ventilation in patients with pulmonary encephalopathy due to chronic obstructive pulmonary disease (COPD). A prospective study was conducted. The patients with COPD combined with pulmonary encephalopathy who were admitted to Henan Provincial People's Hospital from January 1, 2017 to June 1, 2021 and initially received non-invasive positive pressure ventilation were enrolled. Besides non-invasive positive pressure ventilation, standard medical treatments were delivered to these patients according to guidelines. The need for endotracheal intubation was judged as failure of non-invasive ventilation treatment. Early failure was defined as the need for endotracheal intubation within 48 hours of treatment, and late failure was defined as the need for endotracheal intubation 48 hours and later. The HACOR score at different time points after non-invasive ventilation, the length of intensive care unit (ICU) stay, the total length of hospital stay, and the clinical outcome were recorded. The above indexes of patients with non-invasive ventilation were compared between successful and failed groups. The receiver operator characteristic curve (ROC curve) was drawn to evaluate the predictive effect of HACOR score on the failure of non-invasive positive pressure ventilation in the treatment of COPD with pulmonary encephalopathy. A total of 630 patients were evaluated, and 51 patients were enrolled, including 42 males (82.35%) and 9 females (17.65%), with a median age of 70.0 (62.0, 78.0) years old. Among the 51 patients, 36 patients (70.59%) were successfully treated with non-invasive ventilation and discharged from the hospital eventually, and 15 patients (29.41%) failed and switched to invasive ventilation, of which 10 patients (19.61%) were defined early failure, 5 patients (9.80%) were late failure. The length of ICU and the total length of hospital stay of the non-invasive ventilation successful group were significantly longer than those of the non-invasive ventilation failure group [length of ICU stay (days): 13.0 (10.0, 16.0) vs. 5.0 (3.0, 8.0), total length of hospital stay (days): 23.0 (12.0, 28.0) vs. 12.0 (9.0, 15.0), both P < 0.01]. The HACOR score of patients at 1-2 hours in the non-invasive ventilation failure group was significantly higher than that in the successful group [10.47 (6.00, 16.00) vs. 6.00 (3.25, 8.00), P < 0.05]. However, there was no significant difference in HACOR score before non-invasive ventilation and at 3-6 hours between the two groups. The ROC curve showed that the area under the ROC curve (AUC) of 1-2 hour HACOR score after non-invasive ventilation for predicting non-invasive ventilation failure in COPD patients with pulmonary encephalopathy was 0.686, and the 95% confidence interval (95%CI) was 0.504-0.868. When the best cut-off value was 10.50, the sensitivity was 60.03%, the specificity was 86.10%, positive predictive value was 91.23%, and negative predictive value was 47.21%. Non-invasive positive pressure ventilation could prevent 70.59% of COPD patients with pulmonary encephalopathy from intubation. HACOR score was valuable to predict non-invasive positive pressure ventilation failure in pulmonary encephalopathy patients due to COPD.