Goals of end-of-life care must be adapted to the needs of patients with chronic pulmonary disease (COPD) who are in the last phase of life. However, identification of those patients is limited by 1) moderate performances of existing prognostic models, and 2) limited validation of the often-recommended surprise question (SQ). We prospectively included COPD patients from five hospitals in the Netherlands to develop a clinical prediction model to predict 1-year mortality in patients with COPD. The ADO-SQ model, which consists of the ADO model (Age, Dyspnea, airflow Obstruction) and SQ, offers improved discriminative performance for predicting 1-year mortality compared to the SQ and ADO. A nomogram and web application were developed.