Development and validation of a mortality predictive model for ICU patients with primary pulmonary hypertension

There is a lack of an effective prognostic model for predicting outcomes in patients with primary pulmonary hypertension (PPH). A retrospective analysis was conducted on PPH patients from MIMIC and eICU databases. A predictive model was developed to assess mortality risk. The Consistency Index (C-index) and Receiver Operating Characteristic (ROC) curve were utilized to assess the overall performance of the model and its discriminatory capacity. The model's calibration and clinical applicability were assessed through calibration curve and decision curve analysis (DCA). The nomogram was employed for visual representation of the model. The study included 420 patients, 260 in the development group, 104 in the internal validation group and 56 in the external validation group. The predictive model's risk factors included age, respiratory rate, red blood cell distribution width, glucose, and SAPS II. The model demonstrated C-indexes of 0.736 and 0.696 in the development and internal validation groups, respectively. The ROC curves for the development, internal validation and external validation groups demonstrated robust discriminatory capabilities. The calibration curves indicated a slope close to 1, suggesting good calibration of the model. Additionally, DCA analysis revealed the model offered significant clinical benefits across a wide range of thresholds. The model showed good discrimination ability, accuracy and clinical application value in predicting the prognosis of patients with PPH.