Abstract
BACKGROUND: Predicting long-term survival in intensive care unit patients with intracerebral hemorrhage (ICH) is crucial. This study aimed to develop a platelet-to-white blood cell ratio (PWR) incorporated nomogram for long-term survival prediction. METHODS: A retrospective analysis was conducted on 1,728 ICH patients in the MIMIC-IV 2.2 database. The independent prognostic value of PWR for 1-year mortality was assessed. A nomogram was developed using LASSO and Cox regression to predict 1-year survival, incorporating PWR and other factors. The performance of the nomogram was evaluated through calibration curves, area under the curve, Delong test, net reclassification index, integrated discrimination improvement, and decision curve analysis. RESULTS: The nomogram, which included age, weight, Glasgow Coma Scale (GCS) score, mechanical ventilation, glucose, red blood cell (RBC) count, blood urea nitrogen (BUN), and PWR, showed good predictive performance for 1-year survival. The C-index was 0.736 (95% CI = 0.716-0.756) for the training set and 0.766 (95% CI = 0.735-0.797) for the testing set. Higher age and ventilation increased mortality risk, while higher weight, GCS score, RBC count, and PWR decreased risk. The nomogram outperformed conventional scores. CONCLUSIONS: A nomogram incorporating PWR as a prognostic factor accurately predicts long-term survival in ICH patients. However, validation in large-scale multicenter studies and further exploration of biomarkers are needed.