OBJECTIVES: The aim of this study is to validate Nosocomial Pneumonia Mortality Prediction (NPMP) tool, developed in our hospital in comparison with various standard severity assessment scoring systems to predict in-hospital mortality in patients with nosocomial pneumonia. METHODS: A prospective cohort study was conducted in a tertiary care hospital. One hundred patients who were admitted in the Intensive Care Units (ICU) and general wards, who developed pneumonia after > 48 hours of admission were included in the study. The clinical variables required for each of the scoring systems were collected on the day of pneumonia diagnosis. The NPMP tool calculates mortality using seven dichotomous variables which include mechanical ventilation, immunosuppression, liver insufficiency, APACHE II score >20, male sex, age >60 years and pulmonary disease The predictive ability of the NPMP tool was compared with APACHE II, Mortality Probability Model (MPM) II and Simplified Acute Physiology Score (SAPS) II. The outcome measure was hospital death. The predictive accuracy of the various mortality prediction models was analyzed by calculating the area under the receiver operating characteristic (ROC) curve for each of the models. RESULTS: The mortality rate for the study population was 44%. All the four scoring systems were similar in their predictive ability. Discrimination was fairly good for the developed NPMP tool (ROC AUC: 0.75; 95% CI: 0.650-0.828; p<0.0001). It was on a par with APACHE II (ROC AUC: 0.75; 95% CI: 0.653-0.831; p<0.0001), MPM II(ROC AUC: 0.74; 95% CI: 0.637-0.818; p<0.0001) and SAPS II (ROC AUC: 0.75; 95% CI: 0.656-0.833; p<0.0001). CONCLUSIONS: The NPMP tool is comparable to other widely used tools to predict mortality in patients with nosocomial pneumonia. This will be a useful alternative to aid physicians in risk stratification and consequently optimize therapy in such patients as NPMP can be relatively easily calculated.