Aim: The National Surgery Quality Improvement Program (NSQIP) and Portsmouth Physiological and Operative Severity Score for enUmeration of Mortality and Morbidity (P‐POSSUM) are well‐established risk calculators employed by surgeons worldwide to calculate predicted surgical mortality and morbidity. Since 2008, the Hospital Authority has implemented the Surgical Outcomes Monitoring and Improvement Program (SOMIP) for auditing of 30‐day mortality in emergency surgery. In the present study, we aimed to compare the performance of this locally‐developed risk calculator with NSQIP and P‐POSSUM for 30‐day mortality predictions in patients undergoing emergency colectomy. Patients and Methods: The present study was a retrospective study of 119 patients who underwent emergency colectomy between January and December 2014 at the Department of Surgery, Queen Elizabeth Hospital, Hong Kong. The predicted mortality rate was calculated by SOMIP, NSQIP and P‐POSSUM. Data were analysed by the area under the receiver–operator characteristic curve (AUROC). Results: The overall mortality rate was 12.6 per cent (15/119). The AUROC for SOMIP was 0.908 [95 per cent confidence interval (CI): 0.845–0.970, P < 0.05), whereas the the AUROC for NSQIP and P‐POSSUM were 0.903 (95 per cent CI: 0.815–0.990, P < 0.05) and 0.842 (95 per cent CI: 0.743–0.942, P < 0.05), respectively. The SOMIP calculator provided the highest AUROC and was comparable to the other two well‐established international risk calculators. Conclusions: All three risk calculators (SOMIP, NSQIP and P‐POSSUM) showed considerable accuracy in predicting the 30‐day mortality rate. The SOMIP risk calculator was comparable to the well‐established international risk calculators NSQIP and P‐POSSUM. [ABSTRACT FROM AUTHOR]