Predictive performance of ISS and NISS for clinical outcomes in severely injured trauma patients: a retrospective registry study

Abstract

Background: The Injury Severity Score (ISS) and New Injury Severity Score (NISS) are widely used in evaluation of injury severity in trauma patients. The aim of this study is to assess the predictive accuracy of these scoring systems on clinical outcomes. Methods: We conducted a retrospective registry study of 1,112 severely injured trauma patients (NISS ≥ 16) treated at Tampere University Hospital (TAUH) between 2015 and 2024. Outcomes included in-hospital mortality, prolonged hospital and ICU stay (≥ 75th percentile), in-hospital intubation, and blood transfusions. Predictive performance was assessed using the area under the receiver operating characteristic curve (AUC) and the Hosmer-Lemeshow (H-L) test for calibration. Subgroup analyses were performed for patients with significant (AIS ≥ 3) head, thorax, and extremity injuries. Results: A total of 848 (76%) patients had a higher NISS than ISS with a median increase of 9 points. Both scoring systems generally demonstrated fair to considerable (0.7 < AUC < 0.9) discrimination for mortality and intubation, and poor to fair (0.6 < AUC < 0.8) discrimination for blood transfusions and prolonged hospital/ICU stay. ISS had superior discrimination for blood transfusions in the total cohort (AUC: 0.669 vs. 0.630, p = 0.019), head (AUC: 0.737 vs. 0.672, p = 0.004), and thorax (AUC: 0.656 vs. 0.613, p = 0.006) subgroups, and for intubation in the head injury subgroup (AUC: 0.817 vs. 0.787 p = 0.038). Conversely, NISS outperformed ISS for predicting prolonged hospital stay in the extremity subgroup (AUC 0.654 vs. 0.585, p = 0.003). Conclusions: Contrary to its theoretical advantages, NISS does not broadly outperform ISS in severe trauma. ISS remains an equal or superior scoring system for predicting many clinical outcomes. Level of evidence: III.