Related Experiment Video
Updated: Sep 5, 2025
07:31
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
7.2K
Polytrauma scoring revisited: prognostic validity and usability in daily clinical practice
Robert Girshausen1, Klemens Horst1, Christian Herren1
1Department of Orthopedics, Trauma and Reconstructive Surgery and Harald Tscherne Laboratory, University Hospital RWTH Aachen, Pauwelsstraße 30, 52074, Aachen, Germany.
Summary
The Risk, Injury, Severity, Case (RISC II) score demonstrated superior accuracy in predicting mortality for severely injured patients compared to other trauma and intensive care unit (ICU) scores. Simpler scores showed inferior predictive capabilities.
Area of Science:
- Trauma surgery
- Critical care medicine
- Medical informatics
Background:
- Trauma scores are crucial for assessing injury severity and guiding treatment in critically injured patients.
- Existing scores vary significantly in complexity, usability, and prognostic accuracy.
- A comprehensive comparison of established and novel trauma and ICU scores is needed.
Purpose of the Study:
- To compare the prognostic accuracy of various well-established and recently developed trauma and intensive care unit (ICU) scores.
- To identify the most effective score for predicting in-hospital mortality in severely injured patients.
Main Methods:
- Retrospective analysis of 444 severely injured patients (Age ≥ 18 years, Injury Severity Score ≥ 16) treated at a level I trauma center (2010-2015).
- In-hospital mortality was the primary endpoint.
- Evaluated predictive performance of Injury Severity Score (ISS), Acute Physiology and Chronic Health Evaluation II (APACHE II), Revised Trauma Score (RTS), Marshall Score, Sequential Organ Failure Assessment (SOFA), New Injury Severity Score (NISS), Risk, Injury, Severity, Case II (RISC II), Early Assessment of Severity (EAC), and Patient Trauma Grading Scale (PTGS) using correlation analysis and receiver operating characteristic (ROC) curves.
Main Results:
- RISC II exhibited the highest predictive accuracy for mortality, with an area under the ROC curve (AUROC) of 0.92.
- Established ICU scores like APACHE II (AUROC 0.81), SOFA (AUROC 0.70), and Marshall Score (AUROC 0.69) also demonstrated significant predictive value.
- Simpler scores such as ISS, NISS, RTS, EAC, and PTGS showed inferior mortality prediction compared to RISC II.
Conclusions:
- RISC II is the most effective score for predicting mortality in severely injured patients.
- While established ICU scores are valuable, simpler trauma-specific scores have limited prognostic accuracy for mortality.
- The findings highlight the importance of selecting appropriate scoring systems for accurate prognostication in trauma care.
