Predicting Outcome in Traumatic Brain Injury: Development of a Novel Computerized Tomography Classification System (Helsinki Computerized Tomography Score) BACKGROUND: Early computerized tomography (CT) abnormalities are important predictors of outcome after traumatic brain injury (TBI). OBJECTIVE: To develop a novel CT scoring system (Helsinki CT score) and to compare it with the Marshall CT classification and the Rotterdam CT score in predicting long-term outcome of patients with TBI. METHODS: Eight hundred sixty-nine consecutive TBI patients were included in this open-cohort, retrospective, single-center study. Logistic regression was used to develop the Helsinki CT score. The scores from the Marshall, Rotterdam, and Helsinki CT scoring methods were added to a clinical model based on age, motor score, and pupils to evaluate their value in predicting outcome. Internal validity was assessed by a bootstrap technique and expressed as area under the curve (AUC). Outcome was 6-month unfavorable neurological outcome and mortality. RESULTS: Variables included in the Helsinki CT score were bleeding type and size, intra- ventricular hemorrhage, and suprasellar cisterns. In the present data set, the performance of the Helsinki CT score was superior to that of the Marshall CT and Rotterdam CT scores (AUC, 0.74-0.75 vs 0.63-0.70; P , .001). Addition of the Helsinki CT score modestly increased prognostic performance of the clinical model (AUC neurological outcome 10.02 [P = .002]; AUC mortality, 10.01 [ P = .21]). In contrast, the Marshall and Rotterdam CT scores were of no additional predictive value to the clinical model (P . .05). CONCLUSION: Use of the novel Helsinki CT score improved outcome prediction accu- racy, and the Helsinki CT score is a feasible alternative to the Rotterdam and Marshall CT systems. External validation of the Helsinki CT score is advocated to show generalizability. KEY WORDS: Computerized tomography, Helsinki CT, Marshall CT, Prediction model, Prognosis, Rotterdam CT, Sensitivity and specificity, Traumatic brain injury Neurosurgery 75:632–647, 2014 DOI: 10.1227/NEU.0000000000000533 www.neurosurgery-online.com T he use of prognostic models is becoming increasingly important in traumatic brain injury (TBI) research for baseline risk stratification in clinical trials and standardization of case-mix in comparative effectiveness research. 1 Clinically, TBI is often classified according to the Glasgow Coma Scale (GCS) into mild, moderate, and severe. 2 Although GCS is of great descriptive value and is one of the strongest predictors of outcome in TBI, early structural pathological abnormalities detected by computerized tomography (CT) may be of similar predictive value. 3-5 Furthermore, GCS is subject to error resulting from, for instance, Rahul Raj, PhD(c), BM* Jari Siironen, MD, PhD* Markus B. Skrifvars, MD, PhD‡ Juha Hernesniemi, MD, PhD* Riku Kivisaari, MD, PhD* *Departments of Neurosurgery and ‡Intensive Care, Helsinki University Hospital, Helsinki, Finland Correspondence: Rahul Raj, PhD(c), BM, Department of Neurosurgery, Helsinki University Hospital, Topeliuksenkatu 5, PB-266, 00029 HUS, Finland. E-mail: rahul.raj@hus.fi, rahul.raj@helsinki.fi Received, May 29, 2014. Accepted, August 7, 2014. Published Online, August 29, 2014. Copyright © 2014 by the Congress of Neurological Surgeons. WHAT IS THIS BOX? A QR Code is a matrix barcode readable by QR scanners, mobile phones with cameras, and smartphones. The QR Code above links to Supplemental Digital Content from this article. ABBREVIATIONS: AOR, adjusted odds ratio; AUC, area under the receiver-operating curve; CI, confi- dence interval; EDH, epidural hematoma; GCS, Glasgow Coma Scale; GOS, Glasgow Outcome Scale; ICH, intracerebral hemorrhage; IMPACT, International Mission for Prognosis and Analysis of Clinical Trials in TBI; IVH, intraventricular hem- orrhage; SDH, subdural hematoma; TBO, traumatic brain injury; tSAH, traumatic subarachnoid hemorrhage Supplemental digital content is available for this article. Direct URL citations appear in the printed text and are provided in the HTML and PDF versions of this article on the journal’s Web site (www.neurosurgery-online.com). RESEARCH—HUMAN—CLINICAL STUDIES RESEARCH—HUMAN—CLINICAL STUDIES 632 | VOLUME 75 | NUMBER 6 | DECEMBER 2014 www.neurosurgery-online.com Copyright © Congress of Neurological Surgeons. Unauthorized reproduction of this article is prohibited