Prediction of Mortality in Patients with Isolated Traumatic Subarachnoid Hemorrhage Using a Decision Tree Classifier: A Retrospective Analysis Based on a Trauma Registry System

Background: In contrast to patients with traumatic subarachnoid hemorrhage (tSAH) in the presence of other types of intracranial hemorrhage, the prognosis of patients with isolated tSAH is good. The incidence of mortality in these patients ranges from 0–2.5%. However, few data or predictive models are available for the identification of patients with a high mortality risk. In this study, we aimed to construct a model for mortality prediction using a decision tree (DT) algorithm, along with data obtained from a population-based trauma registry, in a Level 1 trauma center. Methods: Five hundred and forty-five patients with isolated tSAH, including 533 patients who survived and 12 who died, between January 2009 and December 2016, were allocated to training (n = 377) or test (n = 168) sets. Using the data on demographics and injury characteristics, as well as laboratory data of the patients, classification and regression tree (CART) analysis was performed based on the Gini impurity index, using the rpart function in the rpart package in R. Results: In this established DT model, three nodes (head Abbreviated Injury Scale (AIS) score ≤4, creatinine (Cr) <1.4 mg/dL, and age <76 years) were identified as important determinative variables in the prediction of mortality. Of the patients with isolated tSAH, 60% of those with a head AIS >4 died, as did the 57% of those with an AIS score ≤4, but Cr ≥1.4 and age ≥76 years. All patients who did not meet the above-mentioned criteria survived. With all the variables in the model, the DT achieved an accuracy of 97.9% (sensitivity of 90.9% and specificity of 98.1%) and 97.7% (sensitivity of 100% and specificity of 97.7%), for the training set and test set, respectively. Conclusions: The study established a DT model with three nodes (head AIS score ≤4, Cr <1.4, and age <76 years) to predict fatal outcomes in patients with isolated tSAH. The proposed decision-making algorithm may help identify patients with a high risk of mortality.

[1]  J. Takeuchi,et al.  Experimental Studies on the Nervous Control of the Renal Circulation-Effect of the Electrical Stimulation of the Diencephalon on the Renal Circulation , 1960 .

[2]  Shiun-Yuan Hsu,et al.  Differences between the sexes in motorcycle-related injuries and fatalities at a Taiwanese level I trauma center , 2017, Biomedical journal.

[3]  P. Kasbekar,et al.  A Decision Tree Analysis of Diabetic Foot Amputation Risk in Indian Patients , 2017, Front. Endocrinol..

[4]  M. Lawton,et al.  Hypernatremia predicts adverse cardiovascular and neurological outcomes after SAH , 2006, Neurocritical care.

[5]  Li-Yen Chang,et al.  Analysis of traffic injury severity: an application of non-parametric classification tree techniques. , 2006, Accident; analysis and prevention.

[6]  R. Marshall,et al.  Multimodal early rehabilitation and predictors of outcome in survivors of severe traumatic brain injury. , 2008, The Journal of trauma.

[7]  Grant W. Mallory,et al.  Triage Patterns of Traumatic Subarachnoid Hemorrhage: Is Referral to a Tertiary Care Center Necessary? , 2017, World neurosurgery.

[8]  D. Menon,et al.  Predicting the outcome for individual patients with traumatic brain injury: a case-based review , 2016, British journal of neurosurgery.

[9]  W. Poon,et al.  Neurological outcome in patients with traumatic brain injury and its relationship with computed tomography patterns of traumatic subarachnoid hemorrhage. , 2011, Journal of neurosurgery.

[10]  P. Kilgo,et al.  Age thresholds for increased mortality of three predominant crash induced head injuries. , 2008, Annals of advances in automotive medicine. Association for the Advancement of Automotive Medicine. Annual Scientific Conference.

[11]  H. Phelan,et al.  Does isolated traumatic subarachnoid hemorrhage merit a lower intensity level of observation than other traumatic brain injury? , 2014, Journal of neurotrauma.

[12]  Stan Matwin,et al.  A Tree-Based Decision Model to Support Prediction of the Severity of Asthma Exacerbations in Children , 2010, Journal of Medical Systems.

[13]  Hester F. Lingsma,et al.  External Validation of the International Mission for Prognosis and Analysis of Clinical Trials in Traumatic Brain Injury: Prognostic Models for Traumatic Brain Injury on the Study of the Neuroprotective Activity of Progesterone in Severe Traumatic Brain Injuries Trial. , 2016, Journal of neurotrauma.

[14]  D. Orringer,et al.  Cumulative incidence and predictors of neurosurgical interventions following nonsevere traumatic brain injury with mildly abnormal head imaging findings , 2012, The journal of trauma and acute care surgery.

[15]  M. Braddock,et al.  Classification and regression tree analysis of acute‐on‐chronic hepatitis B liver failure: Seeing the forest for the trees , 2017, Journal of viral hepatitis.

[16]  R. Latifi,et al.  Traumatic subarachnoid hemorrhage due to motor vehicle crash versus fall from height: a 4-year epidemiologic study. , 2014, World neurosurgery.

[17]  D. McArthur,et al.  Hemodynamically significant cerebral vasospasm and outcome after head injury: a prospective study. , 1997, Journal of neurosurgery.

[18]  Ewout Steyerberg,et al.  Predicting outcome after traumatic brain injury: practical prognostic models based on large cohort of international patients , 2008, BMJ : British Medical Journal.

[19]  J. Wilberger,et al.  The clinical significance of isolated traumatic subarachnoid hemorrhage , 2013, The journal of trauma and acute care surgery.

[20]  N. Lipsman,et al.  The clinical significance of isolated traumatic subarachnoid hemorrhage in mild traumatic brain injury: A meta-analysis , 2017, Journal of Trauma and Acute Care Surgery.

[21]  N. King,et al.  External validation of the CRASH and IMPACT prognostic models in severe traumatic brain injury. , 2014, Journal of neurotrauma.

[22]  T. C. Stewart,et al.  Hypernatremia is associated with increased risk of mortality in pediatric severe traumatic brain injury. , 2013, Journal of neurotrauma.

[23]  J. Cruickshank,et al.  The stress response in subarachnoid haemorrhage and head injury. , 1990, Acta neurochirurgica. Supplementum.

[24]  C. Hsieh,et al.  Motorcycle-related hospitalizations of the elderly , 2017, Biomedical journal.

[25]  Yuchiao Chang,et al.  Patients with traumatic subarachnoid hemorrhage are at low risk for deterioration or neurosurgical intervention , 2013, The journal of trauma and acute care surgery.

[26]  Elias Zintzaras,et al.  A tree-based decision rule for identifying profile groups of cases without predefined classes: application in diffuse large B-cell lymphomas , 2007, Comput. Biol. Medicine.

[27]  G. Sung,et al.  Prognostic Significance of Hypernatremia and Hyponatremia among Patients with Aneurysmal Subarachnoid Hemorrhage , 2002, Neurosurgery.

[28]  P. Sipponen,et al.  PROGNOSIS OF SEVERE BRAIN INJURY , 1970, Acta neurologica Scandinavica.

[29]  J. LeeJonathan,et al.  Comprehensive Assessment of Isolated Traumatic Subarachnoid Hemorrhage , 2014 .

[30]  S. Ross,et al.  Epidemiology of blunt head injury victims undergoing ED cranial computed tomographic scanning. , 2006, The American journal of emergency medicine.

[31]  John H. Zhang,et al.  Traumatic subarachnoid hemorrhage: our current understanding and its evolution over the past half century , 2006, Neurological research.

[32]  H. Karibe,et al.  Delayed Deterioration in Isolated Traumatic Subarachnoid Hemorrhage. , 2016, World neurosurgery.

[33]  E. Steyerberg,et al.  Multivariable prognostic analysis in traumatic brain injury: results from the IMPACT study. , 2007, Journal of neurotrauma.

[34]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[35]  S. Wisniewski,et al.  Classification and Regression Tree (CART) analysis to predict influenza in primary care patients , 2016, BMC Infectious Diseases.

[36]  J. J. Lee,et al.  Comprehensive assessment of isolated traumatic subarachnoid hemorrhage. , 2014, Journal of neurotrauma.

[37]  M. Ebell,et al.  External Validation of Two Classification and Regression Tree Models to Predict the Outcome of Inpatient Cardiopulmonary Resuscitation , 2017, Journal of intensive care medicine.

[38]  Z. Balogh,et al.  AIS>2 in at least two body regions: a potential new anatomical definition of polytrauma. , 2012, Injury.

[39]  G. Murray,et al.  Traumatic Subarachnoid Hemorrhage: Demographic and Clinical Study of 750 Patients from the European Brain Injury Consortium Survey of Head Injuries , 2002, Neurosurgery.

[40]  S. Ross,et al.  Isolated traumatic brain injury: age is an independent predictor of mortality and early outcome. , 2002, The Journal of trauma.

[41]  P. Foreman,et al.  The nonsurgical nature of patients with subarachnoid or intraparenchymal hemorrhage associated with mild traumatic brain injury. , 2015, Journal of neurosurgery.

[42]  C. Compagnone,et al.  Factors Associated with Neurological Outcome and Lesion Progression in Traumatic Subarachnoid Hemorrhage Patients , 2005, Neurosurgery.

[43]  Tzu-Kang Lin,et al.  The impact of traumatic subarachnoid hemorrhage on outcome: A study with grouping of traumatic subarachnoid hemorrhage and transcranial Doppler sonography , 2012, The journal of trauma and acute care surgery.

[44]  G. Tomei,et al.  PATIENTS WITH MODERATE HEAD INJURY: A PROSPECTIVE MULTICENTER STUDY OF 315 PATIENTS , 2009, Neurosurgery.