In-hospital mortality after traumatic brain injury surgery: a nationwide population-based comparison of mortality predictors used in artificial neural network and logistic regression models.

OBJECT Most reports compare artificial neural network (ANN) models and logistic regression models in only a single data set, and the essential issue of internal validity (reproducibility) of the models has not been adequately addressed. This study proposes to validate the use of the ANN model for predicting in-hospital mortality after traumatic brain injury (TBI) surgery and to compare the predictive accuracy of ANN with that of the logistic regression model. METHODS The authors of this study retrospectively analyzed 16,956 patients with TBI nationwide who were surgically treated in Taiwan between 1998 and 2009. For every 1000 pairs of ANN and logistic regression models, the area under the receiver operating characteristic curve (AUC), Hosmer-Lemeshow statistics, and accuracy rate were calculated and compared using paired t-tests. A global sensitivity analysis was also performed to assess the relative importance of input parameters in the ANN model and to rank the variables in order of importance. RESULTS The ANN model outperformed the logistic regression model in terms of accuracy in 95.15% of cases, in terms of Hosmer-Lemeshow statistics in 43.68% of cases, and in terms of the AUC in 89.14% of cases. The global sensitivity analysis of in-hospital mortality also showed that the most influential (sensitive) parameters in the ANN model were surgeon volume followed by hospital volume, Charlson comorbidity index score, length of stay, sex, and age. CONCLUSIONS This work supports the continued use of ANNs for predictive modeling of neurosurgery outcomes. However, further studies are needed to confirm the clinical efficacy of the proposed model.

[1]  R. D'Agostino,et al.  External validity of predictive models: a comparison of logistic regression, classification trees, and neural networks. , 2003, Journal of clinical epidemiology.

[2]  J. Ghajar,et al.  In Reply: Guidelines for the Management of Severe Traumatic Brain Injury: 2020 Update of the Decompressive Craniectomy Recommendations. , 2020, Neurosurgery.

[3]  E. Livingston,et al.  Procedure volume as a predictor of surgical outcomes. , 2010, JAMA.

[4]  R. Deyo,et al.  Adapting a clinical comorbidity index for use with ICD-9-CM administrative databases. , 1992, Journal of clinical epidemiology.

[5]  Michael R Galarneau,et al.  Traumatic brain injury during Operation Iraqi Freedom: findings from the United States Navy-Marine Corps Combat Trauma Registry. , 2008, Journal of neurosurgery.

[6]  J. Sahuquillo,et al.  The role of surgery in traumatic brain injury , 2007, Current opinion in critical care.

[7]  A. Hyder,et al.  The impact of traumatic brain injuries: a global perspective. , 2007, NeuroRehabilitation.

[8]  D. Chang,et al.  Predictors of Inpatient Death and Complications among Postoperative Elderly Patients with Metastatic Brain Tumors , 2011, Annals of Surgical Oncology.

[9]  Richard Goldstein,et al.  The Accuracy of Artificial Neural Networks in Predicting Long‐term Outcome After Traumatic Brain Injury , 2006, The Journal of head trauma rehabilitation.

[10]  T. Sundt,et al.  Referral bias in aneurysmal subarachnoid hemorrhage. , 1993, Journal of neurosurgery.

[11]  Mohammad Ghodsi,et al.  Comparison of artificial neural network and logistic regression models for prediction of mortality in head trauma based on initial clinical data , 2005, BMC Medical Informatics Decis. Mak..

[12]  Amitabh Chak,et al.  Prediction of outcome in acute lower-gastrointestinal haemorrhage based on an artificial neural network: internal and external validation of a predictive model , 2003, The Lancet.

[13]  K. J. Dalton,et al.  Artificial neural networks for decision support in clinical medicine. , 1995, Annals of medicine.

[14]  Josh Bongard,et al.  C L I N I C a L a R T I C L E , 2022 .

[15]  A. Defillo.  Traumatic brain injury. , 2010, Journal of neurosurgery.

[16]  Stephen Ashwal,et al.  Guidelines for the determination of brain death in infants and children: An update of the 1987 Task Force recommendations* , 2011, Critical care medicine.

[17]  J. Povlishock,et al.  Guidelines for the management of severe traumatic brain injury. Editor's Commentary. , 2007, Journal of neurotrauma.

[18]  P. Reilly,et al.  Factors associated with mortality and brain injury after falls from the standing position. , 2009, The Journal of trauma.

[19]  D. Cadotte,et al.  The epidemiological trends of head injury in the largest Canadian adult trauma center from 1986 to 2007. , 2011, Journal of neurosurgery.

[20]  S. Stein,et al.  Relationship of aggressive monitoring and treatment to improved outcomes in severe traumatic brain injury. , 2010, Journal of neurosurgery.

[21]  M. McDermott,et al.  Craniotomy for meningioma in the United States between 1988 and 2000: decreasing rate of mortality and the effect of provider caseload. , 2005, Journal of neurosurgery.

[22]  Wen-Hsien Ho,et al.  Comparison of Artificial Neural Network and Logistic Regression Models for Predicting In-Hospital Mortality after Primary Liver Cancer Surgery , 2012, PloS one.

[23]  Yi Han,et al.  Overview of Artificial Neural Networks , 2009, Artificial Neural Networks.

[24]  J. Savino,et al.  An artificial neural network as a model for prediction of survival in trauma patients: validation for a regional trauma area. , 1998, The Journal of trauma.

[25]  M. D. de Jongh,et al.  Accuracy of different survival prediction models in a trauma population , 2010, The British journal of surgery.

[26]  Shigeru Katagiri,et al.  Nonlinear Dynamical Systems: Feedforward Neural Network Perspectives , 2001 .

[27]  J. Hotchkiss,et al.  Artificial neural networks and power of breathing: new approaches, expanded utility? , 2006, Critical care medicine.

[28]  J V Tu,et al.  Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. , 1996, Journal of clinical epidemiology.

[29]  S. Dikmen,et al.  Rates of major depressive disorder and clinical outcomes following traumatic brain injury. , 2010, JAMA.

[30]  G. Bukhman,et al.  Sex differences in health care-seeking behavior for acute coronary syndrome in a low income country, Peru. , 2011, Critical pathways in cardiology.

[31]  L. Pitts,et al.  Outcome after severe head injury: an analysis of prediction based upon comparison of neural network versus logistic regression analysis. , 1997, Neurological research.

[32]  R. Deyo,et al.  ADAPTING A CLINICAL COMORBIDITY USE WITH ICD-g-CM ADMINISTRATIVE INDEX FOR DATABASES , 1992 .