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

Journal of Neurosurgery - Tập 118 Số 4 - Trang 746-752 - 2013
Hon‐Yi Shi1, Shiuh‐Lin Hwang2,3,4, King‐Teh Lee5,6, Chih‐Lung Lin2,3,4
1Department of Healthcare Administration and Medical Informatics, Kaohsiung Medical University, Kaohsiung, Taiwan, Republic of China.
22Neurosurgery,
3Faculty of Medicine, College of Medicine, and
4Neurosurgery
54Division of Hepatobiliary Surgery, Department of Surgery, Kaohsiung Medical University, Kaohsiung, Taiwan, Republic of China
6Division of Hepatobiliary Surgery, Department of Surgery, Kaohsiung Medical University, Kaohsiung, Taiwan, Republic of China

Tóm tắt

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.

Từ khóa


Tài liệu tham khảo

Bombardier, 2010, Rates of major depressive disorder and clinical outcomes following traumatic brain injury, 303, 1938, 10.1001/jama.2010.599

Bullock, 2007, Guidelines for the management of severe traumatic brain injury. Editor's Commentary, 24

Cadotte, 2011, The epidemiological trends of head injury in the largest Canadian adult trauma center from 1986 to 2007. Clinical article, 114, 1502, 10.3171/2010.12.JNS10808

Curry, 2005, Craniotomy for meningioma in the United States between 1988 and 2000: decreasing rate of mortality and the effect of provider caseload, 102, 977, 10.3171/jns.2005.102.6.0977

Das, 2003, Prediction of outcome in acute lower-gastrointestinal haemorrhage based on an artificial neural network: internal and external validation of a predictive model, 362, 1261, 10.1016/S0140-6736(03)14568-0

de Jongh, 2010, Accuracy of different survival prediction models in a trauma population, 97, 1805, 10.1002/bjs.7216

Defillo, 2010, Traumatic brain injury, 113, 399, 10.3171/2009.10.JNS091500

Deyo, 1992, Adapting a clinical comorbidity index for use with ICD-9-CM administrative databases, 45, 613, 10.1016/0895-4356(92)90133-8

DiRusso, 2000, An artificial neural network as a model for prediction of survival in trauma patients: validation for a regional trauma area, 49, 212, 10.1097/00005373-200008000-00006

Eftekhar, 2005, Comparison of artificial neural network and logistic regression models for prediction of mortality in head trauma based on initial clinical data, 5, 3, 10.1186/1472-6947-5-3

Farahvar, 2011, Response to intracranial hypertension treatment as a predictor of death in patients with severe traumatic brain injury. Clinical article, 114, 1471, 10.3171/2010.11.JNS101116

Forsström, 1995, Artificial neural networks for decision support in clinical medicine, 27, 509, 10.3109/07853899509002462

Galarneau, 2008, Traumatic brain injury during Operation Iraqi Freedom: findings from the United States Navy-Marine Corps Combat Trauma Registry, 108, 950, 10.3171/JNS/2008/108/5/0950

Grossman, 2011, Predictors of inpatient death and complications among postoperative elderly patients with metastatic brain tumors, 18, 521, 10.1245/s10434-010-1299-2

Hampton, 2011, Traumatic brain injury a growing problem among troops serving in today's wars, 306, 477, 10.1001/jama.2011.1092

Hotchkiss, 2006, Artificial neural networks and power of breathing: new approaches, expanded utility?, 34, 1267, 10.1097/01.CCM.0000208148.13721.AE

Hyder, 2007, The impact of traumatic brain injuries: a global perspective, 22, 341, 10.3233/NRE-2007-22502

Lang, 1997, Outcome after severe head injury: an analysis of prediction based upon comparison of neural network versus logistic regression analysis, 19, 274, 10.1080/01616412.1997.11740813

Livingston, 2010, Procedure volume as a predictor of surgical outcomes, 304, 95, 10.1001/jama.2010.905

Nakagawa, 2011, Guidelines for the determination of brain death in infants and children: an update of the 1987 Task Force recommendations, 39, 2139, 10.1097/CCM.0b013e31821f0d4f

Pastorius Benziger, 2011, Sex differences in health care-seeking behavior for acute coronary syndrome in a low income country, Peru, 10, 99, 10.1097/HPC.0b013e318223e375

Rughani, 2010, Use of an artificial neural network to predict head injury outcome. Clinical article, 113, 585, 10.3171/2009.11.JNS09857

Sandberg, 2001

Sarani, 2009, Factors associated with mortality and brain injury after falls from the standing position, 67, 954

Segal, 2006, The accuracy of artificial neural networks in predicting long-term outcome after traumatic brain injury, 21, 298, 10.1097/00001199-200607000-00003

Servadei, 2007, The role of surgery in traumatic brain injury, 13, 163, 10.1097/MCC.0b013e32807f2a94

Shamim, 2011, Emergency department predictors of tracheostomy in patients with isolated traumatic brain injury requiring emergency cranial decompression. Clinical article, 115, 1007, 10.3171/2011.7.JNS101829

Shi, 2012, Comparison of artificial neuroal network and logistic regression models for predicting in-hospital mortality after primary liver cancer surgery, 7, e35781, 10.1371/journal.pone.0035781

Stein, 2010, Relationship of aggressive monitoring and treatment to improved outcomes in severe traumatic brain injury. Clinical article, 112, 1105, 10.3171/2009.8.JNS09738

Terrin, 2003, External validity of predictive models: a comparison of logistic regression, classification trees, and neural networks, 56, 721, 10.1016/S0895-4356(03)00120-3

Tu, 1996, Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes, 49, 1225, 10.1016/S0895-4356(96)00002-9

Whisnant, 1993, Referral bias in aneurysmal subarachnoid hemorrhage, 78, 726, 10.3171/jns.1993.78.5.0726

Zou, 2008, Overview of artificial neural networks, 458, 15, 10.1007/978-1-60327-101-1_2

Thông tin
Thông tin xuất bản

Journal of Neurosurgery

Tập 118 Số 4

746-752

Thông tin tác giả