Rui-Zhe Zheng1, Zhi-Jie Zhao2, Xi-Tao Yang3, Shao-Wei Jiang4, Yong-de Li4, Wen-Jie Li4, Xiu-Hui Li5, Yue Zhou6, Cheng-Jin Gao4, Yan-Bin Ma7, Shu-Ming Pan8, Yang Wang9. 1. Department of Neurosurgery, Huashan Hospital, Shanghai Medical College, Fudan University, Shanghai, China. 2. Department of Neurosurgery, Tongren Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China. 3. Department of Interventional Radiology, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China. 4. Department of Emergency, Xinhua Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China. 5. Department of Neurosurgery, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China. 6. School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China. 7. Department of Neurosurgery, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China. mybxj1026@aliyun.com. 8. Department of Emergency, Xinhua Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China. panshuming@xinhuamed.com.cn. 9. Department of Emergency, Xinhua Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China. wang1989727@126.com.
Abstract
OBJECTIVE: To develop and validate a radiomic prediction model using initial noncontrast computed tomography (CT) at admission to predict in-hospital mortality in patients with traumatic brain injury (TBI). METHODS: A total of 379 TBI patients from three cohorts were categorized into training, internal validation, and external validation sets. After filtering the unstable features with the minimum redundancy maximum relevance approach, the CT-based radiomics signature was selected by using the least absolute shrinkage and selection operator (LASSO) approach. A personalized predictive nomogram incorporating the radiomic signature and clinical features was developed using a multivariate logistic model to predict in-hospital mortality in patients with TBI. The calibration, discrimination, and clinical usefulness of the radiomics signature and nomogram were evaluated. RESULTS: The radiomic signature consisting of 12 features had areas under the curve (AUCs) of 0.734, 0.716, and 0.706 in the prediction of in-hospital mortality in the internal and two external validation cohorts. The personalized predictive nomogram integrating the radiomic and clinical features demonstrated significant calibration and discrimination with AUCs of 0.843, 0.811, and 0.834 in the internal and two external validation cohorts. Based on decision curve analysis (DCA), both the radiomic features and nomogram were found to be clinically significant and useful. CONCLUSION: This predictive nomogram incorporating the CT-based radiomic signature and clinical features had maximum accuracy and played an optimized role in the early prediction of in-hospital mortality. The results of this study provide vital insights for the early warning of death in TBI patients.
OBJECTIVE: To develop and validate a radiomic prediction model using initial noncontrast computed tomography (CT) at admission to predict in-hospital mortality in patients with traumatic brain injury (TBI). METHODS: A total of 379 TBI patients from three cohorts were categorized into training, internal validation, and external validation sets. After filtering the unstable features with the minimum redundancy maximum relevance approach, the CT-based radiomics signature was selected by using the least absolute shrinkage and selection operator (LASSO) approach. A personalized predictive nomogram incorporating the radiomic signature and clinical features was developed using a multivariate logistic model to predict in-hospital mortality in patients with TBI. The calibration, discrimination, and clinical usefulness of the radiomics signature and nomogram were evaluated. RESULTS: The radiomic signature consisting of 12 features had areas under the curve (AUCs) of 0.734, 0.716, and 0.706 in the prediction of in-hospital mortality in the internal and two external validation cohorts. The personalized predictive nomogram integrating the radiomic and clinical features demonstrated significant calibration and discrimination with AUCs of 0.843, 0.811, and 0.834 in the internal and two external validation cohorts. Based on decision curve analysis (DCA), both the radiomic features and nomogram were found to be clinically significant and useful. CONCLUSION: This predictive nomogram incorporating the CT-based radiomic signature and clinical features had maximum accuracy and played an optimized role in the early prediction of in-hospital mortality. The results of this study provide vital insights for the early warning of death in TBI patients.
Authors: Michael Katsnelson; Larami Mackenzie; Suzanne Frangos; Mauro Oddo; Joshua M Levine; Bryan Pukenas; Jennifer Faerber; Chuanhui Dong; W Andrew Kofke; Peter D le Roux Journal: Neurosurgery Date: 2012-05 Impact factor: 4.654
Authors: Nancy Carney; Annette M Totten; Cindy O'Reilly; Jamie S Ullman; Gregory W J Hawryluk; Michael J Bell; Susan L Bratton; Randall Chesnut; Odette A Harris; Niranjan Kissoon; Andres M Rubiano; Lori Shutter; Robert C Tasker; Monica S Vavilala; Jack Wilberger; David W Wright; Jamshid Ghajar Journal: Neurosurgery Date: 2017-01-01 Impact factor: 4.654
Authors: Simone A Dijkland; Kelly A Foks; Suzanne Polinder; Diederik W J Dippel; Andrew I R Maas; Hester F Lingsma; Ewout W Steyerberg Journal: J Neurotrauma Date: 2019-08-05 Impact factor: 5.269
Authors: David W Nelson; Harriet Nyström; Robert M MacCallum; Björn Thornquist; Anders Lilja; Bo-Michael Bellander; Anders Rudehill; Michael Wanecek; Eddie Weitzberg Journal: J Neurotrauma Date: 2010-01 Impact factor: 5.269
Authors: Pablo Perel; Miguel Arango; Tim Clayton; Phil Edwards; Edward Komolafe; Stuart Poccock; Ian Roberts; Haleema Shakur; Ewout Steyerberg; Surakrant Yutthakasemsunt Journal: BMJ Date: 2008-02-12
Authors: Ewout W Steyerberg; Nino Mushkudiani; Pablo Perel; Isabella Butcher; Juan Lu; Gillian S McHugh; Gordon D Murray; Anthony Marmarou; Ian Roberts; J Dik F Habbema; Andrew I R Maas Journal: PLoS Med Date: 2008-08-05 Impact factor: 11.069