Jinlin Wu1, Juntao Qiu1, Enzehua Xie1, Wenxiang Jiang1, Rui Zhao1, Jiawei Qiu1, Mohammad A Zafar2, Yan Huang3, Cuntao Yu1. 1. Department of Cardiovascular Surgery, State Key Laboratory of Cardiovascular Disease, Fuwai Hospital, National Center for Cardiovascular Disease, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100037, China. 2. Aortic Institute at Yale-New Haven Hospital, Yale University School of Medicine, New Haven, CT, USA. 3. School of Acu-moxibustion and Tuina, Beijing University of Chinese Medicine, Beijing 100029, China.
Abstract
BACKGROUND: This study is to establish prediction tools for in-hospital rupture of type A aortic dissection (TAAD) patients, to better guide emergency surgical triage and patient counselling. METHODS: We retrospectively evaluated 1,133 consecutive patients with TAAD from January 2010 to December 2016. The study population was divided into training and testing datasets in a 70:30 ratio for further analysis using Random Forest. RESULTS: The Random Forest classification model was developed with the training dataset and 16 variables were confirmed as 'important': age, BMI, gender, syncope, lower limb numbness/pain, acute phase of the TAAD, BP >160 mmHg at admission; acute liver dysfunction, WBC >15×109/L, aortic size, aortic height index (AHI), periaortic hematoma, pleural effusion, brachiocephalic artery involvement, renal artery involvement, and hemopericardium. Validation of the model showed good discrimination with an AUC, sensitivity, specificity, positive predictive value and negative predictive value of 0.994, 1.000, 0.987, 0.998 and 1.000, respectively, in the training dataset, and 0.752, 0.990, 0.514, 0.945 and 0.857, respectively, in the testing dataset. CONCLUSIONS: An easy-to-use tool to predict in-hospital rupture for TAAD patients was developed and validated (http://47.107.228.109/). Periaortic hematoma is the strongest predictor. Simple clinical information such as syncope can be very useful in in-hospital rupture risk stratification. 2019 Journal of Thoracic Disease. All rights reserved.
BACKGROUND: This study is to establish prediction tools for in-hospital rupture of type A aortic dissection (TAAD) patients, to better guide emergency surgical triage and patient counselling. METHODS: We retrospectively evaluated 1,133 consecutive patients with TAAD from January 2010 to December 2016. The study population was divided into training and testing datasets in a 70:30 ratio for further analysis using Random Forest. RESULTS: The Random Forest classification model was developed with the training dataset and 16 variables were confirmed as 'important': age, BMI, gender, syncope, lower limb numbness/pain, acute phase of the TAAD, BP >160 mmHg at admission; acute liver dysfunction, WBC >15×109/L, aortic size, aortic height index (AHI), periaortic hematoma, pleural effusion, brachiocephalic artery involvement, renal artery involvement, and hemopericardium. Validation of the model showed good discrimination with an AUC, sensitivity, specificity, positive predictive value and negative predictive value of 0.994, 1.000, 0.987, 0.998 and 1.000, respectively, in the training dataset, and 0.752, 0.990, 0.514, 0.945 and 0.857, respectively, in the testing dataset. CONCLUSIONS: An easy-to-use tool to predict in-hospital rupture for TAAD patients was developed and validated (http://47.107.228.109/). Periaortic hematoma is the strongest predictor. Simple clinical information such as syncope can be very useful in in-hospital rupture risk stratification. 2019 Journal of Thoracic Disease. All rights reserved.
Entities:
Keywords:
Random Forest; Type A aortic dissection (TAAD); in-hospital rupture
Authors: Flavia del Porto; Maria Proietta; Luigi Tritapepe; Fabio Miraldi; Angela Koverech; Patrizia Cardelli; Fabio Tabacco; Vincenzo de Santis; Andrea Vecchione; Anna Paola Mitterhofer; Italo Nofroni; Rachele Amodeo; Massimo Trappolini; Giuseppe Aliberti Journal: Ann Med Date: 2010-09-23 Impact factor: 4.709
Authors: H Kuehl; H Eggebrecht; T Boes; G Antoch; S Rosenbaum; S Ladd; A Bockisch; J Barkhausen; R Erbel Journal: Heart Date: 2007-12-10 Impact factor: 5.994
Authors: Jip L Tolenaar; Whit Froehlich; Frederik H W Jonker; Gilbert R Upchurch; Vincenzo Rampoldi; Thomas T Tsai; Eduardo Bossone; Arturo Evangelista; Patrick O'Gara; Linda Pape; Dan Montgomery; Eric M Isselbacher; Christoph A Nienaber; Kim A Eagle; Santi Trimarchi Journal: Circulation Date: 2014-09-09 Impact factor: 29.690
Authors: Riaz Ahmed Agha; Mimi R Borrelli; Martinique Vella-Baldacchino; Rachel Thavayogan; Dennis P Orgill Journal: Int J Surg Date: 2017-09-07 Impact factor: 6.071