Vol.69, No.2, 2021, pp.2583-2598, doi:10.32604/cmc.2021.017779
OPEN ACCESS
ARTICLE
Risk Prediction of Aortic Dissection Operation Based on Boosting Trees
  • Ling Tan1, Yun Tan2, Jiaohua Qin2, Hao Tang1,*, Xuyu Xiang2, Dongshu Xie1, Neal N. Xiong3
1 The Second Xiangya Hospital of Central South University, Changsha, 410011, Hunan, China
2 Central South University of Forestry & Technology, Changsha, 410004, Hunan, China
3 Northeastern State University, Tahlequah, 74464, OK, USA
* Corresponding Author: Hao Tang. Email:
Received 10 February 2021; Accepted 11 May 2021; Issue published 21 July 2021
Abstract
During the COVID-19 pandemic, the treatment of aortic dissection has faced additional challenges. The necessary medical resources are in serious shortage, and the preoperative waiting time has been significantly prolonged due to the requirement to test for COVID-19 infection. In this work, we focus on the risk prediction of aortic dissection surgery under the influence of the COVID-19 pandemic. A general scheme of medical data processing is proposed, which includes five modules, namely problem definition, data preprocessing, data mining, result analysis, and knowledge application. Based on effective data preprocessing, feature analysis and boosting trees, our proposed fusion decision model can obtain 100% accuracy for early postoperative mortality prediction, which outperforms machine learning methods based on a single model such as LightGBM, XGBoost, and CatBoost. The results reveal the critical factors related to the postoperative mortality of aortic dissection, which can provide a theoretical basis for the formulation of clinical operation plans and help to effectively avoid risks in advance.
Keywords
Risk prediction; aortic dissection; COVID-19; postoperative mortality; boosting tree
Cite This Article
Tan, L., Tan, Y., Qin, J., Tang, H., Xiang, X. et al. (2021). Risk Prediction of Aortic Dissection Operation Based on Boosting Trees. CMC-Computers, Materials & Continua, 69(2), 2583–2598.
This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.