Developing a practical machine learning model to predict post implantation syndrome after endovascular aneurysm
Jinhua Zhang1, Dong Yang2, Lei Zhang3
1The First People's Hospital of Foshan (The Affiliated Foshan Hospital of Southern University of Science and Technology), School of Medicine, Southern University of Science and Technology, Foshan, Guangdong, China.
CVIR Endovascular
|March 18, 2026
Summary
This study developed a machine learning model to predict post-implantation syndrome (PIS) after endovascular aneurysm repair (EVAR). The best model, using linear discriminant analysis, identified 11 key risk factors for PIS.
Area of Science:
- Vascular Surgery
- Medical Informatics
- Biostatistics
Background:
- Post-implantation syndrome (PIS) is a common systemic inflammatory response after endovascular aneurysm repair (EVAR).
- PIS can lead to cardiovascular complications and prolonged hospitalization.
- Predicting PIS is crucial for patient management and outcomes.
Purpose of the Study:
- To develop and validate a machine learning (ML) model for predicting PIS following EVAR.
- To identify key predictive factors for PIS onset.
Main Methods:
- Retrospective analysis of 594 patients undergoing EVAR.
- Application of Least Absolute Shrinkage and Selection Operator (LASSO) regression for variable selection.
- Development and evaluation of eight ML models, including linear discriminant analysis (LDA).
Main Results:
- The incidence of PIS was 16.8%.
- Eleven significant risk factors for PIS were identified, including age, surgical duration, and specific intraoperative medications and device characteristics.
- The LDA model demonstrated the best performance with an AUC of 0.794.
Conclusions:
- A predictive ML model based on LDA was successfully developed using 11 preoperative and intraoperative variables.
- This model can aid clinicians in predicting and managing PIS after EVAR.
- Further validation and prospective studies are warranted.
