Developing a practical machine learning model to predict post implantation syndrome after endovascular aneurysm repair
Abstract
Our study selected 11 preoperative and intraoperative variables to develop a ML model based on LDA for predicting PIS after EVAR and the model may help assist clinical decision-making.
What are the key findings of this study?
A new tool uses machine learning to help doctors predict a condition called post implantation syndrome after a certain surgery for aneurysms (bulges in blood vessels). By looking at specific patient details before and during the surgery, it can help doctors make better choices. This means safer and more effective care for patients! 🤖
Key Points
Objective
The aim is to develop a machine learning model that predicts post implantation syndrome following endovascular aneurysm repair.
Methods
- Selected 11 preoperative and intraoperative variables
- Utilized Linear Discriminant Analysis (LDA) for model development
- Analyzed data from patients undergoing endovascular aneurysm repair
Results
- The machine learning model can predict post implantation syndrome with selected variables
- Model assists in clinical decision-making processes
What is the clinical evidence from this study?
Study Design
Cohort
Population
Endovascular aneurysm repair (EVAR) (n=594)
Intervention
Linear Discriminant Analysis (LDA) machine learning model vs. Other machine learning models
Key Finding
A linear discriminant analysis machine learning model using 11 perioperative features predicted post-implantation syndrome after endovascular aneurysm repair with an AUC of 0.794.
Limitations
- Single-center study with only internal validation, lacking external validation.
- Postoperative case data were not included in the analysis.
- Respiratory parameters from the anesthesia machine were unavailable.
- Only data on early PIS within 72 hours after EVAR were analyzed.
- Exclusion criteria did not exclude diseases such as malignancy, hematologic diseases, systemic autoimmune disorders, and aortic rupture.