Developing a LASSO Regression-Based Nomogram to Predict Outcomes in Abdominal Aortic Aneurysm Patients Post-Endovascular Aneurysm Repair

Scritto il 05/12/2025
da Fengyi Yu

Clin Interv Aging. 2025 Nov 28;20:2241-2253. doi: 10.2147/CIA.S493841. eCollection 2025.

ABSTRACT

INTRODUCTION: This study aimed to develop a prognostic model to predict outcomes in patients undergoing endovascular aneurysm repair (EVAR) for abdominal aortic aneurysms (AAA).

METHODS: 304 participants were divided into training and validation sets in a 7:3 ratio. Six risk factors were identified using LASSO regression, univariate, and multivariate Cox regression analyses: history of stroke, CIA atherosclerosis, age, hemoglobin levels, monocyte count, and large AAA. A nomogram was constructed to predict 1-year and 3-year all-cause mortality (ACM).

RESULTS: A total of 304 AAA patients who underwent EVAR were included in this study (84.87% male; median age 72 [IQR: 65-77] years). The model showed good predictive performance, with area under the curve (AUC) values of 0.84 (95% CI: 0.79-0.89) and 0.81 (95% CI: 0.76-0.86) for 1-year and 3-year mortality in the training set, and 0.71 (95% CI: 0.62-0.80) and 0.80 (95% CI: 0.73-0.87) in the validation set.

DISCUSSION: These results suggest the model's effectiveness in aiding clinicians with risk stratification and tailoring treatment strategies for post-EVAR patients.

PMID:41347210 | PMC:PMC12673264 | DOI:10.2147/CIA.S493841