Scientific Reports (Sep 2021)

Geometric and biomechanical modeling aided by machine learning improves the prediction of growth and rupture of small abdominal aortic aneurysms

  • Moritz Lindquist Liljeqvist,
  • Marko Bogdanovic,
  • Antti Siika,
  • T. Christian Gasser,
  • Rebecka Hultgren,
  • Joy Roy

DOI
https://doi.org/10.1038/s41598-021-96512-3
Journal volume & issue
Vol. 11, no. 1
pp. 1 – 10

Abstract

Read online

Abstract It remains difficult to predict when which patients with abdominal aortic aneurysm (AAA) will require surgery. The aim was to study the accuracy of geometric and biomechanical analysis of small AAAs to predict reaching the threshold for surgery, diameter growth rate and rupture or symptomatic aneurysm. 189 patients with AAAs of diameters 40–50 mm were included, 161 had undergone two CTAs. Geometric and biomechanical variables were used in prediction modelling. Classifications were evaluated with area under receiver operating characteristic curve (AUC) and regressions with correlation between observed and predicted growth rates. Compared with the baseline clinical diameter, geometric-biomechanical analysis improved prediction of reaching surgical threshold within four years (AUC 0.80 vs 0.85, p = 0.031) and prediction of diameter growth rate (r = 0.17 vs r = 0.38, p = 0.0031), mainly due to the addition of semiautomatic diameter measurements. There was a trend towards increased precision of volume growth rate prediction (r = 0.37 vs r = 0.45, p = 0.081). Lumen diameter and biomechanical indices were the only variables that could predict future rupture or symptomatic AAA (AUCs 0.65–0.67). Enhanced precision of diameter measurements improves the prediction of reaching the surgical threshold and diameter growth rate, while lumen diameter and biomechanical analysis predicts rupture or symptomatic AAA.