Predicting abdominal aortic aneurysm growth using patient-oriented growth models with two-step Bayesian inference

Abstract

Objective: For small abdominal aortic aneurysms (AAAs), a regular follow-up examination is recommended every 12 months for AAAs of 30-39 mm and every six months for AAAs of 40-55 mm. Follow-up diameters can determine if a patient follows the common growth model of the population. However, the rapid expansion of an AAA, often associated with higher rupture risk, may be overlooked even though it requires surgical intervention. Therefore, the prognosis of abdominal aortic aneurysm growth is clinically important for planning treatment. This study aims to build enhanced Bayesian inference methods to predict maximum aneurysm diameter.Methods: 106 CT scans from 25 Korean AAA patients were retrospectively obtained. A two-step approach based on Bayesian calibration was used, and an exponential abdominal aortic aneurysm growth model (population-based) was specified according to each individual patient's growth (patient-specific) and morphologic characteristics of the aneurysm sac (enhanced). The distribution estimates were obtained using a Markov Chain Monte Carlo (MCMC) sampler.

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

“…While these studies are intriguing and the biomarkers are promising, most resulting decision rules have yet to be successfully compared with the clinically available maximal diameter in a validation set. Further, most studies have focused on single markers, and few have used machine learning approaches 60 , 61 . Integrating several of these markers into a machine learning framework could be fruitful going forward.…”

A Computational Growth Framework for Biological Tissues: Application to Growth of Aortic Root Aneurysm Repaired by the V-shape Surgery

“…First, the in vivo thickness of the aortic root was not available from the CT images, and thus the potential growth in the radial direction from Post1 to Post2 was not considered in our simulation. As shown by others, the time rate of change of radial versus in-plane growth can be an important factor in the growth rate of aneurysms [46][47][48] and should be a topic of future work. In vivo thickness of the aortic wall may be obtained based on the method in Elefteriades et al [49] when both contrast and non-contrast CT scans are available.…”

Handling of uncertainty in medical data using machine learning and probability theory techniques: a review of 30 years (1991–2020)

“…BI is the famous statistical inference techniques which utilizes Bayes' theorem in its inference mechanism (Akkoyun et al, 2020;Corani et al, 2013;Howle et al, 2017;Kourou et al, 2020;Seixas et al, 2014;Wang et al, 2019;Watabe et al, 2014). If there is more information or evidence, the probability of a hypothesis can be updated by utilizing Bayes' theorem (Ocampo et al, 2011).…”

“…The former handles uncertainty in data and the later handles it in the model. (Lim, 2020) 2020 COVID-19 Fallacies, facts and uncertainties about COVID-19 using Bayesian inference (Ghoshal et al, 2019) 2020 COVID-19 Uncertainty estimation in deep learning models for diagnosis of COVID-19 (Lin et al 2020) 2020 Human dietary risk Human dietary risk assessment using Bayesian inference (Zhou et al 2020) 2020 Medical image reconstruction Uncertainty quantification and Bayesian inference for the reconstruction of the medical image using Poisson data (Akkoyun et al 2020) 2020 Abdominal aortic aneurysm Abdominal aortic aneurysm prediction using two-step Bayesian inference (Magnusson et al 2019) 2019 Medical data analysis Principal stratum estimand to examine the effect of treatment in a subgroup using Bayesian Inference (Lipková, 2019) (Johnston et al 2015) 2015 Bioinformatics MtDNA bottleneck mechanism using Bayesian inference and Stochastic modeling (Huang et al 2011) 2011 HIV HIV dynamics with longitudinal data (Huang et al 2010) 2010 HIV HIV dynamic differential equation models using hierarchical Bayesian inference (Robertson & DeHart, 2010) 2010 Medical decision making An accessible and agile adaptation of Bayesian inference to medical diagnostics for interior health workers (Galesic et al 2009) 2009 Medical decision making Medical screening tests' evaluation with natural frequencies of older people with low numeracy (Suchard & Redelings, 2006) 2006 Bioinformatics BAli-Phy: simultaneous Bayesian inference of alignment and phylogeny (Mendoza-Blanco et al 1996) 1996 HIV A missing-data approach with simulation-based techniques on Bayesian inference prevalence related to HIV screening (Johnson & Gastwirth, 1991) 1991 Medical decision making Bayesian inference for medical screening tests Kendall et al (2017...…”