Artificial neural networks analysis predicts long-term fistula function in hemodialysis patients following percutaneous transluminal angioplasty

Kidney failure is particularly common in the United States,where it affects over 700,000 individuals.It is typically treated through repeated sessions of hemodialysis to filter and clean the blood.Hemodialysis requires vascular access,in about 70%of cases through an arteriovenous fistula(AVF)surgically created by connecting an artery and vein.AVF take 6 weeks or more to mature.Mature fistulae often require intervention,most often percutaneous transluminal angioplasty(PTA),also known as fistulaplasty,to maintain the patency of the fistula.PTA is also the first-line intervention to restore blood flow and prolong the use of an AVF,and many patients undergo the procedure multiple times.Although PTA is important for AVF maturation and maintenance,research into predictive models of AVF function following PTA has been limited.Therefore,in this paper we hypothesize that based on patient-specific information collected during PTA,a predictive model can be created to help improve treatment planning.We test a set of rich,multimodal data from 28 patients that includes medical history,AVF blood flow,and interventional angiographic imaging(specifically excluding any post-PTA measurements)and build deep hybrid neural networks.A hybrid model combining a 3D convolutional neural network with a multilayer perceptron to classify AVF was established.We found using this model that we were able to identify the association between different factors and evaluate whether the PTA procedure can maintain primary patency for more than 3 months.The testing accuracy achieved was 0.75 with a weighted F1-score of 0.75,and AUROC of 0.75.These results indicate that evaluating multimodal clinical data using artificial neural networks can predict the outcome of PTA.These initial findings suggest that the hybrid model combining clinical data,imaging and hemodynamic analysis can be useful to treatment planning for hemodialysis.Further study based on a large cohort is needed to refine the accuracy and model efficiency.

Comparison of Two Markov Models for a 30-Year Simulation of the Natural History of Intracranial Aneurysms

Objective: There are several Markov models which simulate long-term aneurysm growth and rupture. By comparing multiple models, we cannot only find a way to accurately simulate the growth and rupture behavior of untreated aneurysms in our database, but also find he best model to simulate aneurysm behavior for other studies. This will let us identify which aneurysms require invasive treatment. Methods: We analyzed 290 aneurysms in 29 males and 177 females. The mean diameter was 4.5 ± 3.45 mm, and the mean age was 61 ± 13.22 years. We tested Markov Model I and Markov Model II to simulate growth and rupture over 30 years, and growth and rupture were functions of aneurysm volume. At five-year intervals, we calculated the odds ratio and used the One-Way ANOVA and Independent T-Test to test the effects of aneurysm diameter and growth on the rupture rate. Results: After 30 years, the mean aneurysm sizes were 9.18 ± 2.37 mm and 7.80 ± 6.44 mm for Markov Models I and II, respectively. The mean rupture rate was 13.93% ± 12.89% for Markov Model I and 14.15% ± 21.96% for Markov Model II. There was a significantly higher rupture rate and significant odds ratio for larger aneurysms and “Significant Growth” aneurysms at most five-year intervals. Conclusion: Aneurysms larger than 9.5 mm need immediate surgical treatment. For aneurysms between 3.5 - 9.5 mm, early intervention is recommended if the growth rate exceeds 0.36 mm/year. Markov Model I is the optimal model for our database due to the unrealistically large aneurysms produced by Markov Model II.