The Arteriovenous Access Stage (AVAS) classification simplifies information about suitability of vessels for vascular access (VA). It's been previously validated in a clinical study. Here, AVAS performance was tested against multiple ultrasound mapping measurements using machine learning. A prospective multicentre international study (NCT04796558) with patient recruitment from March 2021-July 2024. Demographics, risk factors, vessels parameters, types of predicted and created VA (pVA, cVA) were collected. We modelled pVA and cVA using the Random Forest algorithm. Model performance was estimated and compared using Bayesian generalized linear models. ROC AUC with 95% credible intervals was the performance metric. 1151 patients were included. ROC AUC for pVA prediction by AVAS was 0.79 (0.77;0.82) and by mapping was 0.85 (0.83;0.88). ROC AUC for cVA prediction by AVAS was 0.71 (0.69;0.74) and by mapping was 0.8 (0.78;0.83). Using AVAS with other parameters increased the ROC AUC to 0.87 for pVA (0.84;0.89) and 0.82 (0.79;0.84) for cVA. Using mapping with other parameters increased the ROC AUC to 0.88 for pVA (0.86;0.91) and 0.85 (0.83;0.88) for cVA. Multiple mapping measurements showed higher performance at VA prediction than AVAS. However, AVAS is simpler and quicker, so may be preferable for routine clinical practice.

3rd Faculty of Medicine Charles University Prague Czech Republic

AdNa s r o Vascular Surgery Clinic Košice Slovak Republic

Cardiocenter 3rd Faculty of Medicine University Hospital Královské Vinohrady Charles University Prague Czech Republic

Centre for Medical Education Queen's University Belfast Belfast UK

Centre for Vascular and Mini invasive Surgery Hospital AGEL Třinec Podlesí Czech Republic

Department of Anaesthesiology and Resuscitation University Hospital Královské Vinohrady Prague Czech Republic

Department of General Surgery Hospital Professor Doutor Fernando Fonseca Amadora Portugal

Department of Nephrology and Transplantation Medicine Wroclaw Medical University Wroclaw Poland

Department of Physiology Faculty of Medicine Masaryk University Brno Czech Republic

Department of Renal Surgery Queen Elizabeth University Hospital Glasgow UK

Department of Transplant Surgery and Regional Nephrology Unit Belfast City Hospital Belfast UK

Department of Transplantation Surgery Institute for Clinical and Experimental Medicine Prague Czech Republic

Department of Vascular Surgery National Institute for Cardiovascular Disease Bratislava Slovak Republic

Division of Nephrology and Haemodialysis Internal Medicine Department University Hospital of Split Split Croatia

Division of Vascular and Endovascular Surgery Cardio Thoracic Vascular Department University Hospital of Trieste Trieste Italy

Division of Vascular Surgery University Hospital Královské Vinohrady Prague Czech Republic

Faculty of Electrical Engineering Czech Technical University Prague Prague Czech Republic

Nephrology and Dialysis Unit Department of Medicine ASUGI University Hospital of Trieste Trieste Italy

RL Vascular Surgery and Interventional Radiology Private Practice Salvador Brazil

Zobrazit více v PubMed

Woo, K. T., Choong, H. L., Wong, K. S., Tan, H. B. & Chan, C. M. The contribution of chronic kidney disease to the global burden of major noncommunicable diseases. Kidney Int.81, 1044–1045 (2012). PubMed

Shi, B., Ying, T. & Chadban, S. J. Survival after kidney transplantation compared with ongoing dialysis for people over 70 years of age: A matched-pair analysis. Am. J. Transplant.23, 1551–1560 (2023). PubMed

Tonelli, M. et al. Systematic review: Kidney transplantation compared with dialysis in clinically relevant outcomes. Am. J. Transplant.11, 2093–2109 (2011). PubMed

Hernández, D. et al. Mortality in elderly waiting-list patients versus age-matched kidney transplant recipients: Where is the risk?. Kidney Blood Press. Res.43, 256–275. 10.1159/000487684 (2018). PubMed

Schold, J. D., Srinivas, T. R., Sehgal, A. R. & Meier-Kriesche, H. U. Half of kidney transplant candidates who are older than 60 years now placed on the waiting list will die before receiving a deceased-donor transplant. Clin. J. Am. Soc. Nephrol.4, 1239 (2009). PubMed PMC

Matas, A. J. et al. OPTN/SRTR 2013 annual data report: Kidney. Am. J. Transplant.15, 1–34 (2015). PubMed

Eckardt, K.-U., Kasiske, B. L. & Zeier, M. G. KDIGO clinical practice guideline for the care of kidney transplant recipients. Am. J. Transplant.9(Suppl 3), S1–S155 (2009). PubMed

Bello, A. K. et al. Epidemiology of haemodialysis outcomes. Nat. Rev. Nephrol.18, 378–395 (2022). PubMed PMC

Martin, A. G., Grasty, M. & Lear, P. A. Haemodynamics of brachial arteriovenous fistula development. J. Vasc. Access1, 54–59 (2000). PubMed

Schmidli, J. et al. Editor’s Choice – Vascular Access: 2018 Clinical Practice Guidelines of the European Society for Vascular Surgery (ESVS). Eur. J. Vasc. Endovasc. Surg.55, 757–818 (2018). PubMed

Lok, C. E. et al. KDOQI clinical practice guideline for vascular access: 2019 update. Am. J. Kidney Dis.75, S1–S164 (2020). PubMed

Chlorogiannis, D. D. et al. Pre-operative ultrasound mapping before arteriovenous fistula formation: An updated systematic review and meta-analysis. J. Nephrol.10.1007/s40620-023-01814-6 (2023). PubMed PMC

Baláž, P. et al. The arteriovenous access stage (AVAS) classification. Clin. Kidney J.14, 1747–1751 (2021). PubMed PMC

Lawrie, K. et al. Validation of arterio venous access stage (AVAS) classification: A prospective international multicentre study. Clin. Kidney J.13, 20 (2024). PubMed PMC

Katerina, L., Stephen, O., Petr, W. & Peter, B. VAVASC study: Clinical trial protocol. J. Vasc. Access.24, 792–797 (2023). PubMed

Peralta, R. et al. Development and validation of a machine learning model predicting arteriovenous fistula failure in a large network of dialysis clinics. Int. J. Environ. Res. Public Health18, 12355 (2021). PubMed PMC

Krackov, W., Sor, M., Razdan, R., Zheng, H. & Kotanko, P. Artificial intelligence methods for rapid vascular access aneurysm classification in remote or in-person settings. Blood Purif.50, 636–641 (2021). PubMed

Julkaew, S., Wongsirichot, T., Damkliang, K. & Sangthawan, P. DeepVAQ: an adaptive deep learning for prediction of vascular access quality in hemodialysis patients. BMC Med. Inform. Decis. Mak.24, 1–11 (2024). PubMed PMC

Study Details | Validation of Arterio Venous Access Stage (AVAS) Classification | ClinicalTrials.gov. https://clinicaltrials.gov/study/NCT04796558?term=Validation%20of%20Arterio%20Venous%20Access%20Stage%20Classification&rank=1.

Sidawy, A. N. et al. Recommended standards for reports dealing with arteriovenous hemodialysis accesses. J. Vasc. Surg.35, 603–610 (2002). PubMed

Katerina, L., Stephen, O., Petr, W. & Peter, B. VAVASC study: Clinical trial protocol. J. Vasc. Access10.1177/11297298211042677 (2021). PubMed

R Core Team. R: A Language and Environment for Statistical Computing. Preprint at https://www.R-project.org/ (2024).

Posit team. RStudio: Integrated Development Environment for R. Preprint at http://www.posit.co/ (2024).

Kuhn, M. & Wickham, H. Tidymodels: a collection of packages for modeling and machine learning using tidyverse principles. Preprint at https://www.tidymodels.org (2020).

Multinomial regression — multinom_reg • parsnip. https://parsnip.tidymodels.org/reference/multinom_reg.html.

Friedman, J., Hastie, T. & Tibshirani, R. Regularization paths for generalized linear models via coordinate descent. J. Stat. Softw.33, 1–22 (2010). PubMed PMC

Random forest — rand_forest • parsnip. https://parsnip.tidymodels.org/reference/rand_forest.html.

Wright, M. N. & Ziegler, A. Ranger: A fast implementation of random forests for high dimensional data in C++ and R. J. Stat. Softw.10.18637/jss.v077.i01 (2017).

Boosted trees — boost_tree • parsnip. https://parsnip.tidymodels.org/reference/boost_tree.html.

Chen, T. et al. xgboost: Extreme Gradient Boosting. Preprint at https://CRAN.R-project.org/package=xgboost (2024).

Hand, D. J. & Till, R. J. A simple generalisation of the area under the roc curve for multiple class classification problems. Mach. Learn.45, 171–186 (2001).

Kuhn, M., Wickham, H. & Hvitfeldt, E. recipes: Preprocessing and Feature Engineering Steps for Modeling. Preprint at https://github.com/tidymodels/recipes (2024).

Kuhn, M. tidyposterior: Bayesian Analysis to Compare Models using Resampling Statistics. Preprint at https://CRAN.R-project.org/package=tidyposterior (2023).

Greenwell, B. M. & Boehmke, B. C. Variable importance plots—An introduction to the vip package. R J12, 343–366 (2020).

Friedman, J. H. Greedy function approximation: A gradient boosting machine. Ann. Stat.29, 1189–1232 (2001).

Apley, D. W. & Zhu, J. Visualizing the effects of predictor variables in black box supervised learning models. J. R Stat. Soc. Series B Stat. Methodol.82, 1059–1086 (2020).

Biecek, P. DALEX: Explainers for complex predictive models in R. J. Mach. Learn. Res.19, 1–5 (2018).

Maksymiuk, S., Gosiewska, A. & Biecek, P. Landscape of R packages for eXplainable Artificial Intelligence. ArXiv (2020).

Zobrazit více v PubMed

ClinicalTrials.gov
NCT04796558