Machine learning validation of the AVAS classification compared to ultrasound mapping in a multicentre study.

Journal: Scientific reports
PMID:

Abstract

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.

Authors

  • Katerina Lawrie
    Department of Transplantation Surgery, Institute for Clinical and Experimental Medicine, Prague, Czech Republic.
  • Petr Waldauf
    The Third Faculty of Medicine, Charles University, Prague, Czech Republic.
  • Peter Balaz
    Third Faculty of Medicine, Charles University, Prague, Czech Republic.
  • Radoslav Bortel
    Faculty of Electrical Engineering, Czech Technical University in Prague, Prague, Czech Republic.
  • Ricardo Lacerda
    RL Vascular Surgery and Interventional Radiology, Private Practice, Salvador, Brazil.
  • Emma Aitken
    Department of Renal Surgery, Queen Elizabeth University Hospital, Glasgow, UK.
  • Krzysztof Letachowicz
    Department of Nephrology and Transplantation Medicine, Wroclaw Medical University, Wroclaw, Poland.
  • Mario D'Oria
    Division of Vascular and Endovascular Surgery, Cardio-Thoracic-Vascular Department, University Hospital of Trieste, Trieste, Italy.
  • Vittorio Di Maso
    Nephrology and Dialysis Unit, Department of Medicine, ASUGI - University Hospital of Trieste, Trieste, Italy.
  • Pavel Stasko
    AdNa s.r.o., Vascular Surgery Clinic, Košice, Slovak Republic.
  • Antonio Gomes
    Department of General Surgery, Hospital Professor Doutor Fernando Fonseca, Amadora, Portugal.
  • Joana Fontainhas
    Department of General Surgery, Hospital Professor Doutor Fernando Fonseca, Amadora, Portugal.
  • Matej Pekar
    Centre for Vascular and Mini-invasive Surgery, Hospital AGEL, Třinec-Podlesí, Czech Republic.
  • Alena Srdelic
    Division of Nephrology and Haemodialysis, Internal Medicine Department, University Hospital of Split, Split, Croatia.
  • Stephen O'Neill
    Department of Public Health and Policy, London School of Hygiene and Tropical Medicine, London, UK; Queen's University, Belfast, UK.