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

J 2025

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

LAWRIE, Katerina; Petr WALDAUF; Peter BALAZ; Radosalv BORTEL; Ricardo LACERDA et. al.

Basic information

Original name

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

Authors

Edition

SCIENTIFIC REPORTS, BERLIN, NATURE PORTFOLIO, 2025, 2045-2322

Other information

Language

English

Type of outcome

Article in a journal

Field of Study

30212 Surgery

Country of publisher

Germany

Confidentiality degree

is not subject to a state or trade secret

References:

URL

Impact factor

Impact factor: 3.900 in 2024

Organization unit

Faculty of Medicine

DOI

https://doi.org/10.1038/s41598-025-86456-3

UT WoS

001401998100028

EID Scopus

999

Keywords in English

AVAS classification; machine learning validation; ultrasound mapping

Abstract

In the original language

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.

Cite

LAWRIE, Katerina; Petr WALDAUF; Peter BALAZ; Radosalv BORTEL; Ricardo LACERDA; Emma AITKEN; Krzysztof LETACHOWICZ; Mario D’ORIA; Vittorio DI MASO; Pavel STASKO; Antonio GOMES; Joana FONTAINHAS; Matej PEKAŘ; Alena SRDELIC; Study Group VAVASC and Stephen O’NEILL. Machine learning validation of the AVAS classification compared to ultrasound mapping in a multicentre study. SCIENTIFIC REPORTS. BERLIN: NATURE PORTFOLIO, 2025, vol. 15, No 1, p. 1-14. ISSN 2045-2322. Available from: https://doi.org/10.1038/s41598-025-86456-3.

@article{2469881,
   author = {Lawrie, Katerina and Waldauf, Petr and Balaz, Peter and Bortel, Radosalv and Lacerda, Ricardo and Aitken, Emma and Letachowicz, Krzysztof and D’Oria, Mario and Di Maso, Vittorio and Stasko, Pavel and Gomes, Antonio and Fontainhas, Joana and Pekař, Matej and Srdelic, Alena and VAVASC, Study Group and O’Neill, Stephen},
   article_location = {BERLIN},
   article_number = {1},
   doi = {https://doi.org/10.1038/s41598-025-86456-3},
   keywords = {AVAS classification; machine learning validation; ultrasound mapping},
   language = {eng},
   issn = {2045-2322},
   journal = {SCIENTIFIC REPORTS},
   title = {Machine learning validation of the AVAS classification compared to ultrasound mapping in a multicentre study},
   url = {https://www.nature.com/articles/s41598-025-86456-3},
   volume = {15},
   year = {2025}
}

TY  - JOUR
ID  - 2469881
AU  - Lawrie, Katerina - Waldauf, Petr - Balaz, Peter - Bortel, Radosalv - Lacerda, Ricardo - Aitken, Emma - Letachowicz, Krzysztof - D’Oria, Mario - Di Maso, Vittorio - Stasko, Pavel - Gomes, Antonio - Fontainhas, Joana - Pekař, Matej - Srdelic, Alena - VAVASC, Study Group - O’Neill, Stephen
PY  - 2025
TI  - Machine learning validation of the AVAS classification compared to ultrasound mapping in a multicentre study
JF  - SCIENTIFIC REPORTS
VL  - 15
IS  - 1
SP  - 1-14
EP  - 1-14
PB  - NATURE PORTFOLIO
SN  - 20452322
KW  - AVAS classification
KW  - machine learning validation
KW  - ultrasound mapping
UR  - https://www.nature.com/articles/s41598-025-86456-3
N2  - 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.
ER  -

LAWRIE, Katerina; Petr WALDAUF; Peter BALAZ; Radosalv BORTEL; Ricardo LACERDA; Emma AITKEN; Krzysztof LETACHOWICZ; Mario D’ORIA; Vittorio DI MASO; Pavel STASKO; Antonio GOMES; Joana FONTAINHAS; Matej PEKAŘ; Alena SRDELIC; Study Group VAVASC and Stephen O’NEILL. Machine learning validation of the AVAS classification compared to ultrasound mapping in a multicentre study. \textit{SCIENTIFIC REPORTS}. BERLIN: NATURE PORTFOLIO, 2025, vol.~15, No~1, p.~1-14. ISSN~2045-2322. Available from: https://doi.org/10.1038/s41598-025-86456-3.

Přehled o publikaci