AI-assisted detection of high-pitched bruits in arteriovenous fistulas using a digital stethoscope
The Journal of Vascular Access · 2026-07 · 27 (4) · 1565-1575
DOI: 10.1177/11297298251396199 ↗Kurz gefasst
Multizentrische Studie in der Zeitschrift The Journal of Vascular Access, online erschienen am 07.01.2026. Verfasst von Jasmine Ion Titapiccolo und 9 weiteren Autor:innen. Beteiligte Einrichtung: Renal Research Institute, Fresenius Medical Care, Vaiano Cremasco, Italy. Hauptthemen laut MEDLINE: Arteriovenous Shunt, Surgical, Renal Dialysis, Graft Occlusion, Vascular, Stethoscopes. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 41 Literaturangaben.
Abstract (Originalsprache)
Background
The arteriovenous fistula (AVF) is the preferred vascular access for patients undergoing hemodialysis, and early identification of complications such as stenosis or dysfunction is essential to preserve access patency and reduce morbidity.
Method
AVF bruit recordings were collected from 65 patients across 12 dialysis centers in Europe and Asia using a digital stethoscope connected to the medical record of the patients. A deep learning model was developed to detect high-pitched bruits—an acoustic marker commonly associated with AVF stenosis. Expert-annotated recordings served as the reference standard for supervised training and evaluation.
Results
Mean age of patients was 68, and the average blood flow during the dialysis session was 352 ml/min. The model demonstrated excellent performance on independent testing datasets, achieving a sensitivity of 97.1%, specificity of 73.8%, and an overall accuracy of 82%. The area under the receiver operating characteristic curve (ROC-AUC) was 94%, reflecting strong discriminative ability. The model showed excellent calibration. Model performance across different experimental retraining folds indicates a stable and reliable training process.
Conclusion
The integration of this deep learning tool into clinical workflows could provide clinicians with a sensitive, objective, and time-efficient method for detecting high-pitched bruits which may be used in combination with other clinical signs for the detection of AVF complications such as stenosis. Implemented through a low-cost phono angiography protocol requiring minimal training, this approach has the potential to support earlier interventions and improve outcomes in the hemodialysis population.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Renal Research Institute, Fresenius Medical Care, Vaiano Cremasco, Italy.
- Care Enablement, Fresenius Medical Care, Berlin, Germany.
- NephroCare Portugal, Fresenius Medical Care Portugal, Lisboa, Portugal.
ORCID-Profile: Jasmine Ion Titapiccolo
Zitieren
APA
Ion Titapiccolo, J., Botler, M., Bellocchio, F., Vas, A., Brockherde, F., Peralta, R., Kahouli, K., Warren, N., Neri, L., & Arterio-Venous Fistula Bruit Electronic Auscultation for Monitoring (AVF-BEAM) Group (2026). AI-assisted detection of high-pitched bruits in arteriovenous fistulas using a digital stethoscope. The Journal of Vascular Access, 27(4), 1565-1575. https://doi.org/10.1177/11297298251396199
Vancouver
Ion Titapiccolo J, Botler M, Bellocchio F, Vas A, Brockherde F, Peralta R, et al. AI-assisted detection of high-pitched bruits in arteriovenous fistulas using a digital stethoscope. The Journal of Vascular Access. 2026;27(4):1565-1575. doi:10.1177/11297298251396199
BibTeX
@article{IonTitapiccolo2026,
author = {Ion Titapiccolo, Jasmine and Botler, Max and Bellocchio, Francesco and Vas, Austin and Brockherde, Felix and Peralta, Ricardo and Kahouli, Khaled and Warren, Nathan and Neri, Luca and Arterio-Venous Fistula Bruit Electronic Auscultation for Monitoring (AVF-BEAM) Group, Arterio-Venous Fistula Bruit Electronic Auscultation for Monitoring (AVF-BEAM) Group},
title = {AI-assisted detection of high-pitched bruits in arteriovenous fistulas using a digital stethoscope},
journal = {The Journal of Vascular Access},
year = {2026},
volume = {27},
number = {4},
pages = {1565--1575},
doi = {10.1177/11297298251396199}
}
EUVIMED