Deep learning analysis of blood flow sounds to detect arteriovenous fistula stenosis

Risk prediction models for autogenous arteriovenous fistula failure in maintenance hemodialysis patients: A systematic review and meta-analysis

BACKGROUND

The aim of this study was to systematically retrieve and evaluate published risk prediction models for autogenous arteriovenous fistula (AVF) failure post-formation in maintenance hemodialysis (MHD) patients, with the goal of assisting healthcare providers in selecting or developing appropriate risk assessment tools and providing a reference for future research.

METHODS

A systematic search of relevant studies was conducted in PubMed, Web of Science, Cochrane Library, CINAHL, Embase, CNKI, Wanfang Database, VIP Database, and CBM Database up to February 1, 2024. Two researchers independently performed literature screening, data extraction, and methodological quality assessment using the Prediction Model Risk of bias (ROB) Assessment Tool.

RESULTS

A total of 4869 studies were identified, from which 25 studies with 28 prediction models were ultimately included. The incidence of autogenous AVF failure in MHD patients ranged from 3.9% to 39%. The most commonly used predictors were age, vein diameter, history of diabetes, AVF blood flow, and sex. The reported area under the curve (AUC) ranged from 0.61 to 0.911. All studies were found to have a high ROB, primarily due to inappropriate data sources and a lack of rigorous reporting in the analysis domain. The pooled AUC of five validation models was 0.80 (95% confidence interval: 0.79-0.81), indicating good predictive accuracy.

CONCLUSION

The included studies indicated that the predictive models for AVF failure post-formation in MHD patients are biased to some extent. Future research should focus on developing new models with larger sample sizes, strict adherence to reporting procedures, and external validation across multiple centers.

Prediction of Vascular Access Stenosis by Lightweight Convolutional Neural Network Using Blood Flow Sound Signals

This research examines the application of non-invasive acoustic analysis for detecting obstructions in vascular access (fistulas) used by kidney dialysis patients. Obstructions in these fistulas can interrupt essential dialysis treatment. In this study, we utilized a condenser microphone to capture the blood flow sounds before and after angioplasty surgery, analyzing 3819 sound samples from 119 dialysis patients. These sound signals were transformed into spectrogram images to classify obstructed and unobstructed vascular accesses, that is fistula conditions before and after the angioplasty procedure. A novel lightweight two-dimension convolutional neural network (CNN) was developed and benchmarked against pretrained CNN models such as ResNet50 and VGG16. The proposed model achieved a prediction accuracy of 100%, surpassing the ResNet50 and VGG16 models, which recorded 99% and 95% accuracy, respectively. Additionally, the study highlighted the significantly smaller memory size of the proposed model (2.37 MB) compared to ResNet50 (91.3 MB) and VGG16 (57.9 MB), suggesting its suitability for edge computing environments. This study underscores the efficacy of diverse deep-learning approaches in the obstructed detection of dialysis fistulas, presenting a scalable solution that combines high accuracy with reduced computational demands.

Prediction of Arteriovenous Access Dysfunction by Mel Spectrogram-based Deep Learning Model

Background: The early detection of arteriovenous (AV) access dysfunction is crucial for maintaining the patency of vascular access. This study aimed to use deep learning to predict AV access malfunction necessitating further vascular management. Methods: This prospective cohort study enrolled prevalent hemodialysis (HD) patients with an AV fistula or AV graft from a single HD center. Their AV access bruit sounds were recorded weekly using an electronic stethoscope from three different sites (arterial needle site, venous needle site, and the midpoint between the arterial and venous needle sites) before HD sessions. The audio signals were converted to Mel spectrograms using Fourier transformation and utilized to develop deep learning models. Three deep learning models, (1) Convolutional Neural Network (CNN), (2) Convolutional Recurrent Neural Network (CRNN), and (3) Vision Transformers-Gate Recurrent Unit (ViT-GRU), were trained and compared to predict the likelihood of dysfunctional AV access. Results: Total 437 audio recordings were obtained from 84 patients. The CNN model outperformed the other models in the test set, with an F1 score of 0.7037 and area under the receiver operating characteristic curve (AUROC) of 0.7112. The Vit-GRU model had high performance in out-of-fold predictions, with an F1 score of 0.7131 and AUROC of 0.7745, but low generalization ability in the test set, with an F1 score of 0.5225 and AUROC of 0.5977. Conclusions: The CNN model based on Mel spectrograms could predict malfunctioning AV access requiring vascular intervention within 10 days. This approach could serve as a useful screening tool for high-risk AV access.