12
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Feasibility of Deep Learning-Based Analysis of Auscultation for Screening Significant Stenosis of Native Arteriovenous Fistula for Hemodialysis Requiring Angioplasty

      research-article

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Objective

          To investigate the feasibility of using a deep learning-based analysis of auscultation data to predict significant stenosis of arteriovenous fistulas (AVF) in patients undergoing hemodialysis requiring percutaneous transluminal angioplasty (PTA).

          Materials and Methods

          Forty patients (24 male and 16 female; median age, 62.5 years) with dysfunctional native AVF were prospectively recruited. Digital sounds from the AVF shunt were recorded using a wireless electronic stethoscope before (pre-PTA) and after PTA (post-PTA), and the audio files were subsequently converted to mel spectrograms, which were used to construct various deep convolutional neural network (DCNN) models (DenseNet201, EfficientNetB5, and ResNet50). The performance of these models for diagnosing ≥ 50% AVF stenosis was assessed and compared. The ground truth for the presence of ≥ 50% AVF stenosis was obtained using digital subtraction angiography. Gradient-weighted class activation mapping (Grad-CAM) was used to produce visual explanations for DCNN model decisions.

          Results

          Eighty audio files were obtained from the 40 recruited patients and pooled for the study. Mel spectrograms of “pre-PTA” shunt sounds showed patterns corresponding to abnormal high-pitched bruits with systolic accentuation observed in patients with stenotic AVF. The ResNet50 and EfficientNetB5 models yielded an area under the receiver operating characteristic curve of 0.99 and 0.98, respectively, at optimized epochs for predicting ≥ 50% AVF stenosis. However, Grad-CAM heatmaps revealed that only ResNet50 highlighted areas relevant to AVF stenosis in the mel spectrogram.

          Conclusion

          Mel spectrogram-based DCNN models, particularly ResNet50, successfully predicted the presence of significant AVF stenosis requiring PTA in this feasibility study and may potentially be used in AVF surveillance.

          Related collections

          Most cited references21

          • Record: found
          • Abstract: found
          • Article: not found

          SMOTE: Synthetic Minority Over-sampling Technique

          An approach to the construction of classifiers from imbalanced datasets is described. A dataset is imbalanced if the classification categories are not approximately equally represented. Often real-world data sets are predominately composed of ``normal'' examples with only a small percentage of ``abnormal'' or ``interesting'' examples. It is also the case that the cost of misclassifying an abnormal (interesting) example as a normal example is often much higher than the cost of the reverse error. Under-sampling of the majority (normal) class has been proposed as a good means of increasing the sensitivity of a classifier to the minority class. This paper shows that a combination of our method of over-sampling the minority (abnormal) class and under-sampling the majority (normal) class can achieve better classifier performance (in ROC space) than only under-sampling the majority class. This paper also shows that a combination of our method of over-sampling the minority class and under-sampling the majority class can achieve better classifier performance (in ROC space) than varying the loss ratios in Ripper or class priors in Naive Bayes. Our method of over-sampling the minority class involves creating synthetic minority class examples. Experiments are performed using C4.5, Ripper and a Naive Bayes classifier. The method is evaluated using the area under the Receiver Operating Characteristic curve (AUC) and the ROC convex hull strategy.
            Bookmark
            • Record: found
            • Abstract: found
            • Article: not found

            Adam: A Method for Stochastic Optimization

            We introduce Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments. The method is straightforward to implement, is computationally efficient, has little memory requirements, is invariant to diagonal rescaling of the gradients, and is well suited for problems that are large in terms of data and/or parameters. The method is also appropriate for non-stationary objectives and problems with very noisy and/or sparse gradients. The hyper-parameters have intuitive interpretations and typically require little tuning. Some connections to related algorithms, on which Adam was inspired, are discussed. We also analyze the theoretical convergence properties of the algorithm and provide a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework. Empirical results demonstrate that Adam works well in practice and compares favorably to other stochastic optimization methods. Finally, we discuss AdaMax, a variant of Adam based on the infinity norm. Published as a conference paper at the 3rd International Conference for Learning Representations, San Diego, 2015
              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              KDOQI Clinical Practice Guideline for Vascular Access: 2019 Update

              The National Kidney Foundation's Kidney Disease Outcomes Quality Initiative (KDOQI) has provided evidence-based guidelines for hemodialysis vascular access since 1996. Since the last update in 2006, there has been a great accumulation of new evidence and sophistication in the guidelines process. The 2019 update to the KDOQI Clinical Practice Guideline for Vascular Access is a comprehensive document intended to assist multidisciplinary practitioners care for chronic kidney disease patients and their vascular access. New topics include the end-stage kidney disease "Life-Plan" and related concepts, guidance on vascular access choice, new targets for arteriovenous access (fistulas and grafts) and central venous catheters, management of specific complications, and renewed approaches to some older topics. Appraisal of the quality of the evidence was independently conducted by using a Grading of Recommendations Assessment, Development, and Evaluation (GRADE) approach, and interpretation and application followed the GRADE Evidence to Decision frameworks. As applicable, each guideline statement is accompanied by rationale/background information, a detailed justification, monitoring and evaluation guidance, implementation considerations, special discussions, and recommendations for future research.
                Bookmark

                Author and article information

                Journal
                Korean J Radiol
                Korean J Radiol
                KJR
                Korean Journal of Radiology
                The Korean Society of Radiology
                1229-6929
                2005-8330
                October 2022
                13 September 2022
                : 23
                : 10
                : 949-958
                Affiliations
                [1 ]Department of Radiology, Yonsei University College of Medicine, Seoul, Korea.
                [2 ]Department of Anesthesiology and Pain Medicine, Seoul National University Bundang Hospital, Seongnam, Korea.
                [3 ]Department of Surgery, Yonsei University College of Medicine, Seoul, Korea.
                [4 ]Department of Internal Medicine, College of Medicine, Ewha Womans University, Seoul, Korea.
                Author notes
                Corresponding author: Kichang Han, MD, PhD, Department of Radiology, Yonsei University College of Medicine, 50-1 Yonsei-ro, Seodaemun-gu, Seoul 03722, Korea. wowsaycheese@ 123456yuhs.ac

                *These authors contributed equally to this work.

                Author information
                https://orcid.org/0000-0002-7626-194X
                https://orcid.org/0000-0002-6413-752X
                https://orcid.org/0000-0002-9701-9757
                https://orcid.org/0000-0003-4733-7658
                https://orcid.org/0000-0003-2711-2793
                https://orcid.org/0000-0002-5576-8557
                https://orcid.org/0000-0002-8237-5628
                https://orcid.org/0000-0003-2821-9007
                https://orcid.org/0000-0001-6906-2590
                https://orcid.org/0000-0002-4334-3797
                https://orcid.org/0000-0001-6768-4396
                https://orcid.org/0000-0002-3575-5847
                Article
                10.3348/kjr.2022.0364
                9523235
                36174999
                12a77457-1c8e-4306-bec4-8c4741b4ecb4
                Copyright © 2022 The Korean Society of Radiology

                This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License ( https://creativecommons.org/licenses/by-nc/4.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

                History
                : 04 June 2022
                : 05 August 2022
                : 05 August 2022
                Categories
                Intervention
                Original Article

                Radiology & Imaging
                angioplasty,deep learning,arteriovenous fistula,auscultation,renal dialysis
                Radiology & Imaging
                angioplasty, deep learning, arteriovenous fistula, auscultation, renal dialysis

                Comments

                Comment on this article