A deep learning algorithm to quantify AVF stenosis and predict 6-month primary patency : a pilot study
© The Author(s) 2022. Published by Oxford University Press on behalf of the ERA..
Background: A deep convolutional neural network (DCNN) model that predicts the degree of arteriovenous fistula (AVF) stenosis and 6-month primary patency (PP) based on AVF shunt sounds was developed, and was compared with various machine learning (ML) models trained on patients' clinical data.
Methods: Forty dysfunctional AVF patients were recruited prospectively, and AVF shunt sounds were recorded before and after percutaneous transluminal angioplasty using a wireless stethoscope. The audio files were converted to melspectrograms to predict the degree of AVF stenosis and 6-month PP. The diagnostic performance of the melspectrogram-based DCNN model (ResNet50) was compared with that of other ML models [i.e. logistic regression (LR), decision tree (DT) and support vector machine (SVM)], as well as the DCNN model (ResNet50) trained on patients' clinical data.
Results: Melspectrograms qualitatively reflected the degree of AVF stenosis by exhibiting a greater amplitude at mid-to-high frequency in the systolic phase with a more severe degree of stenosis, corresponding to a high-pitched bruit. The proposed melspectrogram-based DCNN model successfully predicted the degree of AVF stenosis. In predicting the 6-month PP, the area under the receiver operating characteristic curve of the melspectrogram-based DCNN model (ResNet50) (≥0.870) outperformed that of various ML models based on clinical data (LR, 0.783; DT, 0.766; SVM, 0.733) and that of the spiral-matrix DCNN model (0.828).
Conclusion: The proposed melspectrogram-based DCNN model successfully predicted the degree of AVF stenosis and outperformed ML-based clinical models in predicting 6-month PP.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2023 |
|---|---|
| Erschienen: |
2023 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:16 |
|---|---|
| Enthalten in: |
Clinical kidney journal - 16(2023), 3 vom: 28. März, Seite 560-570 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Park, Jae Hyon [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Angioplasty |
|---|
| Anmerkungen: |
Date Revised 04.03.2023 published: Electronic-eCollection Citation Status PubMed-not-MEDLINE |
|---|
| doi: |
10.1093/ckj/sfac254 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM353709239 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM353709239 | ||
| 003 | DE-627 | ||
| 005 | 20231226060630.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1093/ckj/sfac254 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1178.xml |
| 035 | |a (DE-627)NLM353709239 | ||
| 035 | |a (NLM)36865006 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Park, Jae Hyon |e verfasserin |4 aut | |
| 245 | 1 | 2 | |a A deep learning algorithm to quantify AVF stenosis and predict 6-month primary patency |b a pilot study |
| 264 | 1 | |c 2023 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Revised 04.03.2023 | ||
| 500 | |a published: Electronic-eCollection | ||
| 500 | |a Citation Status PubMed-not-MEDLINE | ||
| 520 | |a © The Author(s) 2022. Published by Oxford University Press on behalf of the ERA. | ||
| 520 | |a Background: A deep convolutional neural network (DCNN) model that predicts the degree of arteriovenous fistula (AVF) stenosis and 6-month primary patency (PP) based on AVF shunt sounds was developed, and was compared with various machine learning (ML) models trained on patients' clinical data | ||
| 520 | |a Methods: Forty dysfunctional AVF patients were recruited prospectively, and AVF shunt sounds were recorded before and after percutaneous transluminal angioplasty using a wireless stethoscope. The audio files were converted to melspectrograms to predict the degree of AVF stenosis and 6-month PP. The diagnostic performance of the melspectrogram-based DCNN model (ResNet50) was compared with that of other ML models [i.e. logistic regression (LR), decision tree (DT) and support vector machine (SVM)], as well as the DCNN model (ResNet50) trained on patients' clinical data | ||
| 520 | |a Results: Melspectrograms qualitatively reflected the degree of AVF stenosis by exhibiting a greater amplitude at mid-to-high frequency in the systolic phase with a more severe degree of stenosis, corresponding to a high-pitched bruit. The proposed melspectrogram-based DCNN model successfully predicted the degree of AVF stenosis. In predicting the 6-month PP, the area under the receiver operating characteristic curve of the melspectrogram-based DCNN model (ResNet50) (≥0.870) outperformed that of various ML models based on clinical data (LR, 0.783; DT, 0.766; SVM, 0.733) and that of the spiral-matrix DCNN model (0.828) | ||
| 520 | |a Conclusion: The proposed melspectrogram-based DCNN model successfully predicted the degree of AVF stenosis and outperformed ML-based clinical models in predicting 6-month PP | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a angioplasty | |
| 650 | 4 | |a arteriovenous fistula | |
| 650 | 4 | |a auscultation | |
| 650 | 4 | |a convolutional neural network | |
| 650 | 4 | |a primary patency | |
| 700 | 1 | |a Yoon, Jongjin |e verfasserin |4 aut | |
| 700 | 1 | |a Park, Insun |e verfasserin |4 aut | |
| 700 | 1 | |a Sim, Yongsik |e verfasserin |4 aut | |
| 700 | 1 | |a Kim, Soo Jin |e verfasserin |4 aut | |
| 700 | 1 | |a Won, Jong Yun |e verfasserin |4 aut | |
| 700 | 1 | |a Han, Kichang |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Clinical kidney journal |d 2012 |g 16(2023), 3 vom: 28. März, Seite 560-570 |w (DE-627)NLM219739579 |x 2048-8505 |7 nnns |
| 773 | 1 | 8 | |g volume:16 |g year:2023 |g number:3 |g day:28 |g month:03 |g pages:560-570 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1093/ckj/sfac254 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 16 |j 2023 |e 3 |b 28 |c 03 |h 560-570 | ||