Automate the peripheral arterial disease prediction in lower extremity arterial doppler study using machine learning and neural networks

Lena Ara, Xiao Luo, Alan Sawchuk, Dave Rollins

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This research work aims to automate the prediction of peripheral arterial diseases implied by the Lower Extremity Arterial Doppler (LEAD) studies by applying machine learning and artificial intelligence algorithms. This study is the first to use machine learning and artificial intelligence algorithms to analyze LEAD data for peripheral arterial disease prediction. Specifically, we employ a Convolutional Neural Network (CNN) to classify the waveform into three types. The classified waveforms are used as input to the learning algorithms for disease prediction. We evaluate two traditional machine learning algorithms as well as two neural networks to predict normal and three types of artery diseases: aortoiliac disease, femoral-popliteal arterial disease, and trifurcation disease. The hierarchical neural network model (HNN) is investigated to deal with imbalanced data set. The first level of the HNN predicts the normal from diseases. The remaining two neural networks are used to predict other diseases from the rest. HNN has achieved high F1 scores: 99% on the normal case, 97% on the aortoiliac disease, and 94% on the femoral-popliteal arterial disease and 89% on the trifurcation disease through 10-fold cross-validation. The comparison shows that HNN works better than multilayer perceptron, random forests, and SVM. The overall result demonstrates that machine learning and artificial intelligence algorithms can be developed for peripheral arterial diseases implied by the LEAD studies while reducing the reading variability in vascular laboratories.

Original languageEnglish (US)
Title of host publicationACM-BCB 2019 - Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics
PublisherAssociation for Computing Machinery, Inc
Pages130-135
Number of pages6
ISBN (Electronic)9781450366663
DOIs
StatePublished - Sep 4 2019
Event10th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM-BCB 2019 - Niagara Falls, United States
Duration: Sep 7 2019Sep 10 2019

Publication series

NameACM-BCB 2019 - Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics

Conference

Conference10th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM-BCB 2019
CountryUnited States
CityNiagara Falls
Period9/7/199/10/19

Fingerprint

Peripheral Arterial Disease
Learning systems
Lower Extremity
Artificial Intelligence
Neural networks
Neural Networks (Computer)
Artificial intelligence
Thigh
Machine Learning
Learning algorithms
Blood Vessels
Reading
Multilayer neural networks
Arteries
Learning

Keywords

  • Lower Extremity Arterial Doppler
  • Neural networks
  • Peripheral arterial disease prediction

ASJC Scopus subject areas

  • Computer Science Applications
  • Software
  • Biomedical Engineering
  • Health Informatics

Cite this

Ara, L., Luo, X., Sawchuk, A., & Rollins, D. (2019). Automate the peripheral arterial disease prediction in lower extremity arterial doppler study using machine learning and neural networks. In ACM-BCB 2019 - Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics (pp. 130-135). (ACM-BCB 2019 - Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics). Association for Computing Machinery, Inc. https://doi.org/10.1145/3307339.3342180

Automate the peripheral arterial disease prediction in lower extremity arterial doppler study using machine learning and neural networks. / Ara, Lena; Luo, Xiao; Sawchuk, Alan; Rollins, Dave.

ACM-BCB 2019 - Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics. Association for Computing Machinery, Inc, 2019. p. 130-135 (ACM-BCB 2019 - Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ara, L, Luo, X, Sawchuk, A & Rollins, D 2019, Automate the peripheral arterial disease prediction in lower extremity arterial doppler study using machine learning and neural networks. in ACM-BCB 2019 - Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics. ACM-BCB 2019 - Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, Association for Computing Machinery, Inc, pp. 130-135, 10th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM-BCB 2019, Niagara Falls, United States, 9/7/19. https://doi.org/10.1145/3307339.3342180
Ara L, Luo X, Sawchuk A, Rollins D. Automate the peripheral arterial disease prediction in lower extremity arterial doppler study using machine learning and neural networks. In ACM-BCB 2019 - Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics. Association for Computing Machinery, Inc. 2019. p. 130-135. (ACM-BCB 2019 - Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics). https://doi.org/10.1145/3307339.3342180
Ara, Lena ; Luo, Xiao ; Sawchuk, Alan ; Rollins, Dave. / Automate the peripheral arterial disease prediction in lower extremity arterial doppler study using machine learning and neural networks. ACM-BCB 2019 - Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics. Association for Computing Machinery, Inc, 2019. pp. 130-135 (ACM-BCB 2019 - Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics).
@inproceedings{1ef7d7c395b942edbb3bf9839bb40f7f,
title = "Automate the peripheral arterial disease prediction in lower extremity arterial doppler study using machine learning and neural networks",
abstract = "This research work aims to automate the prediction of peripheral arterial diseases implied by the Lower Extremity Arterial Doppler (LEAD) studies by applying machine learning and artificial intelligence algorithms. This study is the first to use machine learning and artificial intelligence algorithms to analyze LEAD data for peripheral arterial disease prediction. Specifically, we employ a Convolutional Neural Network (CNN) to classify the waveform into three types. The classified waveforms are used as input to the learning algorithms for disease prediction. We evaluate two traditional machine learning algorithms as well as two neural networks to predict normal and three types of artery diseases: aortoiliac disease, femoral-popliteal arterial disease, and trifurcation disease. The hierarchical neural network model (HNN) is investigated to deal with imbalanced data set. The first level of the HNN predicts the normal from diseases. The remaining two neural networks are used to predict other diseases from the rest. HNN has achieved high F1 scores: 99{\%} on the normal case, 97{\%} on the aortoiliac disease, and 94{\%} on the femoral-popliteal arterial disease and 89{\%} on the trifurcation disease through 10-fold cross-validation. The comparison shows that HNN works better than multilayer perceptron, random forests, and SVM. The overall result demonstrates that machine learning and artificial intelligence algorithms can be developed for peripheral arterial diseases implied by the LEAD studies while reducing the reading variability in vascular laboratories.",
keywords = "Lower Extremity Arterial Doppler, Neural networks, Peripheral arterial disease prediction",
author = "Lena Ara and Xiao Luo and Alan Sawchuk and Dave Rollins",
year = "2019",
month = "9",
day = "4",
doi = "10.1145/3307339.3342180",
language = "English (US)",
series = "ACM-BCB 2019 - Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics",
publisher = "Association for Computing Machinery, Inc",
pages = "130--135",
booktitle = "ACM-BCB 2019 - Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics",

}

TY - GEN

T1 - Automate the peripheral arterial disease prediction in lower extremity arterial doppler study using machine learning and neural networks

AU - Ara, Lena

AU - Luo, Xiao

AU - Sawchuk, Alan

AU - Rollins, Dave

PY - 2019/9/4

Y1 - 2019/9/4

N2 - This research work aims to automate the prediction of peripheral arterial diseases implied by the Lower Extremity Arterial Doppler (LEAD) studies by applying machine learning and artificial intelligence algorithms. This study is the first to use machine learning and artificial intelligence algorithms to analyze LEAD data for peripheral arterial disease prediction. Specifically, we employ a Convolutional Neural Network (CNN) to classify the waveform into three types. The classified waveforms are used as input to the learning algorithms for disease prediction. We evaluate two traditional machine learning algorithms as well as two neural networks to predict normal and three types of artery diseases: aortoiliac disease, femoral-popliteal arterial disease, and trifurcation disease. The hierarchical neural network model (HNN) is investigated to deal with imbalanced data set. The first level of the HNN predicts the normal from diseases. The remaining two neural networks are used to predict other diseases from the rest. HNN has achieved high F1 scores: 99% on the normal case, 97% on the aortoiliac disease, and 94% on the femoral-popliteal arterial disease and 89% on the trifurcation disease through 10-fold cross-validation. The comparison shows that HNN works better than multilayer perceptron, random forests, and SVM. The overall result demonstrates that machine learning and artificial intelligence algorithms can be developed for peripheral arterial diseases implied by the LEAD studies while reducing the reading variability in vascular laboratories.

AB - This research work aims to automate the prediction of peripheral arterial diseases implied by the Lower Extremity Arterial Doppler (LEAD) studies by applying machine learning and artificial intelligence algorithms. This study is the first to use machine learning and artificial intelligence algorithms to analyze LEAD data for peripheral arterial disease prediction. Specifically, we employ a Convolutional Neural Network (CNN) to classify the waveform into three types. The classified waveforms are used as input to the learning algorithms for disease prediction. We evaluate two traditional machine learning algorithms as well as two neural networks to predict normal and three types of artery diseases: aortoiliac disease, femoral-popliteal arterial disease, and trifurcation disease. The hierarchical neural network model (HNN) is investigated to deal with imbalanced data set. The first level of the HNN predicts the normal from diseases. The remaining two neural networks are used to predict other diseases from the rest. HNN has achieved high F1 scores: 99% on the normal case, 97% on the aortoiliac disease, and 94% on the femoral-popliteal arterial disease and 89% on the trifurcation disease through 10-fold cross-validation. The comparison shows that HNN works better than multilayer perceptron, random forests, and SVM. The overall result demonstrates that machine learning and artificial intelligence algorithms can be developed for peripheral arterial diseases implied by the LEAD studies while reducing the reading variability in vascular laboratories.

KW - Lower Extremity Arterial Doppler

KW - Neural networks

KW - Peripheral arterial disease prediction

UR - http://www.scopus.com/inward/record.url?scp=85073152235&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073152235&partnerID=8YFLogxK

U2 - 10.1145/3307339.3342180

DO - 10.1145/3307339.3342180

M3 - Conference contribution

AN - SCOPUS:85073152235

T3 - ACM-BCB 2019 - Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics

SP - 130

EP - 135

BT - ACM-BCB 2019 - Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics

PB - Association for Computing Machinery, Inc

ER -