Automate the Peripheral Arterial Disease Prediction in Lower Extremity Arterial Doppler Study using Machine Learning and Neural Networks

Ara, Lena; Luo, Xiao; Sawchuk, Alan P.; Rollins, Dave

doi:10.1145/3307339.3342180

Cited by 9 publications

(7 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although this agreement does not reach that obtained between two trained vascular physicians (Kappa = 0.83 (0.79–0.87), strong agreement) it is very similar and without any potential reproducibility error. These results are in keeping with those of previous studies where neural networks were used to diagnose PAD [ 23 , 24 ] and the prospect of perfect reproducibility is of importance, especially as an arterial Doppler waveform description is frequently debated amongst vascular medicine physicians [ 17 ]. Neural networks could indeed provide an objective approach for categorization and a description of arterial Doppler waveforms.…”

Section: Discussionsupporting

confidence: 89%

“…Since the 1960s there has been a growing emphasis on computer aided diagnosis (CADg) in medicine. An increasingly utilized CADg technique is the application of neural networks in the classification of patients’ conditions [ 22 ], including in patients suffering from PAD [ 23 , 24 ]. A neural network trained by experts to categorize arterial Doppler flow waveforms could potentially remove the remaining subjectivity in the classification process.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Use of a Pre-Trained Neural Network for Automatic Classification of Arterial Doppler Flow Waveforms: A Proof of Concept

Guilcher

Lanéelle

2021

JCM

View full text Add to dashboard Cite

Background: Arterial Doppler flow waveform analysis is a tool recommended for the management of lower extremity peripheral arterial disease (PAD). To standardize the waveform analysis, classifications have been proposed. Neural networks have shown a great ability to categorize data. The aim of the present study was to use an existing neural network to evaluate the potential for categorization of arterial Doppler flow waveforms according to a commonly used classification. Methods: The Pareto efficient ResNet-101 (ResNet-101) neural network was chosen to categorize 424 images of arterial Doppler flow waveforms according to the Simplified Saint-Bonnet classification. As a reference, the inter-operator variability between two trained vascular medicine physicians was also assessed. Accuracy was expressed in percentage, and agreement was assessed using Cohen’s Kappa coefficient. Results: After retraining, ResNet-101 was able to categorize waveforms with 83.7 ± 4.6% accuracy resulting in a kappa coefficient of 0.79 (0.75–0.83) (CI 95%), compared with a kappa coefficient of 0.83 (0.79–0.87) (CI 95%) between the two physicians. Conclusion: This study suggests that the use of transfer learning on a pre-trained neural network is feasible for the automatic classification of images of arterial Doppler flow waveforms.

show abstract

Section: Discussionsupporting

confidence: 89%

Section: Introductionmentioning

confidence: 99%

Use of a Pre-Trained Neural Network for Automatic Classification of Arterial Doppler Flow Waveforms: A Proof of Concept

Guilcher

Lanéelle

2021

JCM

View full text Add to dashboard Cite

show abstract

“…Applications of computer vision algorithms to PAD-specific imaging are just starting to be reported and have the possibility to inform approaches to revascularization and potentially reduce the number of invasive diagnostic studies. Ara et al 71 developed a computer vision model to automate classification of Doppler waveforms and detect aortoiliac, femoral-popliteal, and tibial trifurcation disease. Their model classified waveforms using a CNN, followed by a hierarchical neural network that integrated waveform classifications at each segment to classify normal versus diseased segments.…”

Section: Pad Imagingmentioning

confidence: 99%

Leveraging Machine Learning and Artificial Intelligence to Improve Peripheral Artery Disease Detection, Treatment, and Outcomes

Flores

Demsas

Leeper

et al. 2021

Circulation Research

View full text Add to dashboard Cite

Peripheral artery disease is an atherosclerotic disorder which, when present, portends poor patient outcomes. Low diagnosis rates perpetuate poor management, leading to limb loss and excess rates of cardiovascular morbidity and death. Machine learning algorithms and artificially intelligent systems have shown great promise in application to many areas in health care, such as accurately detecting disease, predicting patient outcomes, and automating image interpretation. Although the application of these technologies to peripheral artery disease are in their infancy, their promises are tremendous. In this review, we provide an introduction to important concepts in the fields of machine learning and artificial intelligence, detail the current state of how these technologies have been applied to peripheral artery disease, and discuss potential areas for future care enhancement with advanced analytics.

show abstract

“…In terms of ML, we used four well-known algorithms: Neural Networks [ 55 , 56 ], Random Forest [ 57 ], Support Vector Machine (SVM) [ 58 ], and Logistic Regression [ 59 ]. Previous research used these algorithms in many classification tasks for diagnostic applications in the medical fields [ 31 , 32 , 60 , 61 , 62 ]. We ran each group to achieve the best predictions and find the minimum features that produced acceptable performance.…”

Section: Predictive ML Models To Diagnose Padmentioning

confidence: 99%

“…ML and Neural Networks have also been used to automate the classification of arterial segments affected following PAD diagnosis. This approach used computer vision algorithms with Doppler waveforms and PAD imaging but also required manual adjustment of images, which is time consuming [ 31 , 32 ]. Deep learning-based arterial pulse waveform analysis was also used to detect and estimate PAD severity, but this test is not easier to access than an ankle-brachial index test [ 30 ].…”

Section: Introductionmentioning

confidence: 99%

Machine Learning-Based Peripheral Artery Disease Identification Using Laboratory-Based Gait Data

Al-Ramini

Hassan

Fallahtafti

et al. 2022

Sensors

View full text Add to dashboard Cite

Peripheral artery disease (PAD) manifests from atherosclerosis, which limits blood flow to the legs and causes changes in muscle structure and function, and in gait performance. PAD is underdiagnosed, which delays treatment and worsens clinical outcomes. To overcome this challenge, the purpose of this study is to develop machine learning (ML) models that distinguish individuals with and without PAD. This is the first step to using ML to identify those with PAD risk early. We built ML models based on previously acquired overground walking biomechanics data from patients with PAD and healthy controls. Gait signatures were characterized using ankle, knee, and hip joint angles, torques, and powers, as well as ground reaction forces (GRF). ML was able to classify those with and without PAD using Neural Networks or Random Forest algorithms with 89% accuracy (0.64 Matthew’s Correlation Coefficient) using all laboratory-based gait variables. Moreover, models using only GRF variables provided up to 87% accuracy (0.64 Matthew’s Correlation Coefficient). These results indicate that ML models can classify those with and without PAD using gait signatures with acceptable performance. Results also show that an ML gait signature model that uses GRF features delivers the most informative data for PAD classification.

show abstract

Automate the Peripheral Arterial Disease Prediction in Lower Extremity Arterial Doppler Study using Machine Learning and Neural Networks

Cited by 9 publications

References 12 publications

Use of a Pre-Trained Neural Network for Automatic Classification of Arterial Doppler Flow Waveforms: A Proof of Concept

Use of a Pre-Trained Neural Network for Automatic Classification of Arterial Doppler Flow Waveforms: A Proof of Concept

Leveraging Machine Learning and Artificial Intelligence to Improve Peripheral Artery Disease Detection, Treatment, and Outcomes

Machine Learning-Based Peripheral Artery Disease Identification Using Laboratory-Based Gait Data

Contact Info

Product

Resources

About