Waveform Phasicity Prediction from Arterial Sounds through Spectrogram Analysis using Convolutional Neural Networks for Limb Perfusion Assessment

TL;DR

This paper introduces a CNN-based system that analyzes spectrograms of doppler sounds to accurately predict waveform phasicity, aiding in the diagnosis of Peripheral Arterial Disease at point-of-care.

Contribution

It presents a novel deep learning approach that converts doppler sounds into spectrograms for automatic waveform classification, improving diagnostic accuracy for PAD.

Findings

F1 score of 90.57% achieved

Accuracy of 96.23% achieved

System is computationally efficient and suitable for clinical integration

Abstract

Peripheral Arterial Disease (PAD) is a common form of arterial occlusive disease that is challenging to evaluate at the point-of-care. Hand-held dopplers are the most ubiquitous device used to evaluate circulation and allows providers to audibly "listen" to the blood flow. Providers use the audible feedback to subjectively assess whether the sound characteristics are consistent with Monophasic, Biphasic, or Triphasic waveforms. Subjective assessment of doppler sounds raises suspicion of PAD and leads to further testing, often delaying definitive treatment. Misdiagnoses are also possible with subjective interpretation of doppler waveforms. This paper presents a Deep Learning system that has the ability to predict waveform phasicity through analysis of hand-held doppler sounds. We collected 268 four-second recordings on an iPhone taken during a formal vascular lab study in patients with cardiovascular disease. Our end-to-end system works by converting input sound into a spectrogram which visually represents frequency changes in temporal patterns. This conversion enables visual differentiation between the phasicity classes. With these changes present, a custom trained Convolutional Neural Network (CNN) is used for prediction through learned feature extraction. The performance of the model was evaluated via calculation of the F1 score and accuracy metrics. The system received an F1 score of 90.57% and an accuracy of 96.23%. Our Deep Learning system is not computationally expensive and has the ability for integration within several applications. When used in a clinic, this system has the capability of preventing misdiagnosis and gives practitioners a second opinion that can be useful in the evaluation of PAD.