Proximal detection of guide wire perforation using feature extraction from bispectral audio signal analysis combined with machine learning.

Artery perforation during a vascular catheterization procedure is a potentially life threatening event. It is of particular importance for the surgeons to be aware of hidden or non-obvious events. To minimize the impact it is crucial for the surgeon to detect such a perforation very early. We propose a novel approach to identify perforations based on the acquisition and analysis of audio signals on the outside proximal end of a guide wire. The signals were acquired using a stethoscope equipped with a microphone and attached to the proximal end of the guide wire via a 3D printed adapter. Bispectral analysis was employed to extract acoustic signatures in the signal and several features were extracted from the bispectrum of the signal. Finally, three machine learning algorithms - K-nearest Neighbor, Support Vector Machine (SVM), and Artificial Neural Network (ANN)- were used to classify a signal as a perforation or as an artifact. The bispectrum-based features resulted in valuable features allowing a perforation to be clearly identifiable from other occurring events. A perforation leaves a clear audio signal trace in the time-frequency domain. The recordings were classified as perforation, friction or guide wire bump using SVM with 97% (polykernel) and 98.62% (RBF) accuracy, k-nearest Neighbor an accuracy of 98.28% and ANN with accuracy of 98.73% was obtained. The presented approach shows that interactions starting at the tip of a guide wire can be picked up at its proximal end providing a valuable additional information that could be used during a guide wire procedure.