Automatic Early-Onset Free Flap Failure Detection for Implantable Biomedical Devices

Objective: Up to 10% of free flap cases are compromised, and without prompt intervention, amputation and even death can occur. Hourly monitoring improves salvage rates, but the gold standard for monitoring requires experienced personnel to operate and suffers from high false-positive rates as high as 31% that result in costly and unnecessary surgeries. In this paper, we investigate free flap patency monitoring using automatic hardware-only classification systems that eliminate the need for experienced personnel. The expected flow ranges of the antegrade and retrograde veins for breast reconstruction are studied using a syringe pump to create the laminar flow seen in veins. Methods: Feature data extracted from the Doppler blood flow signals are analyzed for sensitivity, specificity, and false-positive rates. Hardware is built to perform the classification automatically in real-time and output a decision at the end of the observation period. Results: Experimental results using the hardware-only classifier for a 50 ms window size show high sensitivity (96.75%), specificity (90.20%), and low false-positive rate (9.803%). The experimental and theoretical classification results show close agreement. Conclusion: This work indicates that automatic hardware-only classifiers can eliminate the need for experienced personnel to monitor free flap patency. Significance: The hardware-only classification is amenable to a monolithic implementation and future studies should study a totally implantable wirelessly-powered blood flow classifier. The high classifier performance in a short window period indicates that duty-cycled powering can be used to extend the safe operational depth of an implant. This is particularly relevant for the difficult buried free flap applications.