Novel Smartphone Based Free Flap Monitoring Tool Using Machine Learning

Abstract

AbstractFree flap monitoring is important to ensure early detection of arterial or venous failure to facilitate salvage. Our prior research has shown ability to magnify skin change as a result of skin changes. This study was undertaken to test the feasibility of detecting venous and arterial occlusion using a smartphone camera and pattern recognition (a simplistic implementation of a machine learning algorithm). Bilateral hands of seven patients were video recorded with various tourniquet pressures on one hand simulating no occlusion, venous occlusion, and arterial occlusion with the other hand as internal control. Video data resolved at an average iPhone camera quality of 33 fps was processed using the sci-kit learn library in Python to detect changes in color frequency between frames and then compared to the control hand. Comparing the test hand to the control hand allowed for the depiction of the “delta” that was sensitive enough to detect changes on a video without any additional augmentation. The average rate of change in red pixels between video frames was noticeably different compared to control for both arterial occlusion (1.06x greater) and venous occlusion (1.07x greater). A graphical representation depicted a clear relationship while an individual was undergoing occlusion (Fig 1). Our smartphone video capture and analysis facilitates visualization of skin perfusion and can distinguish between states of no occlusion, arterial occlusion, and venous occlusion. This study shows promise for the use of inexpensive smartphone monitoring in a clinical setting for accurate free flap monitoring.