Excluding Indecisive Decisions by Bringing Machine Learning and Sensor Fusion Together in Wound Management

Abstract

Monitoring and analysing of chronic woundsis still primarily based on visual inspections and interpretations of medical professionals. By maintaining this method, there is a chance of misinterpretation due to diverse ways of examining the wound. Further, for each assessment thewound dressing needs to be removed, which results into an intermission of the healing process. The Bioelectrical Impedance Spectroscopy (BIS)technique is tested to observe differences in the wound itself over time. By using Electrical Impedance Tomography (EIT) it is possible to detect variations in conductivity solely based on impedance measurements. Features from this digital image are extracted and fed into a machine learningalgorithm.The output from this gives a detailed feedback of the healing state of a wound and this information in turn can be used to alter the conditions in which a wound is healing so an optimal state of healing can be realized.