Patient comfort level prediction during transport using artificial neural network

Abstract

Since patient comfort during transport is a matter of paramount importance, this paper aims to determinethe possibilities of applying neural networks for its prediction and monitoring. Specific objectives of the research includemonitoring and predicting patient transport comfort, with subjective assessment of comfort by medical personnel. Anoriginal Android application that collects signals from an accelerometer and a GPS sensor was used with the aim ofachieving the research goals. The collected signals were processed and a total of twelve parameters were calculated. Amultilayer perceptron was created in the proposed research. The evaluation results indicate acceptable accuracy andgive the possibility to apply the same model to the next patient transport. The root mean square error was 0.0215 andthe overall confusion matrix prediction accuracy was 90.07%. Moreover, the results were validated in real usage. Thelimitations and future work are highlighted.