Patient comfort level prediction during transport using artificial neural network

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