Affiliations: [a] Department of Computer and Software Engineering, Faculty of Technical Sciences, University of Kragujevac, Cacak 32000, Serbia | [b] Department of Computer Science, Faculty of Electronic Engineering, University of Nis, Nis 18000, Serbia | [c] Department for Electrical Engineering, Faculty of Engineering, University of Kragujevac, Kragujevac 34000, Serbia
Correspondence:
[*]
Corresponding author: Marina Milosevic, Department of Computer Engineering, Faculty of Technical Sciences, University of Kragujevac, Svetog Save 65, Cacak 32000, Serbia. Tel.: +381 32302778; E-mail: marina.milosevic@ftn.kg.ac.rs.
Abstract: BACKGROUND: Passenger comfort is affected by many factors. Patient comfort is even more specific due to its mental and physical health condition. OBJECTIVE: Developing a system for monitoring patient transport conditions with the comfort level classification, which is affected by the patient parameters. METHODS: Smartphone with the developed Android application was installed in an EMS to monitor patient transport between medical institutions. As a result, 10 calculated parameters are generated in addition to the GPS data and the subjective comfort level. Three classifiers are used to classify the transportation. At the end, the adjustment of classified comfort levels is performed based on the patient’s medical condition, age and gender. RESULTS: Modified SVM classifier provided the best overall classification results with the precision of 90.8%. Furthermore, a model that represents patient sensitivity to transport vibration, based on the patient’s medical condition, is proposed and the final classification results are presented. CONCLUSIONS: The Android application is mobile, simple to install and use. According to the obtained results, SVM and Naive Bayes classifier gave satisfying results while KNN should be avoided. The developed model takes transport comfort and the patient’s medical condition into consideration, so it is suitable for the patient transport comfort classification.
