BACKGROUND
Ecologically valid evaluations of patient states or wellbeing by means of new technologies is a key issue in contemporary research in silver science. The in-game metrics generated from interaction of users with serious games can potentially be used in predicting or characterizing user’s health and well-being state. There is currently an increasing body of research that investigates the use of measures from interaction with games as digital biomarkers for health and wellbeing
OBJECTIVE
The research objective of this paper is the prediction of wellbeing digital biomarkers from data collected during the interaction with Serious Games (SGs), using as ground truth the values of standard clinical assessment tests
METHODS
The dataset is gathered during the interaction of Parkinson’s disease (PD) patients with the webFitForAll exergame platform, a serious games engine designed for promoting physical activity among older adults, patients and vulnerable population. The collected data, referred as in-game metrics, represent body movements captured by a 3D sensor camera and translated into game analytics. Standard clinical tests gathered before and after the long-term interaction with exergames (pre-test vs post-test) were used to provide the user baselines.
RESULTS
Our results show that in-game metrics can effectively categorize participants into groups of different cognitive and physical states. Different in-game metrics have higher descriptive value for specific tests and can be used to predict a value range for these tests.
CONCLUSIONS
Our results provide encouraging evidence for the value in-game metrics as digital biomarkers and can boost the analysis of improving in-game metrics in order to obtain more detailed results.