| Autor: |
Konstantinidis EI; Laboratory of Medical Physics and Digital Innovation, School of Medicine, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece., Bamidis PD; Laboratory of Medical Physics and Digital Innovation, School of Medicine, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece., Billis A; Laboratory of Medical Physics and Digital Innovation, School of Medicine, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece., Kartsidis P; Laboratory of Medical Physics and Digital Innovation, School of Medicine, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece., Petsani D; Laboratory of Medical Physics and Digital Innovation, School of Medicine, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece., Papageorgiou SG; Memory Disorders and Rare Dementias Unit, 1st Department of Neurology, Eginiteion University Hospital, National and Kapodistrian University of Athens, 15772 Athens, Greece. |
| Abstrakt: |
Conventional clinical cognitive assessment has its limitations, as evidenced by the environmental shortcomings of various neuropsychological tests conducted away from an older person's everyday environment. Recent research activities have focused on transferring screening tests to computerized forms, as well as on developing short screening tests for screening large populations for cognitive impairment. The purpose of this study was to present an exergaming platform, which was widely trialed (116 participants) to collect in-game metrics (built-in game performance measures). The potential correlation between in-game metrics and cognition was investigated in-depth by scrutinizing different in-game metrics. The predictive value of high-resolution monitoring games was assessed by correlating it with classical neuropsychological tests; the area under the curve (AUC) in the receiver operating characteristic (ROC) analysis was calculated to determine the sensitivity and specificity of the method for detecting mild cognitive impairment (MCI). Classification accuracy was calculated to be 73.53% when distinguishing between MCI and normal subjects, and 70.69% when subjects with mild dementia were also involved. The results revealed evidence that careful design of serious games, with respect to in-game metrics, could potentially contribute to the early and unobtrusive detection of cognitive decline. |
