What is it about?
We discuss the validation of a new digital application for the early detection of cognitive impairment, based on artificial intelligence for patient classification, and more specifically on machine learning algorithms. To evaluate the discrimination power of this application, a cross-sectional pilot study was carried out involving 30 subjects: 10 health control subjects; 14 individuals with mild cognitive impairment and 6 early-stage Alzheimer’s patients. The study was carried out in two separate sessions. All participants completed the study, and no concerns were raised about the acceptability of the test. Analysis including socio-demographics and game data supports the prediction of participants’ cognitive status using machine learning algorithms. According to the performance metrics computed, best classification results are obtained a Multilayer Perceptron classifier, Support Vector Machines and Random Forest, respectively, with weighted recall values >= 0.9784 ± 0.0265 and F1-score = 0.9764 ± 0.0291. Furthermore, thanks to hyper-parameter optimization, false negative rates were dramatically reduced. Shapley’s additive planning (SHAP) applied according to the eXplicable AI (XAI) method, made it possible to visually and quantitatively evaluate the importance of the different features in the final classification.
Featured Image
Photo by Georg Arthur Pflueger on Unsplash
Why is it important?
After playing during 40 minutes with three simple computer games, we can identify whether a senior adult suffers from mild cognitive impairment. This paves the way for cost-effective user-friendly screening instruments for cognitive deterioration.
Perspectives
This research was specially rewarding because cognitive deterioration can be a sign of many different underlying health conditions, so it is important to detect it early. By doing so, you can get the treatment you need as soon as possible and improve your chances of a successful outcome.
Prof. Manuel Fernandez-Iglesias
atlanTTic - University of Vigo
Read the Original
This page is a summary of: Evaluation of the Predictive Ability and User Acceptance of Panoramix 2.0, an AI-Based E-Health Tool for the Detection of Cognitive Impairment, Electronics, October 2022, MDPI AG,
DOI: 10.3390/electronics11213424.
You can read the full text:
Resources
‘Panoramix’, el videojuego que detecta que algo va mal en el cerebro antes de que aparezca el alzhéimer
Article about our research published in El Pais, the reference Spanish newspaper.
Panoramix: detecting cognitive impairment through digital games
The atlanTTic research center of the University of Vigo is one of the successful applications to be selected in the first Gatekeeper Open Call. The pilot aimed to exploit Gatekeeper's Data Federation to manage the information captured by the Panoramix battery of digital games for the detection of cognitive impairment, as well as to integrate the games into the Gatekeeper marketplace.
Contributors
The following have contributed to this page
