New York/Stuttgart – 50 million people around the world have dementia. About two-thirds of these individuals have Alzheimer’s disease. Early detection of Mild Cognitive Impairment, which may lead to Alzheimer’s disease, is essential to slow down the cognitive decline process. In a recent pilot study, published in Methods of Information in Medicine (Thieme Publishers, New York. 2018), researchers found that three digital games had a full success rate in detecting Alzheimer’s disease and Mild Cognitive Impairment.
Traditional tests for Alzheimer’s disease and Mild Cognitive Impairment are time-consuming, affected by factors that distort the results, and are usually administered when it is already too late for preventive treatment. Alternatives to classical tests are therefore very much in demand. In a preliminary study published in Methods of Information in Medicine, Sonia Valladares-Rodriguez from the University of Vigo, Spain, and her co-authors present and evaluate six digital games, to detect Alzheimer’s disease and Mild Cognitive Impairment. The so-called serious games are used for learning, evaluation or training and include a playful component as a motivation element.
The battery of six games, named “Panoramix”, assesses the main early cognitive markers, specifically: memory, executive functions, attention and, gnosia, which is the capacity to interpret and assign meaning to information. The Panoramix battery was put to the test in a cohort study of 16 seniors, including people with Alzheimer’s disease and Mild Cognitive Impairment as well as healthy individuals. When used with machine learning methods, a combination of three games showed a hundred percent success rate in differentiating between healthy subjects and those with Alzheimer’s disease or Mild Cognitive Impairment. In the “Procedurix” game, which measures procedural memory and motor coordination, the subject must track a rotating circle as accurately as possible. The semantic memory of the subject is tested in the “Semantix” game, which consists of 52 sets of chips with three images. Episodic memory allows humans to recall past experiences. In the “Episodix” game the subject takes a virtual walk through a town and memorizes a list of objects that need to be recalled.
According to the authors, the results demonstrate the solid potential of digital serious games and machine learning for the early detection of dementia processes. The promising outcome should encourage further research with the aim of eventually introducing this technique for the clinical diagnosis of cognitive impairment. The authors are convinced, that an early diagnosis facilitated by digital serious games would enable the provision of timely interventions to support individuals affected.
Sonia Valladares-Rodriguez et al.:
Learning to Detect Cognitive Impairment through Digital Games and Machine Learning Techniques
Methods of Information in Medicine 2018; 57; Page 197-207.
About Methods of Information in Medicine
Since the journal's founding in 1962, Methods of Information in Medicine has stressed the methodology and scientific fundamentals of organizing, representing and analyzing data, information and knowledge in biomedicine and health care. Covering publications in the fields of biomedical and health informatics, medical biometry, and epidemiology, the journal publishes original papers, reviews, reports, opinion papers, editorials, and letters to the editor. From time to time, the journal publishes articles on particular focus themes as part of a journal's issue.
Thieme Publishing Group is a medical and scientific publishing house employing more than 900 staff and maintaining offices in seven cities, including New York, Delhi, Rio and Stuttgart, Germany. Founded in 1886, the Thieme name has become synonymous with high quality and excellence in online and print publishing. Thieme publishes 150 peer-reviewed journals and more than 450 new books annually. The company has a rapidly growing array of web-based products in medicine and science. State-of-the-art online products include eNeurosurgery, Medlantis, Thieme E-Journals, Thieme Electronic Book Library, the medical student website WinkingSkull.com and Thieme Teaching Assistant, an innovative web-based platform for faculty. For more information about Thieme, please visit www.thieme.com.
Public Relations and Press Office
Thieme Publishing Group