VSM appears to be a valid method of screening for MCI in an older adult population though it cannot be used for MCI subtype assessment. VSM's concurrent validity is supported by the large number of correlations between the VSM and established tests. It is considered a robust test on its own as the inclusion of other tests failed to improve its CCR significantly.

The VR application exhibited very high accuracy in detecting MCI while all participants were able to operate the tablet and application on their own. Diagnostic accuracy was improved compared to a previous study using data from only one administration of the exercise. The results of the present study suggest that remote MCI detection through VR applications can be feasible.

The use of Convolutional Neural Networks (CNNs) as a feature learning method for Human Activity Recognition (HAR) is becoming more and more common. Unlike conventional machine learning methods, which require domain-specific expertise, CNNs can extract features automatically. On the other hand, CNNs require a training phase, making them prone to the cold-start problem. In this work, a case study is presented where the use of a pre-trained CNN feature extractor is evaluated under realistic conditions. The case study consists of two main steps: (1) different topologies and parameters are assessed to identify the best candidate models for HAR, thus obtaining a pre-trained CNN model. The pre-trained model (2) is then employed as feature extractor evaluating its use with a large scale real-world dataset. Two CNN applications were considered: Inertial Measurement Unit (IMU) and audio based HAR. For the IMU data, balanced accuracy was 91.98% on the UCI-HAR dataset, and 67.51% on the real-world Extrasensory dataset. For the audio data, the balanced accuracy was 92.30% on the DCASE 2017 dataset, and 35.24% on the Extrasensory dataset.