Health informatics tools for the assessment and rehabilitation of Central Nervous System diseases such as dementias, have grown steeply over the last decade both in number and robustness (Rose, Brooks, & Rizzo, 2005). Particular emphasis has been put on the development of virtual reality (VR) applications due to their scope for patient immersion in naturalistic environments. Some are aimed at restoring motor functions after brain damage (eFisioTrack; (Ruiz-Fernandez, Marin-Alonso, Soriano-Paya, & Garcia-Perez, 2014); BioTrak; (Llorens et al., 2011); SeeMe; (Sugarman, Weisel-Eichler, Burstin, & Brown, 2011), Rehabilitation Gaming System – RGS; (da Silva, Bermudez, Duarte, & Verschure, 2011; Cameirao, Badia, Oller, & Verschure, 2010)), others pursue a more personalised approach which allow the therapist to tailor intervention plans to meet the individual’s changing abilities (Tost et al., 2009). However, available systems still face important challenges. They still lack the desire ecological validity and flexibility needed to achieve patient adherence to treatment and sustained improvements post-intervention. To achieve ecological validity, such systems should be meaningful to the individual (Clare et al., 2010), that is, they should follow a naturalistic approach through which cognitive abilities can be enhanced in contexts and with tasks familiar to the affected person. Such a familiarity would more likely enable transfer of training from VR environments to real world situations, gradually increasing independence and quality of life in a sustainable manner (Zell et al., 2013). The flexibility component should allow tailoring the demands of the intervention plan in an intelligent and theory-driven manner reducing the need for therapist-centred interventions and consequently health care costs. This adaptive technology would improve the usability of VR systems gradually increasing treatment compliance. It would render the patient’s experience not only more productive (i.e., via meaningfulness) but also more encouraging. VRAIS will tackle these two challenges by merging VR interactive systems and artificial intelligence (AI). VRAIS will rest on the following pillars: (1) it will operate in a theory-driven manner, (2) it will enhance cognition by linking, in a meaningful way, virtual and real experiences in daily living settings, (3) it will monitor the physical impact of cognitive enhancement, and (4) it will integrate different sources of information to tailor advice that highlights the links across virtual and real environments (intelligent advisor) and to generate digital case notes which will be submitted to the health care team via telecare platforms (Brennan, Mawson, & Brownsell, 2009; Kairy, Lehoux, Vincent, & Visintin, 2009).
Objectives and hypotheses
1. Integration. Integrate VR platforms such as environment, monitor, and advisor through an AI engine which operates in a theory-driven fashion (i.e., using cognitive variables). Hypothesis: a self-regulated and interactive system that delivers the right task (i.e., demands) in the precise moment accompanied by tailored cues, all led by the individual’s underlying cognitive status, will promote functionality, treatment adherence, and well-being.
2. Meaningfulness. Promote independence and slow down cognitive decline via meaningful tasks performed in meaningful environments delivered in a controlled and systematic way. Hypothesis: immersion in VR experiences that can be naturally connected to real world challenges, will allow the development of compensatory strategies which will prolong the ability to live and function independently.
3. Attainability. Deliver a system that sets achievable targets both for patients and health professionals through a bio-psycho-social approach to intervention. Hypothesis: integrating biological (e.g., physical and cognitive), psychological (e.g., motivations, well-being), and social variables (i.e., social interactions,
Brennan, D. M., Mawson, S., & Brownsell, S. (2009). Telerehabilitation: enabling the remote delivery of healthcare, rehabilitation, and self management. Stud.Health Technol.Inform., 145, 231-248.
Cameirao, M. S., Badia, S. B., Oller, E. D., & Verschure, P. F. (2010). Neurorehabilitation using the virtual reality based Rehabilitation Gaming System: methodology, design, psychometrics, usability and validation. J.Neuroeng.Rehabil., 7, 48.
Clare, L., Linden, D. E., Woods, R. T., Whitaker, R., Evans, S. J., Parkinson, C. H. et al. (2010). Goal-oriented cognitive rehabilitation for people with early-stage Alzheimer disease: a single-blind randomized controlled trial of clinical efficacy. American Journal of Geriatric Psychiatry, 18, 928-939.
da Silva, C. M., Bermudez, I. B., Duarte, E., & Verschure, P. F. (2011). Virtual reality based rehabilitation speeds up functional recovery of the upper extremities after stroke: a randomized controlled pilot study in the acute phase of stroke using the rehabilitation gaming system. Restor.Neurol.Neurosci., 29, 287-298.
Kairy, D., Lehoux, P., Vincent, C., & Visintin, M. (2009). A systematic review of clinical outcomes, clinical process, healthcare utilization and costs associated with telerehabilitation. Disabil.Rehabil., 31, 427-447.
Llorens, R., Gil-Gomez, J. A., Mesa-Gresa, P., Alcaniz, M., Colomer, C., & Noe, E. (2011). BioTrak: a comprehensive overview. In Virtual Rehabilitation (ICVR), 2011 International Conference on (pp. 1-6).
Rose, F. D., Brooks, B. M., & Rizzo, A. A. (2005). Virtual reality in brain damage rehabilitation: review. Cyberpsychol.Behav., 8, 241-262.
Ruiz-Fernandez, D., Marin-Alonso, O., Soriano-Paya, A., & Garcia-Perez, J. D. (2014). eFisioTrack: A Telerehabilitation Environment Based on Motion Recognition Using Accelerometry. ScientificWorldJournal., 2014, 495391.
Sugarman, H., Weisel-Eichler, A., Burstin, A., & Brown, R. (2011). Use of novel virtual reality system for the assessment and treatment of unilateral spatial neglect: A feasibility study. In Virtual Rehabilitation (ICVR), 2011 International Conference on (pp. 1-2).
Tost, D., Grau, S., Ferre, M., Garcia, P., Tormos, J. M., Garcia, A. et al. (2009). PREVIRNEC: A cognitive telerehabilitation system based on Virtual Environments. In Virtual Rehabilitation International Conference, 2009 (pp. 87-93).
Zell, E., Dyck, E., Kohsik, A., Grewe, P., Flentge, D., Winter, Y. et al. (2013). OctaVis: A Virtual Reality System for Clinical Studies and Rehabilitation. In Eurographics Medical Prize Papers (pp. 9-12).