Behaviours in REM sleep: personalised Automatic 3D Video Analysis as novel tool to detect alpha-synucleinopathies – BRAVA

Rapid eye movement (REM) sleep behaviour disorder (RBD) is characterized by abnormal muscular activity and dream enactment in REM sleep. In its isolated form (iRBD), it is recognized as an early alpha- h Lewy bodies and multiple system atrophy). Due to the low number of specialized sleep centres and the fact that the disorder might remain unnoticed, iRBD is often not recognized. An early, accurate, automated and population extended recognition of iRBD, however, would be essential to recognize patients in early stages of alpha-synucleinopathies, enabling timely begin of disease modifying treatments. Furthermore, objective and automated methods would improve follow up of iRBD patients and allow personalised treatments. We aim to develop and validate a novel small, light and portable 3D video-based technology employing artificial intelligence as powerful, automatic, stand-alone instrument to identify and follow-up iRBD patients. The technology will be validated in sleep centres and compared to gold standard video-polysomnography, posing the basis for future implementation of 3D video in home environments. The proposed project will be carried out by a consortium of five European sleep centres. To develop a robust and high-standard technology, the multicentric ruitment of participants will ensure excellent representation of both genders, a large iRBD cohort and inclusion of different conditions mimicking RBD. By the end of the project, we expect that 3D video will be validated and ready to be established as a novel and powerful stand-alone technique to reliably identify and follow-up iRBD patients. We believe that this novel tool can revolutionize the way in which iRBD patients are identified, allowing better identification of early-stage alpha-synucleinopathies. Furthermore, this technology will allow to have objective measures of the efficacy of symptomatic treatments, thus making possible to personalise them.