Aiming for a Better Understanding and Improvement of the Diagnosis and Prognosis of Patients With Disorders of Consciousness Through Multimodal Observations

Caregivers, Disorders of Consciousness, Minimally Conscious State, Unresponsive Wakefulness Syndrome

Clinical Neuroscience, Disorders of Consciousness, Neuroimaging, Brain-Body interactions, Multimodal precision diagnosis, Machine Learning, Caregivers well-being, Unresponsive wakefulness syndrome, Minimally conscious state

Improved treatment of severe brain injuries has resulted in increased survival rates. While some of these patients regain consciousness after a transient state of coma, others may develop a disorder of consciousness (DoC). Diagnosis of DoC currently relies on standardized behavioral assessment. The importance of accuracy in such diagnosis cannot be overstated, as it guides critical decisions on treatment (including pain management), and could underlie end-of-life decisions. Despite this importance, current behavioral diagnosis often fails, if because of the major sensory and motor deficits associated with DoC, or because of the heterogeneous etiology and pathophysiology associated with the condition. Finally, the need for accurate diagnosis and prognosis transcends the needs of the patients alone: caregiving of these patients is very stressful, principally for the large uncertainty associated with them. Thus, more accurate diagnosis and prognosis provide major relief for caregivers, and paradoxically, even if the news is not good. For all these reasons it is critical to developing personalized diagnosis and prognosis prediction tools that permit a stratified analysis at the single-patient level. The PerBrain Project will benefit from the multidisciplinary partners' expertise, and the unique opportunity to perform longitudinal assessments in four clinical sites through both established and novel electrophysiological, neuroimaging, and physiological techniques. Based on the collected data, the investigators will develop a multimodal personalized diagnostic tool for DoC patients using state-of-the-art computational tools, such as machine learning, in order to better determine the current state (diagnosis) and future outcome (prognosis). The overall aim of this project will provide for a better understanding of the pathophysiological mechanisms in DoC, which will, in turn, allow personalized rehabilitation strategies, and improved single-patient predictions of state and prognosis.

France, Germany, Israel, Italy