Study Protocol for Characteristics of Neurovascular Discoupling of Cognitive Impairment in Insomnia Based on Multimodal MRI

Abstract

Insomnia disorder (ID) may develop into mild cognitive impairment (MCI) or even dementia. However, there is a lack of reliable objective methods for the identification of MCI in ID patients. Neurovascular coupling (NVC) abnormality may be a potential biological marker of MCI in ID patients, but its characteristics in ID have not been fully explored. Therefore, exploring the imaging features of NVC disorder in patients with ID based on functional magnetic resonance imaging (fMRI) and combining clinical information and neuropsychological features to develop a machine learning-based algorithm may help to detect MCI in ID. In this study, ID patients aged 30-60 and healthy controls (HC) will be recruited and divided into ID with MCI (ID-MCI), simple ID, and HC groups based on neuropsychological evaluation. Resting-state magnetic resonance imaging (rs-fMRI) will be used to explore the characteristics of NVC disorders in patients with ID-MCI based on Blood oxygen-level dependent (BOLD) and arterial spin labeling (ASL) methods. Then, the have been selected features and related clinical features will be set into the classifier model using privileged information. Finally, the optimal model will be trained and the classification performance will be obtained using the testing data. This study will reveal the imaging characteristics of NVC disorders in patients with ID-MCI based on fMRI, and provide a machine learning model for the diagnosis of MCI in patients with ID and has potential clinical significance for timely intervention and treatment to delay the development of MCI.