The role of perfusion, grey matter volume and behavioural phenotypes in the data-driven classification of cognitive syndromes

• Main Authors: Vipin, Ashwati, Lee, Bernett Teck Kwong, Kumar, Dilip, Soo, See Ann, Leow, Yi Jin, Ghildiyal, Smriti, Lee, Faith Phemie Hui En, Hilal, Saima, Kandiah, Nagaendran
• Other Authors: Lee Kong Chian School of Medicine (LKCMedicine)
• Format: Article
• Language: English
• Published: 2024
• Subjects: Medicine, Health and Life Sciences; Cognitive syndromes; Grey matter perfusion
• Online Access: https://hdl.handle.net/10356/174743
• Institution: Nanyang Technological University

Background: The use of structural and perfusion brain imaging in combination with behavioural information in the prediction of cognitive syndromes using a data-driven approach remains to be explored. Here, we thus examined the contribution of brain structural and perfusion imaging and behavioural features to the existing classification of cognitive syndromes using a data-driven approach. Methods: Study participants belonged to the community-based Biomarker and Cognition Cohort Study in Singapore who underwent neuropsychological assessments, structural-functional MRI and blood biomarkers. Participants had a diagnosis of cognitively normal (CN), subjective cognitive impairment (SCI), mild cognitive impairment (MCI) and dementia. Cross-sectional structural and cerebral perfusion imaging, behavioural scale data including mild behaviour impairment checklist, Pittsburgh Sleep Quality Index and Depression, Anxiety and Stress scale data were obtained. Results: Three hundred seventy-three participants (mean age 60.7 years; 56% female sex) with complete data were included. Principal component analyses demonstrated that no single modality was informative for the classification of cognitive syndromes. However, multivariate glmnet analyses revealed a specific combination of frontal perfusion and temporo-frontal grey matter volume were key protective factors while the severity of mild behaviour impairment interest sub-domain and poor sleep quality were key at-risk factors contributing to the classification of CN, SCI, MCI and dementia (p < 0.0001). Moreover, the glmnet model showed best classification accuracy in differentiating between CN and MCI cognitive syndromes (AUC = 0.704; sensitivity = 0.698; specificity = 0.637). Conclusions: Brain structure, perfusion and behavioural features are important in the classification of cognitive syndromes and should be incorporated by clinicians and researchers. These findings illustrate the value of using multimodal data when examining syndrome severity and provide new insights into how cerebral perfusion and behavioural impairment influence classification of cognitive syndromes.