Application of Structural and Functional Connectome Mismatch for Classification and Individualized Therapy in Alzheimer Disease

Abstract

While machine learning approaches to analyzing Alzheimer disease connectome neuroimaging data have been studied, many have limited ability to provide insight in individual patterns of disease and lack the ability to provide actionable information about where in the brain a specific patient's disease is located. We studied a cohort of patients with Alzheimer disease who underwent resting state functional magnetic resonance imaging and diffusion tractography imaging. These images were processed, and a structural and functional connectivity matrix was generated using the HCP cortical and subcortical atlas. By generating a machine learning model, individual-level structural and functional anomalies detection and characterization were explored in this study. Our study found that structural disease burden in Alzheimer's patients is mainly focused in the subcortical structures and the Default mode network (DMN). Interestingly, functional anomalies were less consistent between individuals and less common in general in these patients. More intriguing was that some structural anomalies were noted in all patients in the study, namely a reduction in fibers involving parcellations in the right anterior cingulate. Alternately, the functional consequences of connectivity loss were cortical and variable. Integrated structural/functional connectomics might provide a useful tool for assessing AD progression, while few concerns have been made for analyzing the mismatch between these two. We performed a preliminary exploration into a set of Alzheimer disease data, intending to improve a personalized approach to understanding individual connectomes in an actionable manner. Specifically, we found that there were consistent patterns of white matter fiber loss, mainly focused around the DMN and deep subcortical structures, which were present in nearly all patients with clinical AD. Functional magnetic resonance imaging shows abnormal functional connectivity different within the patients, which may be used as the individual target for further therapeutic strategies making, like non-invasive stimulation technology.

Reducing the Cognitive Footprint of Brain Tumor Surgery

“…As expected, some similarities were found between patients, namely that there was consistent structural white matter loss focused around the DMN and subcortical structures. However, there was also significant heterogeneity in abnormal functional connectivity between patients, suggesting the opportunity to individualize future therapeutic strategies possibly based on different clinical phenotypes, moving us steps closer to true precision medicine (80). Similar work has been…”

“…Furthermore, the allocation of resources and switching between these two networks based on stimulus orientation and changes in tasks is thought to be mediated by the SN, a cingulo-opercular network (77). Unsurprisingly, abnormal connectivity or disconnection in these major networks can lead to cognitive depletion and impaired higher-order cognitive abilities, with recent evidence suggesting their dysfunction likely forms the underlying basis of many known neurologic and psychiatric disorders, including schizophrenia, depression, and anxiety (79,80). Thus, perioperative knowledge of these main cognitive networks is imperative to truly optimize patient cognitive status in cerebral surgery.…”

“…However, to answer a complex question such as this, we must strive to get down to the level of individual connectomes and neural microcircuits, and this requires big data that can be best handled with advanced computational algorithms offered with machine learning (ML) (108). In a cohort of patients with Alzheimer's disease who underwent rsfMRI and diffusion tensor imaging, we utilized ML to generate and detect individual-level anomalies in the structural and functional connectome (80). As expected, some similarities were found between patients, namely that there was consistent structural white matter loss focused around the DMN and subcortical structures.…”

Interventional Neurorehabilitation for Promoting Functional Recovery Post-Craniotomy: A Proof-of-Concept

“…language) between our patient and a normative atlas. Adopted with permission from Reference [48] . resulting in total anterior brain shift.…”

Dynamics of Functional Network Organization Through Graph Mixture Learning

“…Even though DMNs brain regions are similar among all the rest phases of the task fMRI and RS, they may vary in the way they connect. Different studies have tried to capture how the DMN differs in different neurological conditions [54,70,65,62]. That is why we finally focus our attention to the similarities and differences of the DMN patterns estimated during the rest epochs across all task paradigms and during resting state.…”