q-bio.NCAug 13, 2026

Data-driven techniques for translational neuroscience and personalized neuro-health

Authors: Vishal Subedi, Shashipraba N. K. Rajakaruna, Pratyusha Sarkar, Subhankar Chattoraj, Anjali Khasa, Siddhartha Nandy, Hamza Farooq, Animikh Biswas, 

Organizations: Department of Mathematics and Statistics, University of Maryland Baltimore County, Baltimore, Maryland, USA · Department of Mathematics and Statistics, Texas Tech University, Lubbock, Texas, USA · Department of Information Systems, University of Maryland Baltimore County, Baltimore, Maryland, USA · Center for Magnetic Resonance Research, Department of Radiology, University of Minnesota, Minneapolis, Minnesota, USA · 

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Neurodegenexrative diseases such as Alzheimer's disease and Parkinson's disease are diagnosed most reliably only after substantial, often irreversible, neuronal loss has already occurred, creating an urgent need for quantitative tools that can detect subtle, early, and individual-specific brain changes from neuroimaging data. This review surveys a broad and rapidly evolving toolkit of data-driven techniques for translational neuroscience and personalized neuro-health, organized around four complementary methodological pillars. Throughout, we emphasize how these methodologically diverse approaches converge on a common translational goal: personalized, mechanistically grounded, and clinically actionable models of individual brain health, and we close by discussing the principal open statistical, computational, and clinical challenges that remain.

Figures & tables

Notation/AcronymDefinition (expanded form)
 Neuroscince related terms
ADHDattention deficit hyperactivity disorder
ADAlzheimer’s disease
ADNIAlzheimer’s Disease Neuroimaging Initiative
ASDautism spectrum disorder
dMRIdiffusion magnetic resonance imaging
Table 1: Some commonly used acronyms used in this paper. Some additional acronyms, that are less commonly used, are embedded in text as and when they arise.
Figure 1: An illustrative example of empirical likelihood-based inference in fMRI data. The left panel shows the masked region. The middle panel shows active voxels obtained using linear regression model in an axial slice, and the right panel is the its equivalent obtained using EL techniques.
Figure 2: Visualizations of the brain regions with absolute loading values greater than 0.05 for the first Bayesian covariate-assisted principal components, obtained using SSGP, GICA and SCFP parcellation techniques.
Figure 3: Illustration of the TDA steps for an MRI image.
\midrule Node typeADNI instantiation
\midrule SubjectParticipant, labelled CN / MCI / AD
Brain ROIFreeSurfer-parcellated regions from T1 MRI (hippocampus, entorhinal cortex, posterior cingulate, precuneus)
Imaging measureStructural MRI volume/thickness, FDG-PET, amyloid-PET ( 18 F-florbetapir), tau-PET ( 18 F-flortaucipir)
Fluid biomarkerCSF A β\beta 42, t-tau, p-tau181; plasma p-tau
Genetic markerAPOE ε\varepsilon 4 allele count; candidate SNPs; polygenic risk score
Cognitive / clinicalMMSE, ADAS-Cog, CDR-SB, RAVLT
Table 2: Vertex (node) types in the ADNI hypergraph and their instantiation in ADNI variables.
\midrule HyperedgeMembers it connectsHigher-order rationale
e1e_{1} Multimodal biomarker profileSubject ++ its discretised imaging, fluid, genetic, and cognitive markers at a visitDiagnosis is the joint configuration, not any single pair
e2e_{2} Subject similarity (kNN)A subject and its kk nearest neighbours in one modality’s feature spaceMultimodal hypergraph == union over modality-specific hyperedges
e3e_{3} Regional co-atrophy / co-activationA set of ROIs that jointly deviate (e.g., default-mode network)Captures network-level dysfunction across many regions at once
e4e_{4} Longitudinal trajectoryThe same subject’s states across visitsEncodes progression CN →\rightarrow MCI →\rightarrow AD
e5e_{5} Mechanistic bridgeGenetic, molecular, anatomical, and disease nodes (e.g., APOE–amyloid pathway–medial-temporal ROIs–AD)Links the cohort hypergraph to an external biomedical KG
\midrule  
Table 3: Hyperedge (higher-order relation) types in the ADNI hypergraph.
Figure 4: Schematic illustration of a hypergraph representation over ADNI entity types; nodes and memberships
More in this topic

Neuroimaging

Neuroimaging uses brain measurements and computational methods to map anatomy, activity, connectivity, and disease.

See all 235 papers

Explore similar work

CardsList

  1. Neuropsychiatric Deviations From Normative Profiles: An MRI-Derived Marker for Early Alzheimer's Disease Detection

    Apr 1, 2026Synne Hjertager Osenbroch, Lisa Ramona Rosvold, Yao Lu +1Clinical PredictionAlzheimer's Disease Progression Prediction

    Department of Computer Science and Electrical Engineering, University of Stavanger, Norway. · Department of Computer Science, University of Putra Malaysia, Selangor, Malaysia. · SMIL, Department of Radiology, Stavanger University Hospital (SUS), Norway.

  2. Cross-disorder Learning of Imaging-derived Joint Mophometric Markers in Alzheimer's and Parkinson's Diseases

    Oct 19, 2026Yuji Zhao, Boris GutmanParkinson's Disease ClassificationMedical Diagnosis

    Laboratory for Modeling and Computation in Imaging and Genetics (LAMCIG), Medical Imaging Research Center, Department of Biomedical Engineering, Illinois Institute of Technology, Chicago, Illinois, United States of America

  3. Emergence of Transfer Learning towards Specific Identification of Alzheimer's Disease A Prospective Approach

    Aug 13, 2026Soumik Podder, Chandramouli HaldarAlzheimer's Disease ClassificationTransfer Learning

    Department of Basic Science and Humanities Institute of Engineering and Management (IEM), University of Engineering and Management Kolkata Kolkata, India · Department of Computer Science and Engineering Guru Nanak Institute of Technology Kolkata, India