Methodology
Here is the updated Methodology section for the EBRAINS Wiki, incorporating the Generalized Neuro Biomarker Ontology Categorization (Neuromarker) for biomarker classification across all neurodegenerative diseases.
Neurodiagnoses AI: Multimodal AI for Neurodiagnostic Predictions
Project Overview
Neurodiagnoses AI implements AI-driven diagnostic and prognostic models for central nervous system (CNS) disorders, expanding the Florey Dementia Index (FDI) methodology to a broader set of neurological conditions. The approach integrates multimodal data sources (EEG, neuroimaging, biomarkers, and genetics) and employs machine learning models to provide explainable, real-time diagnostic insights. This framework now incorporates Neuromarker, a generalized biomarker ontology that categorizes biomarkers across neurodegenerative diseases, enabling standardized, cross-disease AI training.
Neuromarker: Generalized Biomarker Ontology
Neuromarker extends the Common Alzheimer’s Disease Research Ontology (CADRO) into a cross-disease biomarker categorization framework applicable to all neurodegenerative diseases (NDDs). It allows for standardized classification, AI-based feature extraction, and multimodal integration.
Core Biomarker Categories
The following ontology is used within Neurodiagnoses AI for biomarker categorization:
| Category | Description |
|---|---|
| Molecular Biomarkers | Omics-based markers (genomic, transcriptomic, proteomic, metabolomic, lipidomic) |
| Neuroimaging Biomarkers | Structural (MRI, CT), Functional (fMRI, PET), Molecular Imaging (tau, amyloid, α-synuclein) |
| Fluid Biomarkers | CSF, plasma, blood-based markers for tau, amyloid, α-synuclein, TDP-43, GFAP, NfL |
| Neurophysiological Biomarkers | EEG, MEG, evoked potentials (ERP), sleep-related markers |
| Digital Biomarkers | Gait analysis, cognitive/speech biomarkers, wearables data, EHR-based markers |
| Clinical Phenotypic Markers | Standardized clinical scores (MMSE, MoCA, CDR, UPDRS, ALSFRS, UHDRS) |
| Genetic Biomarkers | Risk alleles (APOE, LRRK2, MAPT, C9orf72, PRNP) and polygenic risk scores |
| Environmental & Lifestyle Factors | Toxins, infections, diet, microbiome, comorbidities |
How to Use External Databases in Neurodiagnoses
To enhance diagnostic accuracy, Neurodiagnoses AI integrates data from multiple biomedical and neurological research databases. Researchers can follow these steps to access, prepare, and integrate data into the Neurodiagnoses framework.
Potential Data Sources
Neurodiagnoses maintains an updated list of biomedical datasets relevant to neurodegenerative diseases:
- ADNI: Alzheimer's Disease Imaging & Biomarkers → ADNI
- PPMI: Parkinson’s Disease Imaging & Biospecimens → PPMI
- GP2: Whole-Genome Sequencing for PD → GP2
- Enroll-HD: Huntington’s Disease Clinical & Genetic Data → Enroll-HD
- GAAIN: Multi-Source Alzheimer’s Data Aggregation → GAAIN
- UK Biobank: Population-Wide Genetic, Imaging & Health Records → UK Biobank
- DPUK: Dementia & Aging Data → DPUK
- PRION Registry: Prion Diseases Clinical & Genetic Data → PRION Registry
- DECIPHER: Rare Genetic Disorder Genomic Variants → DECIPHER
1. Register for Access
- Each external database requires individual registration and access approval.
- Ensure compliance with ethical approvals and data usage agreements before integrating datasets into Neurodiagnoses.
- Some repositories may require a Data Usage Agreement (DUA) for sensitive medical data.
2. Download & Prepare Data
- Download datasets while adhering to database usage policies.
- Ensure files meet Neurodiagnoses format requirements:
| Data Type | Accepted Formats |
|---|---|
| Tabular Data | .csv, .tsv |
| Neuroimaging | .nii, .dcm |
| Genomic Data | .fasta, .vcf |
| Clinical Metadata | .json, .xml |
- Mandatory Fields for Integration:
- Subject ID: Unique patient identifier
- Diagnosis: Standardized disease classification
- Biomarkers: CSF, plasma, or imaging biomarkers
- Genetic Data: Whole-genome or exome sequencing
- Neuroimaging Metadata: MRI/PET acquisition parameters
3. Upload Data to Neurodiagnoses
Option 1: Upload to EBRAINS Bucket
- Location: EBRAINS Neurodiagnoses Bucket
- Ensure correct metadata tagging before submission.
Option 2: Contribute via GitHub Repository
- Location: GitHub Data Repository
- Create a new folder under /data/ and include a dataset description.
- For large datasets, contact project administrators before uploading.
4. Integrate Data into AI Models
- Open Jupyter Notebooks on EBRAINS to run preprocessing scripts.
- Standardize neuroimaging and biomarker formats using harmonization tools.
- Use machine learning models to handle missing data and feature extraction.
- Train AI models with newly integrated patient cohorts.
Reference: See docs/data_processing.md for detailed instructions.
AI-Driven Biomarker Categorization
Neurodiagnoses employs AI models for biomarker classification:
| Model Type | Application |
|---|---|
| Graph Neural Networks (GNNs) | Identify shared biomarker pathways across diseases |
| Contrastive Learning | Distinguish overlapping vs. unique biomarkers |
| Multimodal Transformer Models | Integrate imaging, omics, and clinical data |
Collaboration & Partnerships
Partnering with Data Providers
Neurodiagnoses seeks partnerships with data repositories to:
- Enable API-based data integration for real-time processing.
- Co-develop harmonized AI-ready datasets with standardized annotations.
- Secure funding opportunities through joint grant applications.
Interested in Partnering?
- If you represent a research consortium or database provider, reach out to explore data-sharing agreements.
- Contact: info@neurodiagnoses.com
Final Notes
Neurodiagnoses continuously expands its data ecosystem to support AI-driven clinical decision-making. Researchers and institutions are encouraged to contribute new datasets and methodologies.
For additional technical documentation:
- GitHub Repository: Neurodiagnoses GitHub
- EBRAINS Collaboration Page: EBRAINS Neurodiagnoses
If you experience issues integrating data, open a GitHub Issue or consult the EBRAINS Neurodiagnoses Forum.
This updated methodology now incorporates https://github.com/Fundacion-de-Neurociencias/neurodiagnoses/blob/main/data/biomarker_ontology for standardized biomarker classification, enabling cross-disease AI training across neurodegenerative disorders.