Neurodiagnoses
A new tridimensional diagnostic framework for complex CNS diseases
This project is focused on developing a novel nosological and diagnostic framework for complex CNS diseases by using advanced AI techniques and integrating data from neuroimaging, biomarkers, and biomedical ontologies.
We aim to create a structured, interpretable, and scalable diagnostic tool.
What is this about and what can I find here?
Overview
The classification and diagnosis of central nervous system (CNS) diseases have long been constrained by traditional, phenotype-based approaches that often fail to capture the complex interplay of pathophysiological mechanisms, molecular biomarkers, and neuroanatomical changes. Neurodiagnoses redefines this landscape by integrating advanced AI with multi-modal data—including genetics, neuroimaging, biomarkers, and digital health records—to create a more precise, scalable, and data-driven diagnostic system.
In addition to these clinical diagnostic approaches, Neurodiagnoses has expanded into a research-oriented platform through the integration of CNS Digital Twins. This cutting-edge concept involves creating a personalized digital replica of a patient’s CNS by incorporating multi-omics data (proteomics, genomics, lipidomics, transcriptomics), various neuroimaging modalities, and digital health information. These digital twins enable simulations of disease progression, support the discovery of novel biomarkers, and help identify new therapeutic targets.
On this page, you will find:
- Detailed descriptions of both the clinical diagnostic tools and the research framework.
- Access to our AI models, data processing pipelines, and digital twin simulations.
- Collaborative resources for researchers, clinicians, and AI developers.
- Guidelines and instructions on how to contribute to and expand the project.
The role of AI-powered annotation
To enhance standardization, interpretability, and clinical application, the framework integrates an AI-powered annotation system, which:
- Assign structured metadata tags to diagnostic features.
- Provides real-time contextual explanations for AI-based classifications.
- Tracks longitudinal disease progression using timestamped AI annotations.
- Improves AI model transparency through interpretability tools (e.g., SHAP analysis).
- Facilitates decision-making for clinicians by linking annotations to standardized biomedical ontologies (SNOMED, HPO).
Neurodiagnoses provides two complementary AI-driven diagnostic approaches:
1. Traditional Probabilistic Diagnosis
- AI provides multiple possible diagnoses, each assigned a probability percentage based on biomarker, imaging, and clinical data.
- Useful for differential diagnosis and treatment decision-making.
2. Tridimensional Diagnosis
- Diagnoses are structured based on:
(1) Etiology (genetic, autoimmune, metabolic, infectious)
(2) Molecular Biomarkers (amyloid-beta, tau, inflammatory markers, EEG patterns)
(3) Neuroanatomoclinical Correlations (brain atrophy, connectivity alterations) - This approach enables precise disease subtyping and biologically meaningful classification, particularly useful for tracking progression over time.
Both systems will be offered for every patient case, allowing clinicians to compare AI-generated probabilistic diagnosis with a structured tridimensional classification.
The case of neurodegenerative diseases
There have been described these 3 diagnostic axes:

Neurodegenerative diseases can be studied and classified in a tridimensional scheme with three axes: anatomic–clinical, molecular, and etiologic. CSF, cerebrospinal fluid; FDG, fluorodeoxyglucose; MRI, magnetic resonance imaging; PET, positron emission tomography.
Axis 1: Etiology
- Description: Focuses on genetic and sporadic causes, identifying risk factors and potential triggers.
- Examples: APOE ε4 as a genetic risk factor, or cardiovascular health affecting NDD progression.
- Tests: Genetic testing, lifestyle, and cardiovascular screening.
Axis 2: Molecular Markers
- Description: Analyzes primary (amyloid-beta, tau) and secondary biomarkers (NFL, GFAP) for tracking disease progression.
- Examples: CSF amyloid-beta concentrations to confirm Alzheimer’s pathology.
- Tests: Blood/CSF biomarkers, PET imaging (Tau-PET, Amyloid-PET).
Axis 3: Neuroanatomoclinical
- Description: Links clinical symptoms to neuroanatomical changes, such as atrophy or functional impairments.
- Examples: Hippocampal atrophy correlating with memory deficits.
- Tests: MRI volumetrics, FDG-PET, neuropsychological evaluations.
Applications
This system enhances:
- Research: By stratifying patients, reduces cohort heterogeneity in clinical trials.
- Clinical Practice: Provides dynamic diagnostic annotations with timestamps for longitudinal tracking.
How to Contribute
- Access the `/docs` folder for guidelines.
- Use `/code` for the latest AI pipelines.
- Share feedback and ideas in the wiki discussion pages.
- Join the Discussion Forum at GitHub
Key Objectives
- Develop interpretable AI models for diagnosis and progression tracking.
- Integrate data from Human Phenotype Ontology (HPO), Gene Ontology (GO), and other biomedical resources.
- Foster collaboration among neuroscientists, AI researchers, and clinicians.
- Provide a dual diagnostic system:
- Probabilistic Diagnosis – AI assigns multiple traditional possible diagnoses with probability percentages.
- Tridimensional Diagnosis – AI structures diagnoses based on etiology, biomarkers, and neuroanatomical correlations.
Who has access?
We welcome contributions from the global community. Join us as we transform CNS diagnostics and drive precision medicine forward through a collaborative, open-source approach. Let’s build the future of neurological diagnostics together!
Main contents
- `/docs`: Documentation and contribution guidelines.
- `/code`: Machine learning pipelines and scripts.
- `/data`: Sample datasets for testing.
- `/outputs`: Generated models, visualizations, and reports.
- Methodology
- Notebooks
- Results
- to-do-list