Changes for page Methodology

Last modified by manuelmenendez on 2025/03/14 08:31

From 5.1 to 4.3 From 13.1 to 12.2

From version 12.2

edited by manuelmenendez
on 2025/02/09 09:54

Change comment: There is no comment for this version

To version 5.1

edited by manuelmenendez
on 2025/01/29 19:11

Change comment: There is no comment for this version

Raw
Rendered

Summary

Page properties (1 modified, 0 added, 0 removed)

Details

Page properties

Content

@@ -1,273 +1,109 @@
--==== **Overview** ====
++=== **Overview** ===
--This project develops a **tridimensional diagnostic framework** for **CNS diseases**, incorporating **AI-powered annotation tools** to improve **interpretability, standardization, and clinical utility**. The methodology integrates **multi-modal data**, including **genetic, neuroimaging, neurophysiological, and biomarker datasets**, and applies **machine learning models** to generate **structured, explainable diagnostic outputs**.
++This section describes the step-by-step process used in the **Neurodiagnoses** project to develop a novel diagnostic framework for neurological diseases. The methodology integrates artificial intelligence (AI), biomedical ontologies, and computational neuroscience to create a structured, interpretable, and scalable diagnostic system.
--=== **Workflow** ===
--
--1. (((
--**We Use GitHub to [[Store and develop AI models, scripts, and annotation pipelines.>>https://github.com/Fundacion-de-Neurociencias/neurodiagnoses/discussions]]**
--
--* Create a **GitHub repository** for AI scripts and models.
--* Use **GitHub Projects** to manage research milestones.
--)))
--1. (((
--**We Use EBRAINS for Data & Collaboration**
--
--* Store **biomarker and neuroimaging data** in **EBRAINS Buckets**.
--* Run **Jupyter Notebooks** in **EBRAINS Lab** to test AI models.
--* Use **EBRAINS Wiki** for structured documentation and research discussion.
--)))
--
  ----
  === **1. Data Integration** ===
--== Overview ==
--
--
--Neurodiagnoses integrates clinical data via the **EBRAINS Medical Informatics Platform (MIP)**. MIP federates decentralized clinical data, allowing Neurodiagnoses to securely access and process sensitive information for AI-based diagnostics.
--
--== How It Works ==
--
--
--1. (((
--**Authentication & API Access:**
--
--* Users must have an **EBRAINS account**.
--* Neurodiagnoses uses **secure API endpoints** to fetch clinical data (e.g., from the **Federation for Dementia**).
--)))
--1. (((
--**Data Mapping & Harmonization:**
--
--* Retrieved data is **normalized** and converted to standard formats (.csv, .json).
--* Data from **multiple sources** is harmonized to ensure consistency for AI processing.
--)))
--1. (((
--**Security & Compliance:**
--
--* All data access is **logged and monitored**.
--* Data remains on **MIP servers** using **federated learning techniques** when possible.
--* Access is granted only after signing a **Data Usage Agreement (DUA)**.
--)))
--
--== Implementation Steps ==
--
--
--1. Clone the repository.
--1. Configure your **EBRAINS API credentials** in mip_integration.py.
--1. Run the script to **download and harmonize clinical data**.
--1. Process the data for **AI model training**.
--
--For more detailed instructions, please refer to the **[[MIP Documentation>>url:https://mip.ebrains.eu/]]**.
--
------
--
--= Data Processing & Integration with Clinica.Run =
--
--
--== Overview ==
--
--
--Neurodiagnoses now supports **Clinica.Run**, an open-source neuroimaging platform designed for **multimodal data processing and reproducible neuroscience workflows**.
--
--== How It Works ==
--
--
--1. (((
--**Neuroimaging Preprocessing:**
--
--* MRI, PET, EEG data is preprocessed using **Clinica.Run pipelines**.
--* Supports **longitudinal and cross-sectional analyses**.
--)))
--1. (((
--**Automated Biomarker Extraction:**
--
--* Standardized extraction of **volumetric, metabolic, and functional biomarkers**.
--* Integration with machine learning models in Neurodiagnoses.
--)))
--1. (((
--**Data Security & Compliance:**
--
--* Clinica.Run operates in **compliance with GDPR and HIPAA**.
--* Neuroimaging data remains **within the original storage environment**.
--)))
--
--== Implementation Steps ==
--
--
--1. Install **Clinica.Run** dependencies.
--1. Configure your **Clinica.Run pipeline** in clinica_run_config.json.
--1. Run the pipeline for **preprocessing and biomarker extraction**.
--1. Use processed neuroimaging data for **AI-driven diagnostics** in Neurodiagnoses.
--
--For further information, refer to **[[Clinica.Run Documentation>>url:https://clinica.run/]]**.
--
--====   ====
--
  ==== **Data Sources** ====
--[[List of potential sources of databases>>https://github.com/Fundacion-de-Neurociencias/neurodiagnoses/blob/main/data/sources/list_of_potential_databases]]
++* **Biomedical Ontologies**:
++** Human Phenotype Ontology (HPO) for phenotypic abnormalities.
++** Gene Ontology (GO) for molecular and cellular processes.
++* **Neuroimaging Datasets**:
++** Example: Alzheimer’s Disease Neuroimaging Initiative (ADNI), OpenNeuro.
++* **Clinical and Biomarker Data**:
++** Anonymized clinical reports, molecular biomarkers, and test results.
--**Biomedical Ontologies & Databases:**
--* **Human Phenotype Ontology (HPO)** for symptom annotation.
--* **Gene Ontology (GO)** for molecular and cellular processes.
++==== **Data Preprocessing** ====
--**Dimensionality Reduction and Interpretability:**
++1. **Standardization**: Ensure all data sources are normalized to a common format.
++1. **Feature Selection**: Identify relevant features for diagnosis (e.g., biomarkers, imaging scores).
++1. **Data Cleaning**: Handle missing values and remove duplicates.
--* **Evaluate interpretability** using metrics like the **Area Under the Interpretability Curve (AUIC)**.
--* **Leverage [[DEIBO>>https://github.com/Mellandd/DEIBO]] (Data-driven Embedding Interpretation Based on Ontologies)** to connect model dimensions to ontology concepts.
--
--**Neuroimaging & EEG/MEG Data:**
--
--* **MRI volumetric measures** for brain atrophy tracking.
--* **EEG functional connectivity patterns** (AI-Mind).
--
--**Clinical & Biomarker Data:**
--
--* **CSF biomarkers** (Amyloid-beta, Tau, Neurofilament Light).
--* **Sleep monitoring and actigraphy data** (ADIS).
--
--**Federated Learning Integration:**
--
--* **Secure multi-center data harmonization** (PROMINENT).
--
  ----
--==== **Annotation System for Multi-Modal Data** ====
--
--To ensure **structured integration of diverse datasets**, **Neurodiagnoses** will implement an **AI-driven annotation system**, which will:
--
--* **Assign standardized metadata tags** to diagnostic features.
--* **Provide contextual explanations** for AI-based classifications.
--* **Track temporal disease progression annotations** to identify long-term trends.
--
------
--
  === **2. AI-Based Analysis** ===
--==== **Machine Learning & Deep Learning Models** ====
++==== **Model Development** ====
--**Risk Prediction Models:**
++* **Embedding Models**: Use pre-trained models like BioBERT or BioLORD for text data.
++* **Classification Models**:
++** Algorithms: Random Forest, Support Vector Machines (SVM), or neural networks.
++** Purpose: Predict the likelihood of specific neurological conditions based on input data.
--* **LETHE’s cognitive risk prediction model** integrated into the annotation framework.
++==== **Dimensionality Reduction and Interpretability** ====
--**Biomarker Classification & Probabilistic Imputation:**
++* Leverage [[DEIBO>>https://drive.ebrains.eu/f/8d7157708cde4b258db0/]] (Data-driven Embedding Interpretation Based on Ontologies) to connect model dimensions to ontology concepts.
++* Evaluate interpretability using metrics like the Area Under the Interpretability Curve (AUIC).
--* **KNN Imputer** and **Bayesian models** used for handling **missing biomarker data**.
--
--**Neuroimaging Feature Extraction:**
--
--* **MRI & EEG data** annotated with **neuroanatomical feature labels**.
--
--==== **AI-Powered Annotation System** ====
--
--* Uses **SHAP-based interpretability tools** to explain model decisions.
--* Generates **automated clinical annotations** in structured reports.
--* Links findings to **standardized medical ontologies** (e.g., **SNOMED, HPO**).
--
  ----
--=== **3. Diagnostic Framework & Clinical Decision Support** ===
++=== **3. Diagnostic Framework** ===
--==== **Tridimensional Diagnostic Axes** ====
++==== **Axes of Diagnosis** ====
--**Axis 1: Etiology (Pathogenic Mechanisms)**
++The framework organizes diagnostic data into three axes:
--* Classification based on **genetic markers, cellular pathways, and environmental risk factors**.
--* **AI-assisted annotation** provides **causal interpretations** for clinical use.
++1. **Etiology**: Genetic and environmental risk factors.
++1. **Molecular Markers**: Biomarkers such as amyloid-beta, tau, and alpha-synuclein.
++1. **Neuroanatomical Correlations**: Results from neuroimaging (e.g., MRI, PET).
--**Axis 2: Molecular Markers & Biomarkers**
++==== **Recommendation System** ====
--* **Integration of CSF, blood, and neuroimaging biomarkers**.
--* **Structured annotation** highlights **biological pathways linked to diagnosis**.
++* Suggests additional tests or biomarkers if gaps are detected in the data.
++* Prioritizes tests based on clinical impact and cost-effectiveness.
--**Axis 3: Neuroanatomoclinical Correlations**
--
--* **MRI and EEG data** provide anatomical and functional insights.
--* **AI-generated progression maps** annotate **brain structure-function relationships**.
--
  ----
--=== **4. Computational Workflow & Annotation Pipelines** ===
++=== **4. Computational Workflow** ===
--==== **Data Processing Steps** ====
++1. **Data Loading**: Import data from storage (Drive or Bucket).
++1. **Feature Engineering**: Generate derived features from the raw data.
++1. **Model Training**:
++1*. Split data into training, validation, and test sets.
++1*. Train models with cross-validation to ensure robustness.
++1. **Evaluation**:
++1*. Metrics: Accuracy, F1-Score, AUIC for interpretability.
++1*. Compare against baseline models and domain benchmarks.
--**Data Ingestion:**
--
--* **Harmonized datasets** stored in **EBRAINS Bucket**.
--* **Preprocessing pipelines** clean and standardize data.
--
--**Feature Engineering:**
--
--* **AI models** extract **clinically relevant patterns** from **EEG, MRI, and biomarkers**.
--
--**AI-Generated Annotations:**
--
--* **Automated tagging** of diagnostic features in **structured reports**.
--* **Explainability modules (SHAP, LIME)** ensure transparency in predictions.
--
--**Clinical Decision Support Integration:**
--
--* **AI-annotated findings** fed into **interactive dashboards**.
--* **Clinicians can adjust, validate, and modify annotations**.
--
  ----
--=== **5. Validation & Real-World Testing** ===
++=== **5. Validation** ===
--==== **Prospective Clinical Study** ====
++==== **Internal Validation** ====
--* **Multi-center validation** of AI-based **annotations & risk stratifications**.
--* **Benchmarking against clinician-based diagnoses**.
--* **Real-world testing** of AI-powered **structured reporting**.
++* Test the system using simulated datasets and known clinical cases.
++* Fine-tune models based on validation results.
--==== **Quality Assurance & Explainability** ====
++==== **External Validation** ====
--* **Annotations linked to structured knowledge graphs** for improved transparency.
--* **Interactive annotation editor** allows clinicians to validate AI outputs.
++* Collaborate with research institutions and hospitals to test the system in real-world settings.
++* Use anonymized patient data to ensure privacy compliance.
  ----
  === **6. Collaborative Development** ===
--The project is **open to contributions** from **researchers, clinicians, and developers**.
++The project is open to contributions from researchers, clinicians, and developers. Key tools include:
--**Key tools include:**
--
  * **Jupyter Notebooks**: For data analysis and pipeline development.
--** Example: **probabilistic imputation**
++** Example: [[probabilistic imputation>>https://drive.ebrains.eu/f/4f69ab52f7734ef48217/]]
  * **Wiki Pages**: For documenting methods and results.
  * **Drive and Bucket**: For sharing code, data, and outputs.
--* **Collaboration with related projects**:
--** Example: **Beyond the hype: AI in dementia – from early risk detection to disease treatment**
++* **Collaboration with related projects: **For instance: [[//Beyond the hype: AI in dementia – from early risk detection to disease treatment//>>https://www.lethe-project.eu/beyond-the-hype-ai-in-dementia-from-early-risk-detection-to-disease-treatment/]]
  ----
  === **7. Tools and Technologies** ===
--==== **Programming Languages:** ====
--
--* **Python** for AI and data processing.
--
--==== **Frameworks:** ====
--
--* **TensorFlow** and **PyTorch** for machine learning.
--* **Flask** or **FastAPI** for backend services.
--
--==== **Visualization:** ====
--
--* **Plotly** and **Matplotlib** for interactive and static visualizations.
--
--==== **EBRAINS Services:** ====
--
--* **Collaboratory Lab** for running Notebooks.
--* **Buckets** for storing large datasets.
--
------
--
--=== **Why This Matters** ===
--
--* The annotation system ensures that AI-generated insights are structured, interpretable, and clinically meaningful.
--* It enables real-time tracking of disease progression across the three diagnostic axes.
--* It facilitates integration with electronic health records and decision-support tools, improving AI adoption in clinical workflows.
++* **Programming Languages**: Python for AI and data processing.
++* **Frameworks**:
++** TensorFlow and PyTorch for machine learning.
++** Flask or FastAPI for backend services.
++* **Visualization**: Plotly and Matplotlib for interactive and static visualizations.
++* **EBRAINS Services**:
++** Collaboratory Lab for running Notebooks.
++** Buckets for storing large datasets.