Warning:  Due to planned infrastructure maintenance, the EBRAINS Wiki and EBRAINS Support system will be unavailable for up to three days starting Monday, 14 July. During this period, both services will be inaccessible, and any emails sent to the support address will not be received.

Attention: We are currently experiencing some issues with the EBRAINS Drive. Please bear with us as we fix this issue. We apologise for any inconvenience caused.


Changes for page Methodology

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

From version 18.1
edited by manuelmenendez
on 2025/02/13 12:52
Change comment: There is no comment for this version
To version 6.1
edited by manuelmenendez
on 2025/02/01 11:57
Change comment: There is no comment for this version

Summary

Details

Page properties
Content
... ... @@ -1,133 +1,173 @@
1 -== **Overview** ==
1 +==== **Overview** ====
2 2  
3 -Neurodiagnoses 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.
3 +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**.
4 4  
5 5  ----
6 6  
7 -== **How to Use External Databases in Neurodiagnoses** ==
7 +=== **1. Data Integration** ===
8 8  
9 -To enhance the accuracy of our diagnostic models, Neurodiagnoses integrates data from multiple biomedical and neurological research databases. If you are a researcher, follow these steps to access, prepare, and integrate data into the Neurodiagnoses framework.
9 +==== **Data Sources** ====
10 10  
11 -=== **Potential Data Sources** ===
11 +**Biomedical Ontologies & Databases:**
12 12  
13 -Neurodiagnoses maintains an updated list of potential biomedical databases relevant to neurodegenerative diseases.
13 +* **Human Phenotype Ontology (HPO)** for symptom annotation.
14 +* **Gene Ontology (GO)** for molecular and cellular processes.
14 14  
15 -* Reference: [[List of Potential Databases>>url:https://github.com/Fundacion-de-Neurociencias/neurodiagnoses/blob/main/data/sources/list_of_potential_databases]]
16 +**Dimensionality Reduction and Interpretability:**
16 16  
17 -=== **1. Register for Access** ===
18 +* **Evaluate interpretability** using metrics like the **Area Under the Interpretability Curve (AUIC)**.
19 +* **Leverage DEIBO (Data-driven Embedding Interpretation Based on Ontologies)** to connect model dimensions to ontology concepts.
18 18  
19 -Each external database requires individual registration and access approval. Follow the official guidelines of each database provider.
21 +**Neuroimaging & EEG/MEG Data:**
20 20  
21 -* Ensure that you have completed all ethical approvals and data access agreements before integrating datasets into Neurodiagnoses.
22 -* Some repositories require a Data Usage Agreement (DUA) before downloading sensitive medical data.
23 +* **MRI volumetric measures** for brain atrophy tracking.
24 +* **EEG functional connectivity patterns** (AI-Mind).
23 23  
24 -=== **2. Download & Prepare Data** ===
26 +**Clinical & Biomarker Data:**
25 25  
26 -Once access is granted, download datasets while complying with data usage policies. Ensure that the files meet Neurodiagnoses’ format requirements for smooth integration.
28 +* **CSF biomarkers** (Amyloid-beta, Tau, Neurofilament Light).
29 +* **Sleep monitoring and actigraphy data** (ADIS).
27 27  
28 -==== **Supported File Formats** ====
31 +**Federated Learning Integration:**
29 29  
30 -* Tabular Data: .csv, .tsv
31 -* Neuroimaging Data: .nii, .dcm
32 -* Genomic Data: .fasta, .vcf
33 -* Clinical Metadata: .json, .xml
33 +* **Secure multi-center data harmonization** (PROMINENT).
34 34  
35 -==== **Mandatory Fields for Integration** ====
35 +----
36 36  
37 -|=Field Name|=Description
38 -|Subject ID|Unique patient identifier
39 -|Diagnosis|Standardized disease classification
40 -|Biomarkers|CSF, plasma, or imaging biomarkers
41 -|Genetic Data|Whole-genome or exome sequencing
42 -|Neuroimaging Metadata|MRI/PET acquisition parameters
37 +==== **Annotation System for Multi-Modal Data** ====
43 43  
44 -=== **3. Upload Data to Neurodiagnoses** ===
39 +To ensure **structured integration of diverse datasets**, **Neurodiagnoses** will implement an **AI-driven annotation system**, which will:
45 45  
46 -Once preprocessed, data can be uploaded to EBRAINS or GitHub.
41 +* **Assign standardized metadata tags** to diagnostic features.
42 +* **Provide contextual explanations** for AI-based classifications.
43 +* **Track temporal disease progression annotations** to identify long-term trends.
47 47  
48 -* (((
49 -**Option 1: Upload to EBRAINS Bucket**
45 +----
50 50  
51 -* Location: [[EBRAINS Neurodiagnoses Bucket>>url:https://wiki.ebrains.eu/bin/view/Collabs/neurodiagnoses/Bucket]]
52 -* Ensure correct metadata tagging before submission.
53 -)))
54 -* (((
55 -**Option 2: Contribute via GitHub Repository**
47 +=== **2. AI-Based Analysis** ===
56 56  
57 -* Location: [[GitHub Data Repository>>url:https://github.com/Fundacion-de-Neurociencias/neurodiagnoses/tree/main/data]]
58 -* Create a new folder under /data/ and include dataset description.
59 -)))
49 +==== **Machine Learning & Deep Learning Models** ====
60 60  
61 -//Note: For large datasets, please contact the project administrators before uploading.//
51 +**Risk Prediction Models:**
62 62  
63 -=== **4. Integrate Data into AI Models** ===
53 +* **LETHE’s cognitive risk prediction model** integrated into the annotation framework.
64 64  
65 -Once uploaded, datasets must be harmonized and formatted before AI model training.
55 +**Biomarker Classification & Probabilistic Imputation:**
66 66  
67 -==== **Steps for Data Integration** ====
57 +* **KNN Imputer** and **Bayesian models** used for handling **missing biomarker data**.
68 68  
69 -* Open Jupyter Notebooks on EBRAINS to run preprocessing scripts.
70 -* Standardize neuroimaging and biomarker formats using harmonization tools.
71 -* Use machine learning models to handle missing data and feature extraction.
72 -* Train AI models with newly integrated patient cohorts.
73 -* Reference: [[Detailed instructions can be found in docs/data_processing.md>>url:https://github.com/Fundacion-de-Neurociencias/neurodiagnoses/blob/main/docs/data_processing.md]].
59 +**Neuroimaging Feature Extraction:**
74 74  
61 +* **MRI & EEG data** annotated with **neuroanatomical feature labels**.
62 +
63 +==== **AI-Powered Annotation System** ====
64 +
65 +* Uses **SHAP-based interpretability tools** to explain model decisions.
66 +* Generates **automated clinical annotations** in structured reports.
67 +* Links findings to **standardized medical ontologies** (e.g., **SNOMED, HPO**).
68 +
75 75  ----
76 76  
77 -== **Database Sources Table** ==
71 +=== **3. Diagnostic Framework & Clinical Decision Support** ===
78 78  
79 -=== **Where to Insert This** ===
73 +==== **Tridimensional Diagnostic Axes** ====
80 80  
81 -* GitHub: [[docs/data_sources.md>>url:https://github.com/Fundacion-de-Neurociencias/neurodiagnoses/blob/main/docs/data_sources.md]]
82 -* EBRAINS Wiki: Collabs/neurodiagnoses/Data Sources
75 +**Axis 1: Etiology (Pathogenic Mechanisms)**
83 83  
84 -=== **Key Databases for Neurodiagnoses** ===
77 +* Classification based on **genetic markers, cellular pathways, and environmental risk factors**.
78 +* **AI-assisted annotation** provides **causal interpretations** for clinical use.
85 85  
86 -|=Database|=Focus Area|=Data Type|=Access Link
87 -|ADNI|Alzheimer's Disease|MRI, PET, CSF, cognitive tests|ADNI
88 -|PPMI|Parkinson’s Disease|Imaging, biospecimens|[[PPMI>>url:https://www.ppmi-info.org/]]
89 -|GP2|Genetic Data for PD|Whole-genome sequencing|[[GP2>>url:https://gp2.org/]]
90 -|Enroll-HD|Huntington’s Disease|Clinical, genetic, imaging|[[Enroll-HD>>url:https://enroll-hd.org/]]
91 -|GAAIN|Alzheimer's & Cognitive Decline|Multi-source data aggregation|[[GAAIN>>url:https://www.gaain.org/]]
92 -|UK Biobank|Population-wide studies|Genetic, imaging, health records|[[UK Biobank>>url:https://www.ukbiobank.ac.uk/]]
93 -|DPUK|Dementia & Aging|Imaging, genetics, lifestyle factors|[[DPUK>>url:https://www.dementiasplatform.uk/]]
94 -|PRION Registry|Prion Diseases|Clinical and genetic data|[[PRION Registry>>url:https://www.prionalliance.org/]]
95 -|DECIPHER|Rare Genetic Disorders|Genomic variants|DECIPHER
80 +**Axis 2: Molecular Markers & Biomarkers**
96 96  
97 -If you know a relevant dataset, submit a proposal in [[GitHub Issues>>url:https://github.com/Fundacion-de-Neurociencias/neurodiagnoses/issues]].
82 +* **Integration of CSF, blood, and neuroimaging biomarkers**.
83 +* **Structured annotation** highlights **biological pathways linked to diagnosis**.
98 98  
85 +**Axis 3: Neuroanatomoclinical Correlations**
86 +
87 +* **MRI and EEG data** provide anatomical and functional insights.
88 +* **AI-generated progression maps** annotate **brain structure-function relationships**.
89 +
99 99  ----
100 100  
101 -== **Collaboration & Partnerships** ==
92 +=== **4. Computational Workflow & Annotation Pipelines** ===
102 102  
103 -=== **Where to Insert This** ===
94 +==== **Data Processing Steps** ====
104 104  
105 -* GitHub: [[docs/collaboration.md>>url:https://github.com/Fundacion-de-Neurociencias/neurodiagnoses/blob/main/docs/collaboration.md]]
106 -* EBRAINS Wiki: Collabs/neurodiagnoses/Collaborations
96 +**Data Ingestion:**
107 107  
108 -=== **Partnering with Data Providers** ===
98 +* **Harmonized datasets** stored in **EBRAINS Bucket**.
99 +* **Preprocessing pipelines** clean and standardize data.
109 109  
110 -Beyond using existing datasets, Neurodiagnoses seeks partnerships with data repositories to:
101 +**Feature Engineering:**
111 111  
112 -* Enable direct API-based data integration for real-time processing.
113 -* Co-develop harmonized AI-ready datasets with standardized annotations.
114 -* Secure funding opportunities through joint grant applications.
103 +* **AI models** extract **clinically relevant patterns** from **EEG, MRI, and biomarkers**.
115 115  
116 -=== **Interested in Partnering?** ===
105 +**AI-Generated Annotations:**
117 117  
118 -If you represent a research consortium or database provider, reach out to explore data-sharing agreements.
107 +* **Automated tagging** of diagnostic features in **structured reports**.
108 +* **Explainability modules (SHAP, LIME)** ensure transparency in predictions.
119 119  
120 -* Contact: [[info@neurodiagnoses.com>>mailto:info@neurodiagnoses.com]]
110 +**Clinical Decision Support Integration:**
121 121  
112 +* **AI-annotated findings** fed into **interactive dashboards**.
113 +* **Clinicians can adjust, validate, and modify annotations**.
114 +
122 122  ----
123 123  
124 -== **Final Notes** ==
117 +=== **5. Validation & Real-World Testing** ===
125 125  
126 -Neurodiagnoses continuously expands its data ecosystem to support AI-driven clinical decision-making. Researchers and institutions are encouraged to contribute new datasets and methodologies.
119 +==== **Prospective Clinical Study** ====
127 127  
128 -For additional technical documentation:
121 +* **Multi-center validation** of AI-based **annotations & risk stratifications**.
122 +* **Benchmarking against clinician-based diagnoses**.
123 +* **Real-world testing** of AI-powered **structured reporting**.
129 129  
130 -* [[GitHub Repository>>url:https://github.com/Fundacion-de-Neurociencias/neurodiagnoses]]
131 -* [[EBRAINS Collaboration Page>>url:https://wiki.ebrains.eu/bin/view/Collabs/neurodiagnoses/]]
125 +==== **Quality Assurance & Explainability** ====
132 132  
133 -If you experience issues integrating data, open a [[GitHub Issue>>url:https://github.com/Fundacion-de-Neurociencias/neurodiagnoses/issues]] or consult the EBRAINS Neurodiagnoses Forum.
127 +* **Annotations linked to structured knowledge graphs** for improved transparency.
128 +* **Interactive annotation editor** allows clinicians to validate AI outputs.
129 +
130 +----
131 +
132 +=== **6. Collaborative Development** ===
133 +
134 +The project is **open to contributions** from **researchers, clinicians, and developers**.
135 +
136 +**Key tools include:**
137 +
138 +* **Jupyter Notebooks**: For data analysis and pipeline development.
139 +** Example: **probabilistic imputation**
140 +* **Wiki Pages**: For documenting methods and results.
141 +* **Drive and Bucket**: For sharing code, data, and outputs.
142 +* **Collaboration with related projects**:
143 +** Example: **Beyond the hype: AI in dementia – from early risk detection to disease treatment**
144 +
145 +----
146 +
147 +=== **7. Tools and Technologies** ===
148 +
149 +==== **Programming Languages:** ====
150 +
151 +* **Python** for AI and data processing.
152 +
153 +==== **Frameworks:** ====
154 +
155 +* **TensorFlow** and **PyTorch** for machine learning.
156 +* **Flask** or **FastAPI** for backend services.
157 +
158 +==== **Visualization:** ====
159 +
160 +* **Plotly** and **Matplotlib** for interactive and static visualizations.
161 +
162 +==== **EBRAINS Services:** ====
163 +
164 +* **Collaboratory Lab** for running Notebooks.
165 +* **Buckets** for storing large datasets.
166 +
167 +----
168 +
169 +=== **Why This Matters** ===
170 +
171 +* **The annotation system ensures that AI-generated insights are structured, interpretable, and clinically meaningful.**
172 +* **It enables real-time tracking of disease progression across the three diagnostic axes.**
173 +* **It facilitates integration with electronic health records and decision-support tools, improving AI adoption in clinical workflows.**