Summary

• Page properties (1 modified, 0 added, 0 removed)
• Attachments (0 modified, 1 added, 0 removed)
  • workflow neurodiagnoses.png

Details

Page properties

Content

...	...	@@ -1,106 +1,106 @@
1		-=== **Overview** ===
	1	+**Neurodiagnoses AI** is an open-source, AI-driven framework designed to enhance the diagnosis and prognosis of central nervous system (CNS) disorders. Building upon the Florey Dementia Index (FDI) methodology, it now encompasses a broader spectrum of neurological conditions. The system integrates multimodal data sources—including EEG, neuroimaging, biomarkers, and genetics—and employs machine learning models to deliver explainable, real-time diagnostic insights. A key feature of this framework is the incorporation of the **Generalized Neuro Biomarker Ontology Categorization (Neuromarker)**, which standardizes biomarker classification across all neurodegenerative diseases, facilitating cross-disease AI training.
2	2
3		-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.
	3	+**Neuromarker: Generalized Biomarker Ontology**
4	4
5		-----
	5	+Neuromarker extends the Common Alzheimer’s Disease Research Ontology (CADRO) into a comprehensive biomarker categorization framework applicable to all neurodegenerative diseases (NDDs). This ontology enables standardized classification, AI-based feature extraction, and seamless multimodal data integration.
6	6
7		-=== **1. Data Integration** ===
	7	+**Core Biomarker Categories**
8	8
9		-==== **Data Sources** ====
	9	+Within the Neurodiagnoses AI framework, biomarkers are categorized as follows:
10	10
11		-* **Biomedical Ontologies**:
12		-** Human Phenotype Ontology (HPO) for phenotypic abnormalities.
13		-** Gene Ontology (GO) for molecular and cellular processes.
14		-* **Neuroimaging Datasets**:
15		-** Example: Alzheimer’s Disease Neuroimaging Initiative (ADNI), OpenNeuro.
16		-* **Clinical and Biomarker Data**:
17		-** Anonymized clinical reports, molecular biomarkers, and test results.
	11	+|=**Category**|=**Description**
	12	+|**Molecular Biomarkers**|Omics-based markers (genomic, transcriptomic, proteomic, metabolomic, lipidomic)
	13	+|**Neuroimaging Biomarkers**|Structural (MRI, CT), Functional (fMRI, PET), Molecular Imaging (tau, amyloid, α-synuclein)
	14	+|**Fluid Biomarkers**|CSF, plasma, blood-based markers for tau, amyloid, α-synuclein, TDP-43, GFAP, NfL, autoantiboides
	15	+|**Neurophysiological Biomarkers**|EEG, MEG, evoked potentials (ERP), sleep-related markers
	16	+|**Digital Biomarkers**|Gait analysis, cognitive/speech biomarkers, wearables data, EHR-based markers
	17	+|**Clinical Phenotypic Markers**|Standardized clinical scores (MMSE, MoCA, CDR, UPDRS, ALSFRS, UHDRS)
	18	+|**Genetic Biomarkers**|Risk alleles (APOE, LRRK2, MAPT, C9orf72, PRNP) and polygenic risk scores
	19	+|**Environmental & Lifestyle Factors**|Toxins, infections, diet, microbiome, comorbidities
18	18
19		-==== **Data Preprocessing** ====
	21	+**Integrating External Databases into Neurodiagnoses**
20	20
21		-1. **Standardization**: Ensure all data sources are normalized to a common format.
22		-1. **Feature Selection**: Identify relevant features for diagnosis (e.g., biomarkers, imaging scores).
23		-1. **Data Cleaning**: Handle missing values and remove duplicates.
	23	+To enhance diagnostic precision, Neurodiagnoses AI incorporates data from multiple biomedical and neurological research databases. Researchers can integrate external datasets by following these steps:
24	24
25		-----
	25	+1. (((
	26	+**Register for Access**
26	26
27		-=== **2. AI-Based Analysis** ===
	28	+* Each external database requires individual registration and access approval.
	29	+* Ensure compliance with ethical approvals and data usage agreements before integrating datasets into Neurodiagnoses.
	30	+* Some repositories may require a Data Usage Agreement (DUA) for sensitive medical data.
	31	+)))
	32	+1. (((
	33	+**Download & Prepare Data**
28	28
29		-==== **Model Development** ====
	35	+* Download datasets while adhering to database usage policies.
	36	+* (((
	37	+Ensure files meet Neurodiagnoses format requirements:
30	30
31		-* **Embedding Models**: Use pre-trained models like BioBERT or BioLORD for text data.
32		-* **Classification Models**:
33		-** Algorithms: Random Forest, Support Vector Machines (SVM), or neural networks.
34		-** Purpose: Predict the likelihood of specific neurological conditions based on input data.
	39	+|=**Data Type**|=**Accepted Formats**
	40	+|**Tabular Data**|.csv, .tsv
	41	+|**Neuroimaging**|.nii, .dcm
	42	+|**Genomic Data**|.fasta, .vcf
	43	+|**Clinical Metadata**|.json, .xml
	44	+)))
	45	+* (((
	46	+**Mandatory Fields for Integration**:
35	35
36		-==== **Dimensionality Reduction and Interpretability** ====
	48	+* Subject ID: Unique patient identifier
	49	+* Diagnosis: Standardized disease classification
	50	+* Biomarkers: CSF, plasma, or imaging biomarkers
	51	+* Genetic Data: Whole-genome or exome sequencing
	52	+* Neuroimaging Metadata: MRI/PET acquisition parameters
	53	+)))
	54	+)))
	55	+1. (((
	56	+**Upload Data to Neurodiagnoses**
37	37
38		-* Leverage [[DEIBO>>https://drive.ebrains.eu/f/8d7157708cde4b258db0/]] (Data-driven Embedding Interpretation Based on Ontologies) to connect model dimensions to ontology concepts.
39		-* Evaluate interpretability using metrics like the Area Under the Interpretability Curve (AUIC).
	58	+* (((
	59	+**Option 1: Upload to EBRAINS Bucket**
40	40
41		-----
	61	+* Location: EBRAINS Neurodiagnoses Bucket
	62	+* Ensure correct metadata tagging before submission.
	63	+)))
	64	+* (((
	65	+**Option 2: Contribute via GitHub Repository**
42	42
43		-=== **3. Diagnostic Framework** ===
	67	+* Location: GitHub Data Repository
	68	+* Create a new folder under /data/ and include a dataset description.
	69	+* For large datasets, contact project administrators before uploading.
	70	+)))
	71	+)))
	72	+1. (((
	73	+**Integrate Data into AI Models**
44	44
45		-==== **Axes of Diagnosis** ====
	75	+* Open Jupyter Notebooks on EBRAINS to run preprocessing scripts.
	76	+* Standardize neuroimaging and biomarker formats using harmonization tools.
	77	+* Utilize machine learning models to handle missing data and feature extraction.
	78	+* Train AI models with newly integrated patient cohorts.
46	46
47		-The framework organizes diagnostic data into three axes:
	80	+**Reference**: See docs/data_processing.md for detailed instructions.
	81	+)))
48	48
49		-1. **Etiology**: Genetic and environmental risk factors.
50		-1. **Molecular Markers**: Biomarkers such as amyloid-beta, tau, and alpha-synuclein.
51		-1. **Neuroanatomical Correlations**: Results from neuroimaging (e.g., MRI, PET).
	83	+**AI-Driven Biomarker Categorization**
52	52
53		-==== **Recommendation System** ====
	85	+Neurodiagnoses employs advanced AI models for biomarker classification:
54	54
55		-* Suggests additional tests or biomarkers if gaps are detected in the data.
56		-* Prioritizes tests based on clinical impact and cost-effectiveness.
	87	+|=**Model Type**|=**Application**
	88	+|**Graph Neural Networks (GNNs)**|Identify shared biomarker pathways across diseases
	89	+|**Contrastive Learning**|Distinguish overlapping vs. unique biomarkers
	90	+|**Multimodal Transformer Models**|Integrate imaging, omics, and clinical data
57	57
58		-----
	92	+**Collaboration & Partnerships**
59	59
60		-=== **4. Computational Workflow** ===
	94	+Neurodiagnoses actively seeks partnerships with data providers to:
61	61
62		-1. **Data Loading**: Import data from storage (Drive or Bucket).
63		-1. **Feature Engineering**: Generate derived features from the raw data.
64		-1. **Model Training**:
65		-1*. Split data into training, validation, and test sets.
66		-1*. Train models with cross-validation to ensure robustness.
67		-1. **Evaluation**:
68		-1*. Metrics: Accuracy, F1-Score, AUIC for interpretability.
69		-1*. Compare against baseline models and domain benchmarks.
	96	+* Enable API-based data integration for real-time processing.
	97	+* Co-develop harmonized AI-ready datasets with standardized annotations.
	98	+* Secure funding opportunities through joint grant applications.
70	70
71		-----
	100	+**Interested in Partnering?**
72	72
73		-=== **5. Validation** ===
	102	+If you represent a research consortium or database provider, reach out to explore data-sharing agreements.
74	74
75		-==== **Internal Validation** ====
	104	+**Contact**: [[info@neurodiagnoses.com>>mailto:info@neurodiagnoses.com]]
76	76
77		-* Test the system using simulated datasets and known clinical cases.
78		-* Fine-tune models based on validation results.
79		-
80		-==== **External Validation** ====
81		-
82		-* Collaborate with research institutions and hospitals to test the system in real-world settings.
83		-* Use anonymized patient data to ensure privacy compliance.
84		-
85		-----
86		-
87		-=== **6. Collaborative Development** ===
88		-
89		-The project is open to contributions from researchers, clinicians, and developers. Key tools include:
90		-
91		-* **Jupyter Notebooks**: For data analysis and pipeline development.
92		-* **Wiki Pages**: For documenting methods and results.
93		-* **Drive and Bucket**: For sharing code, data, and outputs.
94		-
95		-----
96		-
97		-=== **7. Tools and Technologies** ===
98		-
99		-* **Programming Languages**: Python for AI and data processing.
100		-* **Frameworks**:
101		-** TensorFlow and PyTorch for machine learning.
102		-** Flask or FastAPI for backend services.
103		-* **Visualization**: Plotly and Matplotlib for interactive and static visualizations.
104		-* **EBRAINS Services**:
105		-** Collaboratory Lab for running Notebooks.
106		-** Buckets for storing large datasets.
	106	+

workflow neurodiagnoses.png

Author

...	...	@@ -1,0 +1,1 @@
	1	+XWiki.manuelmenendez

Size

...	...	@@ -1,0 +1,1 @@
	1	+157.5 KB

Content