Wiki source code of Neurodiagnoses

Version 42.1 by manuelmenendez on 2025/02/02 20:53

version	line-number	content
1.1	1	(% class="jumbotron" %)
	2	(((
	3	(% class="container" %)
	4	(((
40.1	5	= //A new tridimensional diagnostic framework for complex CNS diseases// =
1.1	6
40.1	7	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.
6.1	8	We aim to create a structured, interpretable, and scalable diagnostic tool.
1.1	9	)))
	10	)))
	11
	12	(% class="row" %)
	13	(((
	14	(% class="col-xs-12 col-sm-8" %)
	15	(((
6.1	16	= What is this about and what can I find here? =
1.1	17
27.1	18	= Overview =
6.1	19
28.1	20
40.1	21	The classification and diagnosis of central nervous system (CNS) diseases have long been constrained by traditional phenotype-based approaches, which often fail to capture the complex pathophysiological mechanisms, molecular biomarkers, and neuroanatomical changes that drive disease progression.
29.1	22
40.1	23	Neurodiagnoses is an open-source AI-powered diagnostic system designed for complex CNS disorders, including neurodegenerative diseases, autoimmune encephalopathies, prion disorders, and genetic syndromes. The project aims to develop a tridimensional diagnostic framework with an AI-powered annotation system, integrating etiology, molecular biomarkers, and neuroanatomoclinical correlations for precise, standardized, and scalable CNS disease diagnostics.
33.1	24
23.1	25	The //Tridimensional Diagnostic Framework// redefines CNS diseases can be classified and diagnosed by focusing on:
6.1	26
16.1	27	* Axis 1: Etiology (genetic or other causes of diseases).
	28	* Axis 2: Molecular Markers (biomarkers).
6.1	29	* Axis 3: Neuroanatomoclinical correlations (linking clinical symptoms to structural changes in the nervous system).
	30
	31	This methodology enables:
	32
	33	* Greater precision in diagnosis.
	34	* Integration of incomplete datasets using AI-driven probabilistic modeling.
	35	* Stratification of patients for personalized treatment.
	36
41.1	37	== The role of AI-powered annotation ==
33.1	38
36.1	39	To enhance standardization, interpretability, and clinical application, the framework integrates an AI-powered annotation system, which:
33.1	40
36.1	41	* Assigns structured metadata tags to diagnostic features.
	42	* Provides real-time contextual explanations for AI-based classifications.
	43	* Tracks longitudinal disease progression using timestamped AI annotations.
	44	* Improves AI model transparency through interpretability tools (e.g., SHAP analysis).
	45	* Facilitates decision-making for clinicians by linking annotations to standardized biomedical ontologies (SNOMED, HPO).
33.1	46
37.1	47	Neurodiagnoses provides two complementary AI-driven diagnostic approaches:
	48
	49	1. Traditional Probabilistic Diagnosis
	50
	51	* AI provides multiple possible diagnoses, each assigned a probability percentage based on biomarker, imaging, and clinical data.
	52	* Example Output:
39.1	53	** 75% Alzheimer's Disease
	54	** 20% Lewy Body Dementia
	55	** 5% Vascular Dementia
37.1	56	* Useful for differential diagnosis and treatment decision-making.
	57
	58	2. Tridimensional Diagnosis
	59
	60	* Diagnoses are structured based on:
	61	(1) Etiology (genetic, autoimmune, metabolic, infectious)
	62	(2) Molecular Biomarkers (amyloid-beta, tau, inflammatory markers, EEG patterns)
	63	(3) Neuroanatomoclinical Correlations (brain atrophy, connectivity alterations)
39.1	64	* This approach enables precise disease subtyping and biologically meaningful classification, particularly useful to track progression over time.
37.1	65
	66	For every patient case, both systems will be offered, allowing clinicians to compare AI-generated probabilistic diagnosis with a structured tridimensional classification.
	67
	68
23.1	69	== The case of neurodegenerative diseases ==
6.1	70
23.1	71	There have been described these 3 diagnostic axes:
	72
25.1	73	[[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.>>image:tridimensional.png\|\|alt="tridimensional view of neurodegenerative diseases"]]
	74
6.1	75	* (((
	76	Axis 1: Etiology
	77
	78	* //Description//: Focuses on genetic and sporadic causes, identifying risk factors and potential triggers.
	79	* //Examples//: APOE ε4 as a genetic risk factor, or cardiovascular health affecting NDD progression.
23.1	80	* //Tests//: Genetic testing, lifestyle, and cardiovascular screening.
36.1	81
	82
6.1	83	)))
	84	* (((
	85	Axis 2: Molecular Markers
	86
	87	* //Description//: Analyzes primary (amyloid-beta, tau) and secondary biomarkers (NFL, GFAP) for tracking disease progression.
	88	* //Examples//: CSF amyloid-beta concentrations to confirm Alzheimer’s pathology.
	89	* //Tests//: Blood/CSF biomarkers, PET imaging (Tau-PET, Amyloid-PET).
36.1	90
	91
6.1	92	)))
	93	* (((
	94	Axis 3: Neuroanatomoclinical
	95
	96	* //Description//: Links clinical symptoms to neuroanatomical changes, such as atrophy or functional impairments.
	97	* //Examples//: Hippocampal atrophy correlating with memory deficits.
	98	* //Tests//: MRI volumetrics, FDG-PET, neuropsychological evaluations.
	99	)))
	100
9.1	101	== Applications ==
6.1	102
	103	This system enhances:
	104
7.2	105	* Research: By stratifying patients, reduces cohort heterogeneity in clinical trials.
6.1	106	* Clinical Practice: Provides dynamic diagnostic annotations with timestamps for longitudinal tracking.
	107
10.1	108	== How to Contribute ==
4.4	109
	110	* Access the `/docs` folder for guidelines.
	111	* Use `/code` for the latest AI pipelines.
	112	* Share feedback and ideas in the wiki discussion pages.
5.1	113
10.1	114	== Key Objectives ==
5.1	115
	116	* Develop interpretable AI models for diagnosis and progression tracking.
	117	* Integrate data from Human Phenotype Ontology (HPO), Gene Ontology (GO), and other biomedical resources.
	118	* Foster collaboration among neuroscientists, AI researchers, and clinicians.
42.1	119	* Provide a dual diagnostic system:
	120	** Probabilistic Diagnosis – AI assigns multiple traditional possible diagnoses with probability percentages.
	121	** Tridimensional Diagnosis – AI structures diagnoses based on etiology, biomarkers, and neuroanatomical correlations.
31.1	122
	123	== Who has access? ==
	124
	125	We welcome contributions from the global community. Let’s build the future of neurological diagnostics together!
1.1	126	)))
	127
	128
26.1	129
	130
27.1	131
32.1	132
1.1	133	(% class="col-xs-12 col-sm-4" %)
	134	(((
	135	{{box title="Contents"}}
	136	{{toc/}}
	137	{{/box}}
	138
10.1	139	== Main contents ==
4.4	140
5.1	141	* `/docs`: Documentation and contribution guidelines.
	142	* `/code`: Machine learning pipelines and scripts.
	143	* `/data`: Sample datasets for testing.
	144	* `/outputs`: Generated models, visualizations, and reports.
21.1	145	* [[Methodology>>url:https://wiki.ebrains.eu/bin/view/Collabs/neurodiagnoses/Methodology/]]
35.1	146	* [[Notebooks>>Notebooks]]
21.1	147	* [[Results>>url:https://wiki.ebrains.eu/bin/view/Collabs/neurodiagnoses/Results/]]
22.1	148	* [[to-do-list>>to-do-list]]
1.1	149	)))
	150	)))