Summary

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

Details

Page properties

Content

...	...	@@ -17,10 +17,17 @@
17	17
18	18	= **Overview** =
19	19
20		-The classification and diagnosis of central nervous system (CNS) diseases have long been constrained by traditional phenotypic approaches that fail to capture the underlying pathophysiological mechanisms, molecular biomarkers, and neuroanatomical changes that drive disease progression. For instance, neurodegenerative and psychiatric disorders exhibit significant clinical overlap, co-pathology, and heterogeneity, a new diagnostic framework is urgently needed—one that shifts from symptom-based classifications toward an etiology-driven, tridimensional system integrating genetics, proteomics, neuroimaging, and computational modeling. By leveraging AI, multi-modal biomarkers, and precision medicine, this framework aims to provide a more objective, scalable, and biologically grounded approach to diagnosing and managing CNS diseases, ultimately leading to earlier detection, personalized interventions, and improved patient outcomes.
21	21
22		-The project aims to develop a tridimensional diagnostic framework with an AI-powered annotation system, integrating etiology, molecular biomarkers, and neuroanatomoclinical correlations for precise and scalable CNS disease diagnostics.
	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. Neurodegenerative and psychiatric disorders, for example, exhibit significant clinical overlap, co-pathology, and heterogeneity, making current diagnostic models insufficient.
23	23
	23	+This project proposes a new diagnostic framework—one that shifts from symptom-based classifications to an etiology-driven, tridimensional system. By integrating genetics, proteomics, neuroimaging, computational modeling, and AI-powered annotations, this approach aims to provide a more precise, scalable, and biologically grounded method for diagnosing and managing CNS diseases.
	24	+
	25	+The AI-powered annotation system plays a critical role by structuring, interpreting, and tracking multi-modal data, ensuring real-time disease progression analysis, clinician decision support, and personalized treatment pathways.
	26	+
	27	+=== **Project Aim** ===
	28	+
	29	+Neurodiagnoses is an open-source AI-powered diagnostic system designed for complex central nervous system (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.
	30	+
24	24	The //Tridimensional Diagnostic Framework// redefines CNS diseases can be classified and diagnosed by focusing on:
25	25
26	26	* **Axis 1**: Etiology (genetic or other causes of diseases).
...	...	@@ -33,6 +33,38 @@
33	33	* Integration of incomplete datasets using AI-driven probabilistic modeling.
34	34	* Stratification of patients for personalized treatment.
35	35
	43	+== **The Role of AI-Powered Annotation** ==
	44	+
	45	+To enhance standardization, interpretability, and clinical application, the framework integrates an AI-powered annotation system, which:
	46	+
	47	+* Assigns structured metadata tags to diagnostic features.
	48	+* Provides real-time contextual explanations for AI-based classifications.
	49	+* Tracks longitudinal disease progression using timestamped AI annotations.
	50	+* Improves AI model transparency through interpretability tools (e.g., SHAP analysis).
	51	+* Facilitates decision-making for clinicians by linking annotations to standardized biomedical ontologies (SNOMED, HPO).
	52	+
	53	+Neurodiagnoses provides two complementary AI-driven diagnostic approaches:
	54	+
	55	+1. Traditional Probabilistic Diagnosis
	56	+
	57	+* AI provides multiple possible diagnoses, each assigned a probability percentage based on biomarker, imaging, and clinical data.
	58	+* Example Output:
	59	+** 75% Alzheimer's Disease
	60	+** 20% Lewy Body Dementia
	61	+** 5% Vascular Dementia
	62	+* Useful for differential diagnosis and treatment decision-making.
	63	+
	64	+2. Tridimensional Diagnosis
	65	+
	66	+* Diagnoses are structured based on:
	67	+(1) Etiology (genetic, autoimmune, metabolic, infectious)
	68	+(2) Molecular Biomarkers (amyloid-beta, tau, inflammatory markers, EEG patterns)
	69	+(3) Neuroanatomoclinical Correlations (brain atrophy, connectivity alterations)
	70	+* This approach enables precise disease subtyping and biologically meaningful classification, particularly useful to track progression over time.
	71	+
	72	+For every patient case, both systems will be offered, allowing clinicians to compare AI-generated probabilistic diagnosis with a structured tridimensional classification.
	73	+
	74	+
36	36	== **The case of neurodegenerative diseases** ==
37	37
38	38	There have been described these 3 diagnostic axes:
...	...	@@ -45,6 +45,8 @@
45	45	* //Description//: Focuses on genetic and sporadic causes, identifying risk factors and potential triggers.
46	46	* //Examples//: APOE ε4 as a genetic risk factor, or cardiovascular health affecting NDD progression.
47	47	* //Tests//: Genetic testing, lifestyle, and cardiovascular screening.
	87	+
	88	+
48	48	)))
49	49	* (((
50	50	**Axis 2: Molecular Markers**
...	...	@@ -52,6 +52,8 @@
52	52	* //Description//: Analyzes primary (amyloid-beta, tau) and secondary biomarkers (NFL, GFAP) for tracking disease progression.
53	53	* //Examples//: CSF amyloid-beta concentrations to confirm Alzheimer’s pathology.
54	54	* //Tests//: Blood/CSF biomarkers, PET imaging (Tau-PET, Amyloid-PET).
	96	+
	97	+
55	55	)))
56	56	* (((
57	57	**Axis 3: Neuroanatomoclinical**
...	...	@@ -89,6 +89,7 @@
89	89
90	90
91	91
	135	+
92	92	(% class="col-xs-12 col-sm-4" %)
93	93	(((
94	94	{{box title="**Contents**"}}
...	...	@@ -102,6 +102,7 @@
102	102	* `/data`: Sample datasets for testing.
103	103	* `/outputs`: Generated models, visualizations, and reports.
104	104	* [[Methodology>>url:https://wiki.ebrains.eu/bin/view/Collabs/neurodiagnoses/Methodology/]]
	149	+* [[Notebooks>>Notebooks]]
105	105	* [[Results>>url:https://wiki.ebrains.eu/bin/view/Collabs/neurodiagnoses/Results/]]
106	106	* [[to-do-list>>to-do-list]]
107	107	)))