Machine learning applied to autism diagnosis using functional connectomes #3
Description
Title
Machine learning applied to autism diagnosis using functional connectomes
Leaders
Sebastián Mesch Henriques
Emilio Recart
Collaborators
No response
Brainhack School 2023 Hub
Humai
Project Description
Share a short background of your project.
Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder characterized by persistent deficits in social communication and interaction, as well as restricted and repetitive patterns of behavior, interests, or activities. Early and accurate diagnosis of ASD is crucial for timely intervention and support. However, diagnosing ASD can be challenging due to the complexity and heterogeneity of the disorder. Nowadays, the diagnosis of ASD relies on clinical observations.
In recent years, advancements in neuroimaging techniques, particularly functional magnetic resonance imaging (fMRI), have enabled researchers to investigate the neural mechanisms underlying ASD. Functional connectomes, which capture the functional interactions between different brain regions, have emerged as a valuable tool for understanding the brain connectivity patterns associated with ASD. Machine learning techniques, when applied to functional connectome data, have shown promise in assisting with the diagnosis of ASD.
Link to project repository/sources
https://github.com/SMESCH1/Autism-classification-BrainHack
https://docs.google.com/presentation/d/1iIUEaLJaD5_9o_OBXYWzyYXzSczaZi8M90g1ULHIzfg/edit?usp=sharing
Goals for the Project
To investigate the application of machine learning algorithms for ASD diagnosis
To evaluate the performance of machine learning models in classifying individuals with ASD and typically developing individuals based on functional connectome data.
To assess the potential of functional connectome-based machine learning models as a diagnostic tool for ASD
Deliverables
A Github repository with the script of the project
A jupyter notebook of the analysis codes and visualizations
Skills
- Python
- Bash
- Machine learning
- Deep learning
Data to use
We use data from the ABIDE I and ABIDE II datasets
Type
data_management, other
Development status
1_basic structure
Topic
connectome, data_visualisation, machine_learning, statistical_modelling
Tools
Jupyter, other
Programming language
Python, shell_scripting
Modalities
fMRI
Anything else?
No response