Diagnosis of autism spectrum disorder based on functional brain networks and machine learning

Abstract

Autism is a multifaceted neurodevelopmental condition whose accurate diagnosis may be challenging because the associated symptoms and severity vary considerably. The wrong diagnosis can affect families and the educational system, raising the risk of depression, eating disorders, and self-harm. Recently, many works have proposed new methods for the diagnosis of autism based on machine learning and brain data. However, these works focus on only one pairwise statistical metric, ignoring the brain network organization. In this paper, we propose a method for the automatic diagnosis of autism based on functional brain imaging data recorded from 500 subjects, where 242 present autism spectrum disorder considering the regions of interest throughout Bootstrap Analysis of Stable Cluster map. Our method can distinguish the control group from autism spectrum disorder patients with high accuracy. Indeed the best performance provides an AUC near 1.0, which is higher than that found in the literature. We verify that the left ventral posterior cingulate cortex region is less connected to an area in the cerebellum of patients with this neurodevelopment disorder, which agrees with previous studies. The functional brain networks of autism spectrum disorder patients show more segregation, less distribution of information across the network, and less connectivity compared to the control cases. Our workflow provides medical interpretability and can be used on other fMRI and EEG data, including small data sets.

Temporal Patterns of EEG Connectivity Unveil Parkinson's Disease Progression: Insights from Machine Learning Analysis

“…After preprocessing EEG data using effective techniques demonstrated in our previous endeavors 12 , we segmented it into 10-second windows and built connectivity matrices with Pearson Correlation (PC) 50 , Spearman Correlation (SC) 51 , Sparse Canonical Correlation Analysis (CCA) 52 , and Ledoit-Wolf shrinkage (LW) 53 . We emphasize coherence (Sync) 29,54 for its unique ability to measure synchronization in EEG signals, enhances the dataset analysis, providing a nuanced exploration of EEG signals that were previously unexplored in our prior work [12][13][14][15][16] .…”

“…The current work builds upon our previous research endeavors, which have established a foundation for employing machine learning techniques in the classification of PD and HC groups [12][13][14][15][16]65 . Initially, we utilize the support vector machine (SVM) to select connectivity metrics, leveraging its lower computational cost and effectiveness in binary classification 12 .…”

“…This tailored segmentation offers a more nuanced perspective on PD progression, aiming to capture potential variations in EEG signals corresponding to different duration and the stage of the disease trajectory. Building upon techniques demonstrated to be effective in preprocessing EEG time series data 12 , we employ various pairwise statistical metrics to construct connectivity matrices. Notably, we explore the efficacy of these metrics in binary classification tasks to discern PD patients from controls, alongside their utility in multiclass classification to differentiate between subgroups within the PD cohort based on disease duration.…”

“…Notably, we explore the efficacy of these metrics in binary classification tasks to discern PD patients from controls, alongside their utility in multiclass classification to differentiate between subgroups within the PD cohort based on disease duration. Furthermore, akin to our prior works [12][13][14][15][16] , we enhance the interpretability of our machine learning models using Shapley Additive Explanations (SHAP) values 17 . SHAP values provide valuable insights into the most influential features within our models, elucidating critical brain areas and connectivity patterns.…”

A face image classification method of autistic children based on the two-phase transfer learning

“…Machine learning algorithms belongs to the second group of methods. ASD can be diagnosed using machine learning by analyzing genes ( Gunning and Pavlidis, 2021 ; Lin et al, 2021 ), brain ( Yahata et al, 2016 ; Eslami et al, 2019 ; Payabvash et al, 2019 ; Conti et al, 2020 ; Jiao et al, 2020 ; Doi et al, 2021 ; ElNakieb et al, 2021 ; Garbulowski et al, 2021 ; Gui et al, 2021 ; Leming et al, 2021 ; Liu et al, 2021 ; Nunes et al, 2021 ; Shi et al, 2021 ; Takahashi et al, 2021 ; Ali et al, 2022 ; Alves et al, 2023 ; ElNakieb et al, 2023 ; Martinez and Chen, 2023 ), retina ( Lai et al, 2020 ), eye activity ( Vabalas et al, 2020 ; Cilia et al, 2021 ; Liu et al, 2021 ; Kanhirakadavath and Chandran, 2022 ), facial activity ( Carpenter et al, 2021 ), human behavior ( Tariq et al, 2018 ; Drimalla et al, 2020 ) or movement ( Alcañiz Raya et al, 2020 ). Quiet a few researchers have reviewed the application of machine learning in autism detection.…”