TL;DR
It is demonstrated that the accuracy of diagnosing autism can be improved by investigating the relationships between several behavioural traits using deep learning approach, and the graph-based machine learning models applied to behavioural reaction time features can provide clinically interpretable ASD classification.
The need to develop large, well‐balanced datasets, the application of explainable AI techniques, standardization and regulatory guidelines for facilitating the clinical translation of ASD detection systems are suggested.
Autism spectrum disorder (ASD) is characterized by diversity of behavioural abnormalities, and successful intervention depends on an early diagnosis. Conventional diagnostic techniques depend on interviews and observational evaluations, which can occasionally result in errors. In order to enhance the accuracy of ASD recognition, we propose an early ASD detection using Adaptive Fused Spatial–Temporal Graph Convolutional Network Optimized with Artificial Lemming Algorithm (AFSTGCN‐ALA). Initially, ASD‐related data are collected from ASD Dataset and Adaptive Fast Desensitized Kalman Filter (AFDKF) preprocessing; it effectively eliminates impulsive noise to enhance the accuracy of the data. The Multi‐Synchro Squeezing Transform (MSST) is then used to extract features from the preprocessed data, such as connections and frequency band coherence. To differentiate between instances with and without ASD, these extracted traits are then categorized using the AFSTGCN. However, adaptive optimization for parameter tweaking is absent from traditional AFSTGCN, which might affect the accuracy of detection. In order to solve this, the ALA was introduced, which optimizes the weight parameters of AFSTGCN to guarantee correct ASD categorization. The proposed AFSTGCN‐ALA model is evaluated using performance criteria such as compute time, F1‐score, accuracy and precision. According to experimental data, the suggested technique outperforms current approaches in terms of accuracy by 18.97%, 24.57% and 32.68% while cutting down on computing time by 19.84%, 24.93% and 31.62%. These results open the door to more accurate diagnosis and prompt therapies by demonstrating the effectiveness and dependability of AFSTGCN‐ALA for early ASD identification.
A novel approach for distinguishing individuals with Autism Spectrum Disorder (ASD) using Intuitionistic Fuzzy Set (IFS) theory and Multi-Scale Enhanced Graph Convolutional Networks (MSE-GCNs), which represents a substantial improvement over existing models for ASD and potentially for other neurological disorders.
This work proposes a cross-attention-guided subject-adaptive graph network (CAS-GNN) model that integrates structural MRI and resting-state functional connectivity data, effectively fusing complementary multimodal information and provides a promising tool for interpretable and robust ASD diagnosis, accelerating biomarker discovery and development.
Motivation Graph Neural Networks (GNNs) have gained increasing interest in the biomedical domain, as the integration of prior knowledge and deep neural networks has the potential to enhance insights into molecular processes and disease mechanisms. However, a comprehensive and systematic assessment of model architectures, data modalities, graph structures, and their performance for graph signal classification in the biomedical domain is yet to be performed. In order to close this gap, we conducted a benchmarking study on multiple GNNs on a Protein-Protein Interaction (PPI) network for Kidney Renal Clear Cell Carcinoma and Breast cancer subtype prediction, performing an in-depth investigation of architectures, incorporating skip connections and various data modalities. Results While none of the GNNs outperforms the structure-agnostic Multi-Layer Perceptron baseline, all of them can handle bimodal data (gene methylation and expression) and offer the ability to gain explainability based on PPIs. We offer practical guidelines for applying GNNs to graph signal processing tasks specifically for cancer classification. Depending on the underlying dataset and PPI structure employed, models on different data modalities outperform others. Overall, we suggest using ChebNet, which tends to outperform the Graph Convolutional Network and the Graph Attention Network in cancer subtype prediction. We recommend using GNN architectures that employ a simple flattening readout layer, as they provide better classification performance and faster training time than those with global average pooling. Additionally, we tested residual connections, but they had only an insignificant impact on classification performance. Availability and implementation Code and data available at https://github.com/HauschildLab/GNN4PPI. Contact julia.schirmacher@med.uni-goettingen.de, anne-christin.hauschild@uni-gießen.de Supplementary information Supplementary data attached.
Graph Neural Networks (GNN) facilitate effective prediction on graph data such as molecules, media networks and neural network blueprints. GNNs facilitate prediction through message passing techniques which define how information flows from a node to its neighbors. Due to the ubiquity of the graph data type, the development of newer and better GNNs has garnered much interest in the machine learning community. However, GNN evaluation and benchmarking is primarily driven by classification tasks. Thus, prospective GNN message passing layers are evaluated on their ability to outperform prior work in classification contexts. In contrast, GNNs are equally capable of performing scalar regression prediction, yet this class of problem is often overlooked when proposing new GNNs while the best classification GNNs are utilized in an a priori or off-the-shelf manner for regression problems. In response, this paper studies the efficacy of GNN layers in a slew of regression contexts from rank ordering, error minimization and insight extraction. Results show that deep convolutional GNNs, particularly GEN, are more effective at these tasks than attention-based GNNs, while other classical, theoretically-inspired GNNs remain competitive and efficient.