Comprehensive Analysis of Machine Learning and Deep Learning Approaches for Autism Spectrum Disorder Detection
Bibliographic record
Abstract
In the modern era, Autism Spectrum Disorder (ASD) is recognised as a complex neurodevelopmental disorder characterised by deficits in social communication and the engagement in repetitive behaviours. Specifically, early and reliable diagnosis is crucial for facilitating timely intervention. However, traditional diagnostic services practised in clinical settings are subjective, slow, and inconsistent. Recent developments in AI, specifically Machine Learning (ML) and Deep Learning (DL) approaches, have demonstrated great promise in overcoming these challenges by utilising a range of multimodal data sources such as Electroencephalography (EEG), facial image analysis, structural Magnetic Resonance Imaging (sMRI) and resting-state functional MRI (rs-fMRI). Furthermore, this survey provides a review of recent studies that use these types of datasets, synthesising studies with respect to methodology, strengths and weaknesses, and performance indicators. Moreover, direct comparisons indicate that DLbased frameworks attain superior classification performance, mainly when employing vision transformers and graph-based transformer architectures. In contrast, traditional ML models illustrate better computational and interpretability efficiency. Furthermore, multimodal fusion techniques that combine DL and ML show robust evidence of increased robustness and generalizability. However, challenges related to data heterogeneity, class imbalance, and scalability for real-world clinical deployment remain unsolved. Therefore, this comprehensive analysis highlights the quick need for explainable, inclusive, and clinically validated frameworks that effectively support ASD detection and enable real-time clinical use.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.006 | 0.013 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".