Early Brain Imaging can Predict Autism: Application of Machine Learning to a Clinical Imaging Archive
Bibliographic record
Abstract
Abstract A comprehensive investigation of early brain alterations in Autism Spectrum Disorder (ASD) is critical for understanding the neuroanatomical underpinnings of autism and its early diagnosis. Most previous brain imaging studies in ASD, however, are based on children older than 6 years – well after the average age of ASD diagnosis (~46 months). In this study, we use brain magnetic resonance images that were collected as part of clinical routine from patients who were later diagnosed with ASD. Using 15 ASD subjects of age three to four years and 18 age-matched non-ASD subjects as controls, we perform comprehensive comparison of different brain morphometric features and ASD vs. non-ASD classification by Random Forest machine learning method. We find that, although total intracranial volume (TIV) of ASD was 5.5 % larger than in non-ASD, brain volumes of many other brain areas (as a percentage of TIV) were smaller in ASD and can be partly attributed to larger (>10 %) ventricles in ASD. The larger TIV in ASD was correlated to larger surface area and increased amount of cortical folding but not to cortical thickness. The white matter regions in ASD had less image intensity (predominantly in the frontal and temporal regions) suggesting myelination deficit. We achieved 95 % area under the ROC curve (AUC) for ASD vs. non-ASD classification using all brain features. When classification was performed separately for each feature type, image intensity yielded the highest predictive power (95 % AUC), followed by cortical folding index (69 %), cortical and subcortical volume (69 %), and surface area (68 %). The most important feature for classification was white matter intensity surrounding the rostral middle frontal gyrus and was lower in ASD (d = 0.77, p = 0.04). The high degree of classification success indicates that the application of machine learning methods on brain features holds promise for earlier identification of ASD. To our knowledge this is the first study to leverage a clinical imaging archive to investigate early brain markers in ASD.
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 | 0.003 | 0.011 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.004 | 0.001 |
| 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 | 0.001 |
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".