ASD-Bench: A Four-Axis Comprehensive Benchmark of AI Models for Autism Spectrum Disorder

• URL: http://arxiv.org/abs/2605.11091v1
• Date: Mon, 11 May 2026 18:01:21 GMT
• Title: ASD-Bench: A Four-Axis Comprehensive Benchmark of AI Models for Autism Spectrum Disorder
• Abstract summary: ASD-Bench is a systematic benchmark evaluating ML, deep learning, and foundation model configurations across three age cohorts.<n> applied to a curated v3 dataset of 4,068 AQ-10 records.<n>Adult classification yields high performance (10/17 models achieve perfect F1 and AUC), while adolescents present a harder task (F1 ceiling 0.837 vs. 0.915 for children)
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Automated ASD screening tools remain limited by single-architecture evaluations, axis-restricted assessment, and near-exclusive focus on adult cohorts, obscuring age-specific diagnostic patterns critical for early intervention. We introduce ASD-Bench, a systematic tabular benchmark evaluating ML, deep learning, and foundation model configurations across three age cohorts (children 1-11 yr, adolescents 12-16 yr, adults 17-64 yr) on four axes: predictive performance, calibration, interpretability, and adversarial robustness. Applied to a curated v3 dataset of 4,068 AQ-10 records, our benchmark spans classical models (XGBoost, AdaBoost, Random Forest, Logistic Regression), neural networks (MLP), deep tabular transformers (TabNet, TabTransformer, FT-Transformer), and TabPFN v2. We introduce the Heuristic Aggregate Penalty (HAP): a cost-sensitive metric penalising false negatives more heavily and incorporating cross-validation variance for deployment stability. Adult classification yields high performance (10/17 models achieve perfect F1 and AUC), while adolescents present a harder task (F1 ceiling 0.837 vs. 0.915 for children). Feature hierarchies shift across cohorts: A9 (social motivation) dominates for children, A5 (pattern recognition) leads for adolescents, and adults exhibit a flatter importance profile consistent with developmental social masking. Accuracy and calibration are dissociated: AdaBoost achieves F1=1.000 on adults with ECE=0.302, confirming single-metric evaluation is insufficient for clinical AI. Cohort-specific deployment recommendations are provided. All findings should be interpreted as proof-of-concept evidence on questionnaire-derived labels rather than clinically validated diagnostic performance.

Related papers

• A multimodal large language model for evidence-based autism spectrum disorder screening [43.813514045885704]
  ASDchat is a large language model designed for evidence-based autism screening.<n>The model was trained and evaluated on a dataset of 1,035 participants from 27 sites in China.
  arXiv  Detail & Related papers  (2026-09-15T00:34:21Z)
• TestifAI: Tomography-Based Testing for Deep Learning Systems [42.86570387250456]
  TestifAI is a framework for efficient and accurate estimation of robustness against combinations of perturbations.<n>It reconstructs model behaviour in a multi-perturbation space from tests that apply only a small number of perturbations.<n>It can predict higher-order (3 and 4 perturbations) test outcomes from low-order (1 and 2 perturbations) observations with an aggregate robustness estimation error of less than 7%.
  arXiv  Detail & Related papers  (2026-08-19T13:25:50Z)
• Automating Learner Assessment: Benchmarking Machine Learning and Deep Learning Models for EEG-Based Familiarity Prediction [0.0]
  This study benchmarks fifteen machine learning (ML) and deep learning (DL) models for EEG-based familiarity prediction.<n>We show that while standard stratified cross-validation yields artificially high classification performance (up to 0.9853 F1-score using CNN) due to temporal leakage across neighboring epochs, a rigorous trial-independent validation (Group K-Fold) drops the peak performance to 0.6038 F1-score (using CNN)<n>This highlights the critical necessity of trial-independent evaluation to avoid overestimating model generalizability.
  arXiv  Detail & Related papers  (2026-08-17T13:15:45Z)
• Simultaneous hyperkinetic movement disorders phenotyping: a cross-cohort pediatric transfer study using routine videos, markerless pose estimation and a tabular foundation model [0.0]
  The framework combines markerless pose estimation, kinematic descriptors, and a pretrained fondation model.<n>Results: After local calibration of the decision layer, performance improved consistently on the held-out pediatric patients.
  arXiv  Detail & Related papers  (2026-06-04T18:13:13Z)
• An Interpretable Vision Transformer as a Fingerprint-Based Diagnostic Aid for Kabuki and Wiedemann-Steiner Syndromes [1.9656376732415815]
  Kabuki syndrome (KS) and Wiedemann-Steiner syndrome (WSS) are rare but distinct developmental disorders.<n>Many individuals with KS or WSS remain undiagnosed due to barriers in access to both genetic testing and expertise.<n> Dermatoglyphic anomalies, despite being established hallmarks of several genetic syndromes, remain an underutilized diagnostic signal.
  arXiv  Detail & Related papers  (2026-02-06T00:41:15Z)
• Transparent Early ICU Mortality Prediction with Clinical Transformer and Per-Case Modality Attribution [42.85462513661566]
  We present a lightweight, transparent multimodal ensemble that fuses physiological time-series measurements with unstructured clinical notes from the first 48 hours of an ICU stay.<n>A logistic regression model combines predictions from two modality-specific models: a bidirectional LSTM for vitals and a finetuned ClinicalModernBERT transformer for notes.<n>On the MIMIC-III benchmark, our late-fusion ensemble improves discrimination over the best single model while maintaining well-calibrated predictions.
  arXiv  Detail & Related papers  (2025-11-19T20:11:49Z)
• Generating Natural-Language Surgical Feedback: From Structured Representation to Domain-Grounded Evaluation [66.7752700084159]
  High-quality feedback from a surgical trainer is pivotal for improving trainee performance and long-term skill acquisition.<n>We present a structure-aware pipeline that learns a surgical action ontology from real trainer-to-trainee transcripts.
  arXiv  Detail & Related papers  (2025-11-19T06:19:34Z)
• From Prototypes to Sparse ECG Explanations: SHAP-Driven Counterfactuals for Multivariate Time-Series Multi-class Classification [8.113866195465976]
  We propose a prototype-driven framework for generating sparse counterfactual explanations tailored to 12-lead ECG classification models.<n>Our method employs SHAP-based thresholds to identify critical signal segments and convert them into interval rules.<n>We evaluate three variants of our approach, Original, Sparse, and Aligned Sparse, with class-specific performance ranging from 98.9% validity for MI to challenges with hypertrophy (HYP) detection.
  arXiv  Detail & Related papers  (2025-10-22T12:09:50Z)
• Cross-dataset Multivariate Time-series Model for Parkinson's Diagnosis via Keyboard Dynamics [1.4895002251586484]
  Parkinson's disease (PD) presents a growing global challenge, affecting over 10 million individuals.<n>We propose a novel pipeline that leverages keystroke dynamics as a non-invasive and scalable biomarker for remote PD screening and telemonitoring.
  arXiv  Detail & Related papers  (2025-10-10T17:42:08Z)
• Honest and Reliable Evaluation and Expert Equivalence Testing of Automated Neonatal Seizure Detection [1.4624458429745086]
  Current practices often rely on inconsistent and biased metrics.<n>Expert-level claims about AI performance are frequently made without rigorous validation.<n>This study proposes best practices tailored to the specific challenges of neonatal seizure detection.
  arXiv  Detail & Related papers  (2025-08-06T21:55:28Z)
• VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks [49.0793012627959]
  We present VAPO, a novel framework tailored for reasoning models within the value-based paradigm.<n>VAPO attains a state-of-the-art score of $mathbf60.4$.<n>In direct comparison under identical experimental settings, VAPO outperforms the previously reported results of DeepSeek-R1-Zero-Qwen-32B and DAPO by more than 10 points.
  arXiv  Detail & Related papers  (2025-04-07T14:21:11Z)
• Machine Learning for ALSFRS-R Score Prediction: Making Sense of the Sensor Data [44.99833362998488]
  Amyotrophic Lateral Sclerosis (ALS) is a rapidly progressive neurodegenerative disease that presents individuals with limited treatment options. The present investigation, spearheaded by the iDPP@CLEF 2024 challenge, focuses on utilizing sensor-derived data obtained through an app.
  arXiv  Detail & Related papers  (2024-07-10T19:17:23Z)
• Deep Survival Analysis from Adult and Pediatric Electrocardiograms: A Multi-center Benchmark Study [5.554864650304149]
  Artificial intelligence applied to electrocardiography (AI-ECG) shows potential for mortality prediction.<n>We evaluated model design choices across three large cohorts: Beth Israel Deaconess (MIMIC-IV), Telehealth Network of Minas Gerais (Code-15), and Boston Children's Hospital (BCH)<n>We evaluated models predicting all-cause mortality, comparing horizon-based classification and deep survival methods with neural architectures including convolutional networks and transformers.
  arXiv  Detail & Related papers  (2024-06-24T14:37:17Z)
• Multilabel 12-Lead Electrocardiogram Classification Using Gradient Boosting Tree Ensemble [64.29529357862955]
  We build an algorithm using gradient boosted tree ensembles fitted on morphology and signal processing features to classify ECG diagnosis. For each lead, we derive features from heart rate variability, PQRST template shape, and the full signal waveform. We join the features of all 12 leads to fit an ensemble of gradient boosting decision trees to predict probabilities of ECG instances belonging to each class.
  arXiv  Detail & Related papers  (2020-10-21T18:11:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.