.png){kind=icon}
.png){kind=icon}
Return
Modelling learning dynamics in autism therapy through explainable multimodal representation learning
.png){kind=icon}
OA
AI
P
M
S
DOI：10.3389/fnins.2026.1737098.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
BackgroundAutism Spectrum Disorder (ASD) presents with complex; temporally evolving motor and social behaviours that are difficult to quantify in ecologically valid clinical contexts. While recent computational methods offer diagnostic insights; many depend on fully supervised learning; high-resolution video; or artificial experimental constraints; limiting scalability; interpretability; and privacy compliance. Few approaches leverage unsupervised models to uncover dynamic behavioural structure from minimally invasive inputs.MethodsTo address these limitations; we propose a privacy-preserving; unsupervised representation learning framework that operates solely on skeletal pose and optical flow features. Using 255 multimodal windows from 15 therapy sessions in the MMASD corpus; a publicly available; privacy-safe dataset of child-clinician interactions; we train a denoising temporal autoencoder to derive compact latent embeddings of behaviour.ResultsThe model uncovers a low-dimensional behavioural manifold composed of six latent motor clusters. Transition graphs reveal structured topologies; including behavioural hubs and bottlenecks. Saliency analyses identify anatomically and socially relevant features; such as joint pairs (LWrist-LAnkle; Neck-Rear Head) and dynamic flow regions (e.g.; index pair 7; 14). Temporal saliency; based on reconstruction error; highlights spontaneous gesture onsets and socially salient events. KL divergence between early and late session phases quantified intra-session adaptation (range: 0.06–17.7) and showed a strong negative correlation with joint attention duration (r = −0.96; p = 0.002); suggesting links between behavioural dynamics and social engagement.DiscussionThese findings offer preliminary evidence that interpretable behavioural structure can be extracted from low-resolution; privacy-compliant inputs. While based on a limited sample; the framework illustrates potential for modeling learning dynamics; identifying salient motor patterns; and supporting objective progress tracking in ASD therapy. Future work will involve clinical validation and application to larger; longitudinal datasets to assess generalizability and therapeutic utility.
Keywords:
autism spectrum disorder
behavioural primitive
multimodal behaviour modeling
pose and optical flow
therapy session analysis
unsupervised representation learning
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3.2
Papers:
1.6W
Citations:
5.3W
Organization
Cited Papers