Detecting Children with Autism Spectrum Disorder based on Script-Centric Behavior Understanding with Emotional Enhancement

TL;DR

This paper introduces a zero-shot ASD detection framework using script-centric behavioral understanding with emotional cues, leveraging large language models to improve diagnosis accuracy and interpretability in young children.

Contribution

It presents a novel multimodal pipeline that converts audio-visual data into structured scripts and employs prompt engineering with LLMs for ASD detection without extensive training data.

Findings

Achieved 95.24% F1-score in ASD diagnosis

Generated interpretable detection rationales

Demonstrated effectiveness in children around two years old

Abstract

The early diagnosis of autism spectrum disorder (ASD) is critically dependent on systematic observation and analysis of children's social behaviors. While current methodologies predominantly utilize supervised learning approaches, their clinical adoption faces two principal limitations: insufficient ASD diagnostic samples and inadequate interpretability of the detection outcomes. This paper presents a novel zero-shot ASD detection framework based on script-centric behavioral understanding with emotional enhancement, which is designed to overcome the aforementioned clinical constraints. The proposed pipeline automatically converts audio-visual data into structured behavioral text scripts through computer vision techniques, subsequently capitalizing on the generalization capabilities of large language models (LLMs) for zero-shot/few-shot ASD detection. Three core technical contributions are introduced: (1) A multimodal script transcription module transforming behavioral cues into structured textual representations. (2) An emotion textualization module encoding emotional dynamics as the contextual features to augment behavioral understanding. (3) A domain-specific prompt engineering strategy enables the injection of clinical knowledge into LLMs. Our method achieves an F1-score of 95.24\% in diagnosing ASD in children with an average age of two years while generating interpretable detection rationales. This work opens up new avenues for leveraging the power of LLMs in analyzing and understanding ASD-related human behavior, thereby enhancing the accuracy of assisted autism diagnosis.