用家庭视频微调大模型，实现接近医生水平的自闭症行为评分。
Fine-tuning a multimodal large language model for clinician-grade autism behavioral scoring from short home videos
- 用低秩适配微调Gemini模型，仅训练30个已验证行为特征。
- 在99个孩子上，评分一致性提升40%，27/28特征表现改善。
- 零样本直接诊断准确率达77%，适合早期筛查场景。
自闭症谱系障碍（ASD）影响美国每31名儿童中就有一名，但平均确诊年龄超过四岁。利用易于获取的观察数据（如家庭视频）构建人工智能诊断流程，有助于实现早期发现与及时干预。本研究对Gemini 2.5 Pro模型进行微调，使用400段由临床医生评分的家庭视频，仅训练30个先前验证过的行为特征。在99个未参与训练的孩子（49例自闭症，50例非自闭症）上，与临床医生之间的评分一致性（按特征加权的加权科恩κ值）提升了40%（p<0.001），28个可评估特征中有27个表现改善。作为一项新兴的零样本能力，直接自闭症诊断的F1分数提高了53%（p<0.001），达到或超过临床医生水平。基于微调后大模型提取的行为特征构建的分类器辅助流程，在所有测试路径中均匹配临床评分输入，实现77%准确率（95%置信区间：68-85%），曲线下面积（AUC）为86%（95%置信区间：78-92%）。结果表明，微调后的多模态大模型可作为可扩展的行为特征提取器，用于自闭症评估与诊断。
原文摘要 · Abstract (English)
Autism spectrum disorder (ASD) affects 1 in 31 US children, yet median age at diagnosis exceeds four years. Artificial intelligence pipelines that provide quantified diagnosis using easy to access observational data (e.g., home videos) could help with earlier diagnosis, and timely delivery of early treatments. We fine-tuned Gemini 2.5 Pro on 400 clinician-rated home videos with low-rank adaptation, training only on 30 behavioral features previously validated to produce reliable predictions when passed to various ML models. On 99 held-out children (49 ASD, 50 neurotypical), inter-rater reliability with clinicians (per-feature weighted Cohen's kappa) improved by 40% (p<0.001), with 27 of 28 evaluable features improving. As an emergent zero-shot capability, direct ASD diagnosis F1 improved by 53% (p<0.001), matching or exceeding clinician outcomes. Classifier-assisted pipelines using fine-tuned LLM-derived behavioral features matched clinician-scored inputs across all tested pathways and achieved 77% accuracy (95% CI: 68-85%) and an AUC of 86% (95% CI: 78-92%). Fine-tuned multimodal LLMs can serve as scalable behavioral feature extractors for use in autism assessment and diagnosis.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。