近日，加拿大米拉-曲海人工智能研究所教授Danilo Bzdok及其课题组揭示了大型语言模型解构了诊断自闭症背后的临床直觉。相关论文发表在2025年3月26日出版的《细胞》杂志上。

研究组利用深度学习来解构和质疑专家临床医生从临床报告中获得的直觉逻辑，以告知他们对自闭症的理解。在对数亿个一般句子进行预训练之后，该研究团队对来自医疗保健专业人员的4000份自由格式的健康记录进行了大型语言模型（llm）的处理，以区分确诊的自闭症病例和疑似的自闭症病例。通过引入可解释性策略，他们扩展的语言模型架构可以确定驱动临床思维走向正确诊断的最重要的单句。他们的框架将DSM-5中最关键的自闭症标准标记为刻板的重复行为、特殊兴趣和基于感知的行为，这挑战了今天对社会相互作用缺陷的关注，建议对黄金标准工具中长期存在的诊断标准进行必要的修订。

据悉，用全基因组分析或脑部扫描来诊断自闭症的努力收效甚微。然而，医疗保健专业人员基于长期第一手经验的临床直觉，仍然是诊断自闭症的黄金标准。

附：英文原文

Title: Large language models deconstruct the clinical intuition behind diagnosing autism

Author: Jack Stanley, Emmett Rabot, Siva Reddy, Eugene Belilovsky, Laurent Mottron, Danilo Bzdok

Issue&Volume: 2025-03-26

Abstract: Efforts to use genome-wide assays or brain scans to diagnose autism have seen diminishing returns. Yet the clinical intuition of healthcare professionals, based on longstanding first-hand experience, remains the gold standard for diagnosis of autism. We leveraged deep learning to deconstruct and interrogate the logic of expert clinician intuition from clinical reports to inform our understanding of autism. After pre-training on hundreds of millions of general sentences, we finessed large language models (LLMs) on >4,000 free-form health records from healthcare professionals to distinguish confirmed versus suspected autism cases. By introducing an explainability strategy, our extended language model architecture could pin down the most salient single sentences in what drives clinical thinking toward correct diagnoses. Our framework flagged the most autism-critical DSM-5 criteria to be stereotyped repetitive behaviors, special interests, and perception-based behaviors, which challenges today’s focus on deficits in social interplay, suggesting necessary revision of long-trusted diagnostic criteria in gold-standard instruments.

DOI: 10.1016/j.cell.2025.02.025

Source: https://www.cell.com/cell/abstract/S0092-8674(25)00213-2