大型语言模型解构了诊断自闭症背后的临床直觉
Jack Stanley1, Emmett Rabot2, Siva Reddy3
1Mila - Québec Artificial Intelligence Institute, Montréal, QC H2S3H1, Canada; The Neuro - Montréal Neurological Institute (MNI), McConnell Brain Imaging Centre, Department of Biomedical Engineering, Faculty of Medicine, School of Computer Science, McGill University, Montréal, QC H3A2B4, Canada.
大型语言模型 (LLM) 分析临床报告以了解自闭症诊断. 这项研究将刻板印象的行为和特殊兴趣确定为关键诊断指标,
科学领域:
- 神经科学
- 人工智能
- 临床心理学
背景情况:
- 目前使用全基因组测试或脑部扫描的自闭症谱系障碍 (ASD) 诊断方法取得了有限的成功.
- 医疗保健专业人员的临床直觉仍然是诊断自闭症的主要方法,突出了客观诊断工具的差距.
研究的目的:
- 通过深度学习解构和分析专家诊断自闭症的直觉背后的逻辑.
- 在临床报告中确定有助于准确诊断自闭症的关键指标.
主要方法:
- 在一般文本上进行预训练,并对4000多份临床健康记录进行了微调.
- 在LLM架构中使用可解释性策略来确定驱动诊断决策的突出句子.
主要成果:
- 精细调整的LLM成功地区分了确诊和疑似的自闭症病例.
- 该框架确定了刻板印象的重复行为,特殊兴趣和基于感知的行为作为自闭症的关键诊断指标.
- 这些发现挑战了目前对社会互动缺陷的诊断重视.
结论:
- 临床报告的深度学习分析可以有效地捕获和审视专家的诊断直觉.
- 这项研究表明需要修订目前的自闭症诊断标准,特别是精神障碍诊断和统计手册第五版 (DSM-5),以更好地纳入行为和感知因素.
更多相关视频
09:13Testing Sensory and Multisensory Function in Children with Autism Spectrum Disorder
Published on: April 22, 2015
10:11Portable Intermodal Preferential Looking IPL: Investigating Language Comprehension in Typically Developing Toddlers and Young Children with Autism
Published on: December 14, 2012
相关概念视频
Learning Disabilities
Dyslexia
Dyslexia is a...
Modeling in Therapy
Participant Modeling
Participant modeling involves therapists demonstrating calm and effective behaviors in...
Autism Spectrum Disorder
These core symptoms manifest differently among individuals, ranging from mild to severe. The disorder's complexity extends beyond its clinical presentation, encompassing a diverse range of biological, cognitive, and sociocultural influences.
Language and Cognition
Reason and Intuition
Formulating and Validating Nursing Diagnosis II
Risk nursing diagnoses represent clinical judgments of an individual, family, or community more vulnerable to developing the health problem than others...
