人工智能可以根据患者的描述来诊断发作吗? 一个关于GPT-4的研究
Joseph Ford1, Nathan Pevy2, Richard Grunewald1
1Academic Neurology Unit, University of Sheffield, Sheffield, UK.
Epilepsia
|February 27, 2025
概括
大型语言模型 (LLM) 在诊断与功能性发作方面显示出潜力,并通过示例改进. 进一步的改进可以释放它们的全部诊断能力.
科学领域:
- 医疗人工智能 医疗人工智能
- 神经学 神经学
- 临床诊断 临床诊断 临床诊断
背景情况:
- 一般的大型语言模型 (LLM) 证明了医学中的诊断能力.
- 对于发作与功能/离散性发作 (FDS) 的差异诊断,LLM尚未得到广泛的研究.
研究的目的:
- 根据患者描述,评估OpenAI的GPT-4用于区分发作和FDS的诊断性能.
- 评估几次射击学习 (零次射击,一次射击,两次射击,三次射击) 对GPT-4诊断准确性的影响.
主要方法:
- GPT-4的任务是使用患者的症状记录来诊断41例病例 (16例,25例FDS).
- 该模型的性能在零射击和少数射击条件下进行了测试 (1-3个例子).
- 与三个经验丰富的神经科医生进行了基准比较,他们在没有额外的临床数据的情况下诊断出相同的病例.
主要成果:
- 在零射击条件下,GPT-4实现了57%的平衡精度,在一次射击条件下提高到64%.
- 在两次射击 (62%) 和三次射击 (62%) 条件下,表现平稳,低于神经科医生的平均准确度 (71%).
- 在所有神经科医生正确诊断的病例中,GPT-4实现了81%的平衡精度.
结论:
- GPT-4在最小的例子中显示出改善,这表明发作差异诊断的潜力.
- 该模型在具有挑战性的案例上的增强性能表明,改进的数据和先进的技术 (例如,提示工程,微调) 可以优化LLM诊断实用程序.
- 需要进一步的研究来探索精细的方法来利用LLMs在复杂的神经诊断中.
更多相关视频
06:28Author Spotlight: Unraveling Seizure Dynamics and Novel Therapeutics for Status Epilepticus Using CMOS High-Density Microelectrode Array Systems
Published on: September 27, 2024
2.1K
09:16Use of a Wireless Video-EEG System to Monitor Epileptiform Discharges Following Lateral Fluid-Percussion Induced Traumatic Brain Injury
Published on: June 21, 2019
25.5K
相关概念视频
Arteries of the Lower Limbs
176
Epilepsy is a chronic neurological disease marked by recurrent, unpredictable seizures. These seizures are caused by abnormal electrical discharges in the brain, leading to behavior, sensation, or consciousness alterations. They can also cause transient impairment of awareness, interfering with daily activities.
Various factors can trigger epilepsy, including genetic factors, brain damage, metabolic causes, and unknown etiology. Diagnosis of epilepsy involves electroencephalography (EEG), which...
Various factors can trigger epilepsy, including genetic factors, brain damage, metabolic causes, and unknown etiology. Diagnosis of epilepsy involves electroencephalography (EEG), which...
176
Seizures: Classification
297
Epilepsy is primarily characterized by unpredictable seizures, either provoked by an identifiable factor, such as injury or illness, or unprovoked, occurring spontaneously without apparent cause.
Seizures are typically classified into two main categories: focal and generalized seizures.
Focal Seizures
Focal seizures originate from specific regions of the brain. These seizures are further sub-classified into two types:
Seizures are typically classified into two main categories: focal and generalized seizures.
Focal Seizures
Focal seizures originate from specific regions of the brain. These seizures are further sub-classified into two types:
297
