数据泄露和特征选择对早期帕金森病检测机器学习性能的影响
Jonathan Starcke1, James Spadafora1, Jonathan Spadafora1
1Department of Osteopathic Manipulative Medicine, College of Osteopathic Medicine, New York Institute of Technology, Old Westbury, NY 11568, USA.
Bioengineering (Basel, Switzerland)
|August 28, 2025
概括
机器学习模型对帕金森病的检测可能会因为数据泄露而导致误导. 严格的评估对于确保人工智能诊断工具在临床上有用和值得信赖至关重要.
科学领域:
- 医学的人工智能
- 医疗保健中的机器学习
- 神经疾病诊断
背景情况:
- 人工智能 (AI) 在医学诊断方面表现有前途,但对模型可靠性存在担忧.
- 数据泄露和不适当的验证可能会增加人工智能模型的性能,并可能误导临床医生.
- 准确的早期发现帕金森病 (PD) 对于有效的患者管理至关重要.
研究的目的:
- 系统地调查数据泄露和特征选择对早期发现帕金森病的机器学习模型的影响.
- 在现实,亚临床诊断场景中评估AI模型的真正临床实用性.
- 突出了人工智能诊断中的高性能指标带来的风险.
主要方法:
- 建立了两个实验管道:一个不包括明显的运动症状 (亚临床模拟) 和一个包括它们的控制.
- 使用强大的三向数据分割评估了9个机器学习算法.
- 进行了包括F1分数和特异性在内的全面指标分析.
主要成果:
- 在没有明显运动症状的情况下训练的模型表现出表面上可以接受的F1分数,
- 在临床前情景中,健康对照群经常被错误地归类为患有帕金森病.
- 包括明显的电机特征显著改善了模型性能,表明数据泄露是高初始精度的原因.
结论:
- 人工智能模型的高准确性可能是由于数据泄露而导致的, 而不是真正的预测能力.
- 严格的实验设计和验证对于开发具有临床意义的AI诊断工具至关重要.
- 在现实环境中对人工智能模型进行批判性评估是保持临床医生的信任和提高患者护理的必要条件.
相关概念视频
Parkinson's Disease: Treatment
376
Neurodegenerative disorders, such as Parkinson's Disease (PD), involve the gradual and irreversible destruction of neurons in particular brain areas. These disorders exhibit standard features like proteinopathies, selective vulnerability of some neurons, and an interaction of intrinsic properties, genetics, and environmental influences in neural injury.
Parkinson's Disease is primarily a result of the loss of dopaminergic neurons in the substantia nigra pars compacta. The cornerstone of...
Parkinson's Disease is primarily a result of the loss of dopaminergic neurons in the substantia nigra pars compacta. The cornerstone of...
376
Neural Regulation
39.9K
Digestion begins with a cephalic phase that prepares the digestive system to receive food. When our brain processes visual or olfactory information about food, it triggers impulses in the cranial nerves innervating the salivary glands and stomach to prepare for food.
39.9K
Parkinson's Disease: Overview
702
Neurodegenerative disorders are progressive diseases that cause irreversible damage and loss to neurons in specific brain areas. Examples of these disorders include Parkinson's disease, Alzheimer's disease, Multiple Sclerosis (MS), and Amyotrophic Lateral Sclerosis (ALS). These disorders share characteristics such as proteinopathies, selective neuronal vulnerability, and a complex interplay between genetic and environmental factors. The primary therapeutic goal for these conditions is...
702


