使用特征工程和可解释的AI来预测帕金森病的可解释和平衡的机器学习框架
Nasim Mahmud Nayan1, Al Mamun Rana2, Md Monirul Islam3
1Department of Computer Science and Engineering, University of Information Technology and Sciences (UITS), Dhaka, Bangladesh.
PloS one
|October 31, 2025
概括
这项研究引入了一种增强的机器学习 (ML) 框架,用于预测帕金森病 (PD). 该框架结合了数据平衡,特征选择和可解释的AI,为早期PD检测提供了更准确和可解释的诊断工具.
科学领域:
- 神经学 神经学
- 计算机科学 计算机科学
- 生物医学工程 生物医学工程
背景情况:
- 帕金森病 (PD) 是一种具有诊断挑战的渐进性神经系统疾病.
- 机器学习 (ML) 提供了精确和高效的PD预测的潜力.
- 早期和准确的PD诊断对于患者管理至关重要.
研究的目的:
- 开发一个增强的ML框架,以改善PD预测.
- 整合数据平衡,功能选择和可解释的AI (XAI) 技术.
- 提高PD诊断模型的公平性,性能和可解释性.
主要方法:
- 对临床和语音特征的9个ML算法的评估.
- 应用合成少数群体过量采样技术 (SMOTE) 和NearMiss用于阶级不平衡.
- 使用了Featurewiz,基于树的特征重要性,以及用于特征选择的chi-square.
- 雇佣了SHAP和LIME为XAI解释模型决策.
主要成果:
- 使用SMOTE的KNN模型实现了92%的准确性,0.94的F1得分和0.95的G-Mean,表明了平衡和可靠的PD检测.
- 一些模型在不平衡的数据上显示出更高的准确性 (高达97%),但缺乏敏感性和平衡性.
- 功能选择确定了关键的语音生物标志物,如音调周期 (PPE) 和噪声与律比率 (NHR).
结论:
- 结合SMOTE,特征工程和XAI,显著提高了ML模型的公平性,性能和PD预测的可解释性.
- 拟议的框架提供了一个准确和可解释的基于ML的诊断工具.
- 这项研究支持早期的PD诊断,并增强患者管理策略.
更多相关视频
10:28Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease
Published on: July 24, 2019
15.9K
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
8.6K
相关概念视频
01:15Parkinson's Disease: Overview
1.7K
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...
1.7K
01:37Neural Regulation
43.1K
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.
43.1K
01:24Parkinson's Disease: Treatment
963
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...
963