可解释机器学习的代谢学数据揭示了帕金森病的生物标志物
J Diana Zhang1,2, Chonghua Xue2, Vijaya B Kolachalama2,3
1School of Chemistry, University of New South Wales, Sydney 2052, Australia.
ACS central science
|May 30, 2023
概括
本研究引入了一个可解释的神经网络 (NN) 框架,用于使用代谢学预测疾病. 这种新的方法可以准确地从血中识别帕金森病的生物标志物,超过现有的机器学习方法.
科学领域:
- 生物医学数据分析
- 计算生物学是一种计算生物学.
- 代谢学 代谢学 代谢学
背景情况:
- 机器学习 (ML) 在代谢学中有助于早期诊断疾病,但在模型解释性和分析复杂,杂数据方面面临挑战.
- 解释ML模型和处理众多相关化学特征是当前代谢疾病预测的关键局限性.
研究的目的:
- 开发一个可解释的神经网络 (NN) 框架,以使用整体代谢学数据准确预测疾病.
- 在没有先前特征选择的情况下识别重要的疾病生物标志物.
- 为了提高对帕金森病 (PD) 等疾病的代谢学的诊断性能.
主要方法:
- 实现一个新的,可解释的神经网络 (NN) 框架.
- 对全血代谢学数据的应用,用于帕金森病 (PD) 的预测.
- 与其他ML方法相比,NN性能的评估,没有先验特征选择.
主要成果:
- 与其他ML方法相比,NN框架在预测PD方面取得了显著更高的性能,曲线下的平均面积>0.995.5.
- 确定了PD特异性生物标志物,包括外源性多基基物质,可以在临床诊断前预测疾病.
- 证明了分析整个代谢学数据集的能力,而不需要预先选择的功能.
结论:
- 可解释的NN方法提供了准确的疾病预测和生物标志物识别从代谢学数据.
- 这一框架可以显著提高帕金森病和潜在的其他疾病的诊断能力.
- 该方法促进了代谢学和其他非向的"omics"方法在临床诊断中的应用.
相关概念视频
01:37Neural Regulation
39.6K
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.
39.6K
01:24Parkinson's Disease: Treatment
308
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...
308
01:15Parkinson's Disease: Overview
614
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...
614