在阿尔茨海默氏症研究中缺少数据推算的机器学习:预测中间时叶的灵活性
bioRxiv : the preprint server for biology
|June 12, 2025
概括
机器学习有效地使用先进的归算方法预测中叶 (MTL) 网络在老化队伍中的灵活性. 错过森林与随机森林显著提高了准确性,解决了阿尔茨海默病研究中缺失的数据挑战.
科学领域:
- 神经科学是一个神经科学.
- 生物医学工程 生物医学工程
- 机器学习 机器学习
背景情况:
- 阿尔茨海默病 (AD) 病理在症状出现前几年就开始,因此需要早期检测生物标志物.
- 中间叶 (MTL) 网络灵活性,这是大脑连接的衡量标准,是AD相关衰退的早期指标.
- 认知,遗传和生物化学标记可以预测MTL动态灵活性.
研究的目的:
- 预测中叶 (MTL) 动态灵活性使用老化队列中的多式联络数据.
- 评估先进的机器学习和归算方法,以处理AD研究中的高缺失数据率.
主要方法:
- 利用了来自656名参与者的数据,包括认知,遗传和血液生物标志物.
- 评估了四种缺失数据处理方法 (案例删除,MICE,MissForest,GAIN) 和五种回归模型 (Ridge,k-NN,SVR,回归树,ANN).
- 通过网格搜索优化超参数,并使用MAE,RMSE和运行时间进行交叉验证来评估模型性能.
主要成果:
- 识别了25.86%的缺失值,在列表删除后只有6.40%的完整案例.
- 与随机森林回归相结合的MissForest归算实现了最佳表现 (MAE = 0.083),比删除病例有54.7%的改善.
- 森林小姐的表现明显优于GAIN和MICE (p < 0.001),而GAIN是最快的归算方法.
结论:
- 在缺乏大量数据的研究中,强大的归算策略对于最大限度地提高数据实用性和模型可靠性至关重要.
- 机器学习模型,特别是具有高级归算的机器学习模型,可以有效地预测MTL的动态灵活性.
- 需要进一步研究纳入神经成像,以改进AD临床应用的预测模型.
更多相关视频
09:38Generalized Psychophysiological Interaction PPI Analysis of Memory Related Connectivity in Individuals at Genetic Risk for Alzheimer's Disease
Published on: November 14, 2017
14.8K
09:47Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
Published on: December 15, 2023
981
相关概念视频
Alzheimer's Disease: Treatment
Alzheimer's Disease (AD), a neurodegenerative disorder, is pathologically identified by amyloid plaques and neurofibrillary tangles composed of tau protein. AD pharmacotherapy aims to manage cognitive symptoms, delay disease progression, and treat behavioral symptoms. The treatment is primarily symptomatic and palliative, with no definitive disease-modifying therapy available. Cholinesterase inhibitors, including donepezil (Aricept), rivastigmine (Exelon), and galantamine (Razadyne), are...
Alzheimer Disease l: Introduction
Alzheimer disease is a chronic, progressive, and irreversible neurodegenerative disorder and the most common cause of dementia in older adults. It leads to gradual neuronal loss, causing cognitive decline, behavioral changes, and loss of functional independence.Risk Factors and EtiologyThe disease is multifactorial. Age is the strongest risk factor, with prevalence doubling every 5 years after age 65. Genetic factors include mutations in genes such as APP, PSEN1, and PSEN2, which are associated...
