PDF(Pubmed)
Abstract：
Alzheimer\'s disease (AD) is a challenging neurodegenerative condition, necessitating early diagnosis and intervention. This research leverages machine learning (ML) and graph theory metrics, derived from resting-state functional magnetic resonance imaging (rs-fMRI) data to predict AD. Using Southwest University Adult Lifespan Dataset (SALD, age 21-76 years) and the Open Access Series of Imaging Studies (OASIS, age 64-95 years) dataset, containing 112 participants, various ML models were developed for the purpose of AD prediction. The study identifies key features for a comprehensive understanding of brain network topology and functional connectivity in AD. Through a 5-fold cross-validation, all models demonstrate substantial predictive capabilities (accuracy in 82-92% range), with the support vector machine model standing out as the best having an accuracy of 92%. Present study suggests that top 13 regions, identified based on most important discriminating features, have lost significant connections with thalamus. The functional connection strengths were consistently declined for substantia nigra, pars reticulata, substantia nigra, pars compacta, and nucleus accumbens among AD subjects as compared to healthy adults and aging individuals. The present finding corroborate with the earlier studies, employing various neuroimagining techniques. This research signifies the translational potential of a comprehensive approach integrating ML, graph theory and rs-fMRI analysis in AD prediction, offering potential biomarker for more accurate diagnostics and early prediction of AD.
摘要：
阿尔茨海默病（AD）是一种具有挑战性的神经退行性疾病，需要早期诊断和干预。这项研究利用了机器学习(ML)和图论指标，从静息态功能磁共振成像（rs-fMRI）数据中得出预测AD的数据。使用西南大学成人寿命数据集(SALD，年龄21-76岁)和开放获取系列成像研究(OASIS，年龄64-95岁)数据集，包含112名参与者，开发了各种ML模型用于AD预测。该研究确定了全面了解AD中脑网络拓扑和功能连通性的关键特征。通过5倍交叉验证，所有模型都表现出相当大的预测能力(准确率在82-92%范围内)，支持向量机模型作为最佳模型，准确率为92%。目前的研究表明，前13个地区，基于最重要的区分特征识别，与丘脑失去了重要的联系.黑质的功能连接强度持续下降，网状结构,黑质,parscompacta,与健康成年人和衰老个体相比，AD受试者中的伏隔核。目前的发现证实了早期的研究，采用各种神经成像技术。这项研究标志着整合ML的综合方法的转化潜力，图论和rs-fMRI分析在AD预测中的应用，为AD的更准确诊断和早期预测提供潜在的生物标志物。
