优化机器学习方法以提高阿尔茨海默病预测模型的性能。
Optimizing Machine Learning Methods to Improve Predictive Models of Alzheimer's Disease.
机构信息
Department of Neurology, Albert Einstein College of Medicine, Bronx, NY, USA.
Department of Neurology, Montefiore Medical Center, Bronx, NY, USA.
出版信息
J Alzheimers Dis. 2019;71(3):1027-1036. doi: 10.3233/JAD-190262.
BACKGROUND
Predicting clinical course of cognitive decline can boost clinical trials' power and improve our clinical decision-making. Machine learning (ML) algorithms are specifically designed for the purpose of prediction; however. identifying optimal features or algorithms is still a challenge.
OBJECTIVE
To investigate the accuracy of different ML methods and different features to classify cognitively normal (CN) individuals from Alzheimer's disease (AD) and to predict longitudinal outcome in participants with mild cognitive impairment (MCI).
METHODS
A total of 1,329 participants from the Alzheimer's Disease Neuroimaging Initiative (ADNI) were included: 424 CN, 656 MCI, and 249 AD individuals. Four feature-sets at baseline (hippocampal volume and volume of 47 cortical and subcortical regions with and without demographics and APOE4) and six machine learning methods (decision trees, support vector machines, K-nearest neighbor, ensemble linear discriminant, boosted trees, and random forests) were used to classify participants with normal cognition from participants with AD. Subsequently the model with best classification performance was used for predicting clinical outcome of MCI participants.
RESULTS
Ensemble linear discriminant models using demographics and all volumetric magnetic resonance imaging measures as feature-set showed the best performance in classification of CN versus AD participants (accuracy = 92.8%, sensitivity = 95.8%, and specificity = 88.3%). Prediction accuracy of future conversion from MCI to AD for this ensemble linear discriminant at 6, 12, 24, 36, and 48 months was 63.8% (sensitivity = 74.4, specificity = 63.1), 68.9% (sensitivity = 75.9, specificity = 67.8), 74.9% (sensitivity = 71.5, specificity = 76.3), 75.3%, (sensitivity = 65.2, specificity = 79.7), and 77.0% (sensitivity = 59.6, specificity = 86.1), respectively.
CONCLUSIONS
Machine learning models trained for classification of CN versus AD can improve our prediction ability of MCI conversion to AD.
背景
预测认知能力下降的临床病程可以提高临床试验的效能，并改善我们的临床决策。机器学习（ML）算法专门用于预测目的；然而，确定最佳特征或算法仍然是一个挑战。
目的
调查不同 ML 方法和不同特征对分类认知正常（CN）个体与阿尔茨海默病（AD）以及预测轻度认知障碍（MCI）患者纵向结局的准确性。
方法
共纳入来自阿尔茨海默病神经影像学倡议（ADNI）的 1329 名参与者：424 名 CN、656 名 MCI 和 249 名 AD 个体。在基线时使用 4 个特征集（海马体积和 47 个皮质和皮质下区域的体积，有和没有人口统计学和 APOE4）和 6 种机器学习方法（决策树、支持向量机、K-最近邻、集成线性判别、增强树和随机森林）对认知正常参与者与 AD 参与者进行分类。随后，使用分类性能最佳的模型对 MCI 参与者的临床结局进行预测。
结果
使用人口统计学和所有容积磁共振成像测量值作为特征集的集成线性判别模型在 CN 与 AD 参与者的分类中表现出最佳性能（准确性=92.8%，敏感性=95.8%，特异性=88.3%）。对于这个集成线性判别模型，6、12、24、36 和 48 个月时从 MCI 向 AD 转换的未来预测准确率为 63.8%（敏感性=74.4，特异性=63.1）、68.9%（敏感性=75.9，特异性=67.8）、74.9%（敏感性=71.5，特异性=76.3）、75.3%（敏感性=65.2，特异性=79.7）和 77.0%（敏感性=59.6，特异性=86.1）。
结论
为分类 CN 与 AD 而训练的机器学习模型可以提高我们对 MCI 向 AD 转换的预测能力。
Zotero 插件