Tabarestani Solale, Eslami Mohammad, Cabrerizo Mercedes, Curiel Rosie E, Barreto Armando, Rishe Naphtali, Vaillancourt David, DeKosky Steven T, Loewenstein David A, Duara Ranjan, Adjouadi Malek
Center for Advanced Technology and Education, Florida International University, Miami, FL, United States.
Harvard Ophthalmology AI Lab and Harvard Medical School, Schepens Eye Research Institute, Massachusetts Eye and Ear, Boston, MA, United States.
Front Aging Neurosci. 2022 May 6;14:810873. doi: 10.3389/fnagi.2022.810873. eCollection 2022.
With the advances in machine learning for the diagnosis of Alzheimer's disease (AD), most studies have focused on either identifying the subject's status through classification algorithms or on predicting their cognitive scores through regression methods, neglecting the potential association between these two tasks. Motivated by the need to enhance the prospects for early diagnosis along with the ability to predict future disease states, this study proposes a deep neural network based on modality fusion, kernelization, and tensorization that perform multiclass classification and longitudinal regression simultaneously within a unified multitask framework. This relationship between multiclass classification and longitudinal regression is found to boost the efficacy of the final model in dealing with both tasks. Different multimodality scenarios are investigated, and complementary aspects of the multimodal features are exploited to simultaneously delineate the subject's label and predict related cognitive scores at future timepoints using baseline data. The main intent in this multitask framework is to consolidate the highest accuracy possible in terms of precision, sensitivity, F1 score, and area under the curve (AUC) in the multiclass classification task while maintaining the highest similarity in the MMSE score as measured through the correlation coefficient and the RMSE for all time points under the prediction task, with both tasks, run simultaneously under the same set of hyperparameters. The overall accuracy for multiclass classification of the proposed KTMnet method is 66.85 ± 3.77. The prediction results show an average RMSE of 2.32 ± 0.52 and a correlation of 0.71 ± 5.98 for predicting MMSE throughout the time points. These results are compared to state-of-the-art techniques reported in the literature. A discovery from the multitasking of this consolidated machine learning framework is that a set of hyperparameters that optimize the prediction results may not necessarily be the same as those that would optimize the multiclass classification. In other words, there is a breakpoint beyond which enhancing further the results of one process could lead to the downgrading in accuracy for the other.
随着机器学习在阿尔茨海默病（AD）诊断方面的进展，大多数研究要么专注于通过分类算法识别受试者的状态，要么通过回归方法预测他们的认知分数，而忽略了这两项任务之间的潜在关联。出于提高早期诊断前景以及预测未来疾病状态能力的需求，本研究提出了一种基于模态融合、核化和张量化的深度神经网络，该网络在统一的多任务框架内同时执行多类分类和纵向回归。发现多类分类与纵向回归之间的这种关系提高了最终模型处理这两项任务的效率。研究了不同的多模态场景，并利用多模态特征的互补方面，使用基线数据同时描绘受试者的标签并预测未来时间点的相关认知分数。这个多任务框架的主要目的是在多类分类任务中，在精度、灵敏度、F1分数和曲线下面积（AUC）方面巩固尽可能高的准确性，同时在预测任务下的所有时间点，通过相关系数和均方根误差（RMSE）测量，保持MMSE分数的最高相似度，两项任务在同一组超参数下同时运行。所提出的KTMnet方法的多类分类总体准确率为66.85±3.77。预测结果显示，在预测整个时间点的MMSE时，平均RMSE为2.32±0.52，相关性为0.71±5.98。这些结果与文献中报道的最先进技术进行了比较。从这个整合的机器学习框架的多任务处理中发现，一组优化预测结果的超参数不一定与优化多类分类的超参数相同。换句话说，存在一个断点，超过这个断点，进一步提高一个过程的结果可能会导致另一个过程的准确性下降。
