AUTHOR=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 

TITLE=A Tensorized Multitask Deep Learning Network for Progression Prediction of Alzheimer’s Disease

JOURNAL=Frontiers in Aging Neuroscience

VOLUME=Volume 14 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/aging-neuroscience/articles/10.3389/fnagi.2022.810873

DOI=10.3389/fnagi.2022.810873

ISSN=1663-4365

ABSTRACT=Using advances in machine learning for the diagnosis of Alzheimer's disease (AD) has attracted a lot of interest in recent years. However, 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 tasks.  Motivated by the need to enhance the prospects for early diagnosis along with the ability to predict future disease states, this paper proposes a deep neural network based on modality fusion, kernelization, and tensorization to perform multiclass classification and longitudinal regression simultaneously within a unified multitask framework. More specifically, the proposed method explores the relationship between classification and longitudinal regression tasks 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 from baseline. The proposed framework has been evaluated on a longitudinal Alzheimer’s Disease Neuroimaging Initiative (ADNI) cohort, involving 1117 subjects (328 CN, 191 MCI-C, 441 MCI-NC, and 157 AD). 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, and vice versa if the processing order is reversed. In other words, there is a breakpoint at which enhancing further the results of one process could lead to the downgrading of the accuracy for the other.