Self-weighted Multi-task Learning for Subjective Cognitive Decline Diagnosis

Abstract

Subjective cognitive decline (SCD) is an early stage of mild cognitive impairment (MCI) and may represent the first symptom manifestation of Alzheimer’s disease (AD). Early diagnosis of MCI is important because early identification and intervention can delay or even reverse the progression of this disease. This paper proposes an automatic diagnostic framework for SCD and MCI. Specifically, we design a new multi-task learning model to integrate neuroimaging functional and structural connectivity in a predictive framework. We construct a functional brain network by sparse low-rank brain network estimation methods, and a structural brain network is constructed using fiber bundle tracking. Subsequently, we use multi-task learning methods to select features for integrated functional and structural connections, the importance of each task and the balance between both modalities are automatically learned. By integrating both functional and structural information, the most discriminative features of the disease are obtained for diagnosis. The experiments on the dataset show that our proposed method achieves good performance and is superior to the traditional algorithms. In addition, the proposed method can identify the most discriminative brain regions and connections. These results follow current clinical findings and add new findings for disease detection and future medical analysis.