Early diagnosis model of Alzheimer's disease based on sparse logistic regression with the generalized elastic net

Accurate prediction of high-risk group who may convert to Alzheimer's disease (AD) patients is critical for the future treatment of patients. Recently, logistic regression is used for the early diagnosis of AD. However, due to the high-dimensional small sample characteristics of AD data, this brings difficulties to logistic regression-aided diagnosis. To solve the problem, in this paper, we propose sparse logistic regression with the generalized elastic net for the early diagnosis of AD. The generalized elastic net is composed of Lp regularization and L-2 regularization. The Lp regularization can produce sparse solutions. L-2 regularization ensures that the correlated brain regions are in solution. We evaluate our proposed method on 197 subjects from the baseline MRI data of ADNI database. Our proposed method achieves classification accuracy of 96.10, 84.67, and 75.87 %, for AD vs. HC, MCI vs. HC, and cMCI vs. sMCI, respectively. Experimental results show that, compared with previous methods, our proposed method captures distinct brain regions that are significantly related to AD conversion and provides a significant enhancement in AD classification.

Automated summary

This study proposes a method based on generalized elastic net sparse logistic regression for early diagnosis of AD, achieving high classification accuracy in experiments and showing promising results in capturing distinct brain regions related to AD conversion.