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

•Accurate identification of the different stage of Alzheimer's disease is essential for early prevention of disease.•Sparse logistic regression with the generalized elastic net improves is proposed for the early diagnosis of Alzheimer's disease.•The sparsity brought by the generalized elastic net makes the model capable of selecting the most discriminative brain regions and achieving excellent classification performance. 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 L2 regularization. The Lp regularization can produce sparse solutions. L2 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.