Adaptive feature selection with flexible mapping for diagnosis and prediction of Parkinson's disease

Parkinson's disease (PD) is a neurodegenerative disorder in which symptoms gradually worsen over time, with no cure currently available. Therefore, its early-stage treatment is crucial. However, medical neuroimaging data often contain redundant features and high dimensionality, which can negatively impact algorithm accuracy and require greater computational resources. To address this challenge, a supervised feature selection algorithm is proposed for the early diagnosis of PD. Specifically, the proposed method incorporates adaptive learning during iterations, which enables adaptive updating of the similarity matrix and selection of informative features. Meanwhile, flexible mapping is introduced to address the limitations of strict linear mapping. To address the optimization challenge of the model, we propose an alternative iterative algorithm and provide theoretical proof of its strict convergence. To measure the effectiveness of the algorithm, we conducted experiments on the Parkinson's Progression Markers Initiative (PPMI) public dataset, involving three groups: PD vs. normal controls (NC), scans without evidence of dopaminergic deficit (SWEDD) vs. NC, and PD vs. SWEDD. Based on baseline data, the accuracies for these three groups were 83.29%, 87.67%, and 85.16%, respectively. Using the 12-month data, the accuracies improved to 79.70%, 96.79%, and 96.95%, while the 24-month data resulted in accuracies of 91.33%, 70.10%, and 93.36%. The experimental results demonstrate that the proposed method outperforms existing feature selection methods in overall performance.