The neuroimaging-based computer-aided diagnosis for Parkinson's disease (PD) has attracted considerable attention in recent years, where the classifier plays a critical role. Random vector functional link network (RVFL) has shown its effectiveness for classification task, while its extended version, namely RVFL plus (RVFL+), integrates the additional privileged information (PI) about training samples in RVFL to help training a more effective classifier. On the other hand, it is still a popular way to adopt only a single neuroimaging modality for PD diagnosis in clinical practice. In this work, we construct a novel cascaded multi-column RVFL+ (cmcRVFL+) framework for the single-modal neuroimaging-based PD diagnosis without the additional neuroimaging modality as PI. Specifically, the predicted values of RVFL+ classifiers in the current layers are used as the PI for the following classifiers, and therefore, the PI features are self-generated without additional modality. Furthermore, only the multi-column RVFL+ classifiers in the last layer of cmcRVFL+ are finally ensembled to generate the predictive result in the test stage. The experimental results on both the transcranial sonography dataset and the magnetic resonance imaging dataset for PD show that the proposed cmcRVFL+ algorithm achieves superior performance to all the compared algorithms. It suggests that the proposed cmcRVFL+ has the potential to be flexibly applied to various single-modal imaging based CAD.

Patients with uremia have high cardiovascular disease morbidity and mortality despite having normal left ventricular ejection fraction (LVEF). Longitudinal strain (LS) can be associated with subtle changes in LV systolic function. The aim of this study was to use two-dimensional speckle-tracking echocardiography (2DSTE) to assess subclinical LV myocardial dysfunction and to explore strain-changing regularities in uremic patients with LVEF ≥ 55%. The study population included 40 uremic patients and 40 healthy volunteers. 2DSTE was performed on all participants to assess peak LS in the basal, mid and apical LV (BLS, MLS and ALS) and the respective time to peak LS (T-BLS, T-MLS, T-ALS). BLS, MLS, and ALS were significantly decreased in the uremic group relative to healthy controls and LS increased going in a basal to apical direction in both groups. T-BLS, T-MLS and T-ALS was significantly increased in the uremic group compared with the control group. In uremic patients, T-BLS, but not T-MLS or T-ALS, was significantly delayed relative to the control group. Bivariate analysis of creatinine (Cr) or urea nitrogen and strain parameters revealed a correlation only between ALS and Cr. 2DSTE can identify LV myocardial abnormalities in uremic patients with preserved LVEF at early stage, as well as some changing regularities of LS and T-LS in the left ventricle.