Search

Parkinson's disease (PD) is an irreversible neurodegenerative disease that has serious impacts on patients' lives. To provide timely accurate treatment and delay the deterioration of the disease, the accurate early diagnosis and clinical score prediction of PD are extremely important. Differing from previous studies on PD, we propose a network combining feature selection method with feature learning to obtain the most discriminative feature representation for longitudinal early diagnosis and clinical score prediction. Specifically, we first preprocess the multi-modal neuroimaging data at multiple time points to extract original longitudinal multi-modal features. Then, the feature selection method is performed to preliminary reduce the feature dimensions. Finally, the stacked sparse nonnegative autoencoder (SSNAE) is employed to obtain more discriminative longitudinal multi-modal features to improve the accuracy of early diagnosis and clinical score prediction at multiple time points. To verify our proposed network, diverse and extensive experiments are performed on the Parkinson's Progression Markers Initiative dataset, which aims to identify biological markers of PD risk, onset and progression. The results demonstrate that our proposed method is more efficient and achieves promising performance on both longitudinal early diagnosis and clinical scores prediction compared to state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The efficacy of thrombolytic therapy for acute ischemic stroke (AIS) decreases when the administration of tissue plasminogen activator (tPA) is delayed. Derived from Toyota Production System, lean production aims to create top-quality products with high-efficiency procedures, a concept that easily applies to emergency medicine. In this study, we aimed to determine whether applying lean principles to flow optimization could hasten the initiation of thrombolysis. A multidisciplinary team (Stroke Team) was organized to implement an ongoing, continuous loop of lean production that contained the following steps: decomposition, recognition, intervention, reengineering and assessment. The door-to-needle time (DNT) and the percentage of patients with DNT ≤ 60 min before and after the adoption of lean principles were used to evaluate the efficiency of our flow optimization. Thirteen patients with AIS in the pre-lean period and 43 patients with AIS in the lean period (23 in lean period I and 20 patients in lean period II) were consecutively enrolled in our study. After flow optimization, we reduced DNT from 90 to 47 min ( p < 0.001). In addition, the percentage of patients treated ≤60 min after hospital arrival increased from 38.46 to 75.0 % ( p = 0.015). Adjusted analysis of covariance confirmed a significant influence of optimization on delay of tPA administration ( p < 0.001). The patients were more likely to have a good prognosis (mRS ≤ 2 at 90 days) after the flow optimization (30.77-75.00 %, p = 0.012). Our study may offer an effective approach for optimizing the thrombolytic flow in the management of AIS. [ABSTRACT FROM AUTHOR]