No abstract

Machine learning has increasingly been applied to classification of schizophrenia in neuroimaging research. However, direct replication studies and studies seeking to investigate generalizability are scarce. To address these issues, we assessed within‐site and between‐site generalizability of a machine learning classification framework which achieved excellent performance in a previous study using two independent resting‐state functional magnetic resonance imaging data sets collected from different sites and scanners. We established within‐site generalizability of the classification framework in the main data set using cross‐validation. Then, we trained a model in the main data set and investigated between‐site generalization in the validated data set using external validation. Finally, recognizing the poor between‐site generalization performance, we updated the unsupervised algorithm to investigate if transfer learning using additional unlabeled data were able to improve between‐site classification performance. Cross‐validation showed that the published classification procedure achieved an accuracy of 0.73 using majority voting across all selected components. External validation found a classification accuracy of 0.55 (not significant) and 0.70 (significant) using the direct and transfer learning procedures, respectively. The failure of direct generalization from one site to another demonstrates the limitation of within‐site cross‐validation and points toward the need to incorporate efforts to facilitate application of machine learning across multiple data sets. The improvement in performance with transfer learning highlights the importance of taking into account the properties of data when constructing predictive models across samples and sites. Our findings suggest that machine learning classification result based on a single study should be interpreted cautiously.

Current research evaluates the mediating role of attitude toward the green brand and the moderating effect of green trust for the relationship of green brand positioning and green customer value with green purchase intention. Data was collected from the 464 University students with the help of snowball sampling technique. Results describe that green brand positioning and green customer value has noteworthy impact on green purchase intention. Results also illustrate that green brand positioning and green customer value has significant impact on attitude toward green brand. Moreover, attitude toward green brand act as partial mediator for the relationship of green brand positioning and green customer value with green purchase intention. Furthermore, green trust act as moderator for the relationship of green brand positioning and green customer value with green purchase intention. This is cross-sectional research as data is collected at single time point and this kind of research decrease the confidence about cause and effect assumptions. This research only focuses the employees at individual level. Some other potential predictors are not included in this research due to time and cost constraint. It is better to do longitudinal researches on these variables for generalization purpose. In future researches results may be compare at group as well as at network level.

Adverse drug reactions and their related withdrawals occurred mostly at an early stage of NSAID treatment, so it is crucial to strengthen pharmacovigilance during this period. Among the investigated NSAIDs, celecoxib did not prove to be superior to diclofenac, nabumetone or meloxicam with respect to its efficacy in the treatment of rheumatoid arthritis; however, it did show good patient compliance and safety profiles.