Functional magnetic resonance imaging (fMRI) is one of the most promising noninvasive techniques for early Alzheimer's disease (AD) diagnosis. In this paper, we explore the application of different machine learning techniques to the classification of fMRI data for this purpose. The functional images were first preprocessed using the statistical parametric mapping toolbox to output individual maps of statistically activated voxels. A fast filter was applied afterwards to select voxels commonly activated across demented and nondemented groups. Four feature ranking selection techniques were embedded into a wrapper scheme using an inner-outer loop for the selection of relevant voxels. The wrapper approach was guided by the performance of six pattern recognition models, three of which were ensemble classifiers based on stochastic searches. Final classification performance was assessed from the nested internal and external cross-validation loops taking several voxel sets ordered by importance. Numerical performance was evaluated using statistical tests, and the best combination of voxel selection and classification reached a 97.14% average accuracy. Results repeatedly pointed out Brodmann regions with distinct activation patterns between demented and nondemented profiles, indicating that the machine learning analysis described is a powerful method to detect differences in several brain regions between both groups.
BackgroundAcute flaccid paralysis (AFP) surveillance is carried out in Argentina in the frame of the Polio Eradication Program. Acute flaccid myelitis (AFM) is a type of AFP and can be detected in the frame of AFP surveillance. Although many case series of AFM associated to enterovirus (EV) were released since 2014 in many countries, there were no notifications of this entity from Argentina until 2016.MethodsDescriptive-observational study. AFP cases reported to the National Surveillance System (NSS) between 2016 and 2018 were included.ResultsFrom January 1, 2016 to December 31, 2018, 610 cases of AFP in children under 15 years old were registered (207 in 2016, 205 in 2017 and 198 in 2018). In 2016, from epidemiological weeks (EWs) 14 to 28, 23 cases of AFM were notified (median age 36 months; range: 3 months to 13 years). No special clustering was observed, and the number of AFM cases did not correlate with an increase in the annual rate of AFP notifications. Main prodromal were respiratory symptoms in 21 cases (91.3%) and fever in 18 (78.2%). One or two limbs were affected in 65%; in 35% mechanical ventilation was required. More than 90% had sequelae at discharge. Stool (ST), nasopharyngeal aspirate (NPA) and cerebrospinal fluid (CSF) samples were processed at the Regional Reference Laboratory facilities. RT nested PCR was employed. All detections are shown in Table 1. To note, In 12 cases (53%), EV D68 was detected (11, out of 16 NPA and 3, out of 11 ST samples). As for 2017, only one case of AFM was detected. Attempt of viral detection was unsuccessful. In 2018, 3 cases of AFM were detected, one EV C105, one Coxsackie B and one case without viral detection.ConclusionThe occurrence of AFM cases in Argentina since 2016 is similar to the findings in other countries. An association with EV D68 is apparent, notwithstanding the finding of other EV, finding that further points to the causal association between EV D68 and AFM. As NPA is the sample of choice for AFM diagnosis, from 2019 the work-out of every case of AFP includes this sample as mandatory when AFM is suspected. Given the severity and the high rate of permanent sequelae, a high sensitivity of the health team must be sustained to keep with adequate surveillance, which allows prompt outbreak detection of other agents that can cause AFP in the last phase of polio eradication. Disclosures All authors: No reported disclosures.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.