Search

Background: Alzheimer's disease (AD) is a difficult to diagnose pathology of the brain that progressively impairs cognitive functions. Computer-assisted diagnosis of AD based on image analysis is an emerging tool to support AD diagnosis. In this article, we explore the application of Supervised Switching Autoencoders (SSAs) to perform AD classification using only one structural Magnetic Resonance Imaging (sMRI) slice. SSAs are revised supervised autoencoder architectures, combining unsupervised representation and supervised classification as one unified model. In this work, we study the capabilities of SSAs to capture complex visual neurodegeneration patterns, and fuse disease semantics simultaneously. We also examine how regions associated to disease state can be discovered by SSAs following a local patch-based approach., Methods: Patch-based SSAs models are trained on individual patches extracted from a single 2D slice, independently for Axial, Coronal, and Sagittal anatomical planes of the brain at selected informative locations, exploring different patch sizes and network parameterizations. Then, models perform binary class prediction - healthy (CDR = 0) or AD-demented (CDR > 0) - on test data at patch level. The final subject classification is performed employing a majority rule from the ensemble of patch predictions. In addition, relevant regions are identified, by computing accuracy densities from patch-level predictions, and analyzed, supported by Atlas-based regional definitions., Results: Our experiments employing a single 2D T1-w sMRI slice per subject show that SSAs perform similarly to previous proposals that rely on full volumetric information and feature-engineered representations. SSAs classification accuracy on slices extracted along the Axial, Coronal, and Sagittal anatomical planes from a balanced cohort of 40 independent test subjects was 87.5%, 90.0%, and 90.0%, respectively. A top sensitivity of 95.0% on both Coronal and Sagittal planes was also obtained., Conclusions: SSAs provided well-ranked accuracy performance among previous classification proposals, including feature-engineered and feature learning based methods, using only one scan slice per subject, instead of the whole 3D volume, as it is conventionally done. In addition, regions identified as relevant by SSAs' were, in most part, coherent or partially coherent in regard to relevant regions reported on previous works. These regions were also associated with findings from medical knowledge, which gives value to our methodology as a potential analytical aid for disease understanding., Competing Interests: Declaration of competing interest We, Ricardo Mendoza León, John Puentes, Luis Felipe Uriza, and Marcela Hernández Hoyos, the authors of the submitted manuscript entitled “Singleslice Alzheimer's disease classification and disease regional analysis with Supervised Switching Autoencoders”, declare that no conflict of interest or of competing interest exist in relation to this work., (Copyright © 2019 Elsevier Ltd. All rights reserved.)

This study aimed to evaluate the long-term effects of the Kangaroo Mother Care (KMC) intervention on the intellectual and attentional functioning of young adults born with low birth weight. Three hundred infants were randomly assigned at birth in one of two interventions, KMC or traditional care (TC), and completed cognitive tests at adulthood (19-21 years after recruitment). The main results show that participants with a neurological vulnerability at 6 months had higher IQ and sustained attention scores at adulthood if they had received KMC than if they had received TC.

Objective: The protocol for optimal antiplatelet therapy to prevent thrombotic complications following brain aneurysm embolisation is not clear. Our objective is to describe the characteristics of patients presenting with thrombotic or haemorrhagic complications secondary to endovascular treatment., Methods: A cross sectional descriptive study was performed, which included all patients that required endovascular treatment for brain aneurysm at San Ignacio University Hospital from November 2007 to January 2016. Thrombotic and haemorrhagic complications over six months of follow-up were assessed, considering the premedication regimen with antiplatelet agents, location, size of the aneurysm and embolisation technique performed., Results: 122 patients were evaluated, on whom 130 procedures were performed for endovascular treatment of brain aneurysms. Thrombotic complications were more frequent in patients who did not receive premedication (25%) compared to those who did receive an antiplatelet treatment regimen (standard dose 3.87% or loading dose 8.70%), and this difference was statistically significant (P=.043)., Conclusions: Thromboembolic events are the most common complication of brain aneurysm embolisation. Both our study and the literature suggest that the use of dual antiplatelet therapy with aspirin and clopidogrel lowers the rate of symptomatic thromboembolic complications, regardless of the administration protocol., (Copyright © 2017 Sociedad Española de Neurocirugía. Publicado por Elsevier España, S.L.U. All rights reserved.)

Study Objectives: To determine the prevalence of sleep complaints in adults in Colombia at different altitudes., Design: Cross-sectional, population-based and observational study., Setting: Urban areas in three cities (Bogotá, Bucaramanga, Santa Marta) located between 15 and 2640 masl. Subjects Over 18 years old., Interventions: Epworth sleepiness scale (ESS), Pittsburgh sleep quality index (PSQI), Berlin questionnaire, STOP-Bang questionnaire and diagnostic criteria for restless leg syndrome (IRLSSG)., Measurements and Results: The overall prevalence of sleep complaints was 59.6% (CI 95%: 57.3; 61.8%). According to the Pittsburgh scale, 45.3% (CI 95%: 43.0; 47.5) required medical assistance. The Berlin questionnaire indicated that 19.0% (CI 95%: 17.3; 20.8%) had a high risk of sleep apnea (OSA) compared to 26.9% (CI 95%: 24.9; 29.0%) according to STOP-Bang. Among the subjects, 13.7% (CI 95%: 12.3; 15.3%) had excessive daytime sleepiness and 37.7% (CI 95%: 35.5; 39.8%) had a restless leg syndrome. When comparing cities, significant differences in the overall frequency of subjects requiring care were found between Santa Marta (higher frequency) and the other two cities. Differences in sleep problem frequency (Pittsburgh) were observed between Bogota (higher frequency) and Bucaramanga and also between Santa Marta (higher frequency) and the other two cities. The high risk of OSA (STOP-Bang) was different between Bogota (higher frequency) and Bucaramanga and also between Santa Marta (high frequency) and Bucaramanga., Conclusions: We observed a high prevalence of sleep complaints with significant differences among the cities, indicating a need to pay a greater attention to these problems.

Objective: Determine the grade of agreement between the colangiopancreatography by magnetic resonance (CPRM) and the endoscopic retrograde colangio pancreatography (ERCP) in hospitalized patients by biliary lithiasis in a period of time in a reference hospital., Material and Methods: Type of study, retrospective evaluation of diagnostic tool, the size of the sample was calculated from the pilot simple and was 320 patients. We recolected 354 patients that urderwent both studies (CPRM and ERCP), to evaluate the correlation between both procedures we used Kappa variation., Results: 354 pacients were included, 226 women (63.8%), men 128 (36.2%), with mean age of 48 years. There was dilatation of the choledocus by CRMN in 60%, sensibility of 96, 7%, especificity of 40%, Kappa index 0,406 (IC 95%: 0, 32-0, 50) that indicates a moderate agreement. For the presence of choledocus calculi with CPRM was 54%, with sensibility of 72.6%, specificity of 68.3%, Kappa index 0.409 (IC 95%: 0.31-0.51), moderate agreement. For caculi in the gallbladder the kappa index was 0.246 weak. We identify 27% de false negatives for CRMN in detecting choledocusd lithiasis., Conclusions: The CPRM and ERCP had a moderate correlation according to the Kappa index detecting dilatation and choledocus calculi in our patients. The number of false negatives for choledocolithiasis by CPRM leads us to seek in other prospective aleatory studies like endoscopic biliiopancreatic ultrasonopgraphy to compare the CPRM in patients with intermediate probability for choledocolithiasis.