FreshRSS

🔒
❌ Acerca de FreshRSS
Hay nuevos artículos disponibles. Pincha para refrescar la página.
AnteayerPLOS ONE Medicine&Health

A bilateral filtering-based image enhancement for Alzheimer disease classification using CNN

by Nicodemus Songose Awarayi, Frimpong Twum, James Ben Hayfron-Acquah, Kwabena Owusu-Agyemang

This study aims to develop an optimally performing convolutional neural network to classify Alzheimer’s disease into mild cognitive impairment, normal controls, or Alzheimer’s disease classes using a magnetic resonance imaging dataset. To achieve this, we focused the study on addressing the challenge of image noise, which impacts the performance of deep learning models. The study introduced a scheme for enhancing images to improve the quality of the datasets. Specifically, an image enhancement algorithm based on histogram equalization and bilateral filtering techniques was deployed to reduce noise and enhance the quality of the images. Subsequently, a convolutional neural network model comprising four convolutional layers and two hidden layers was devised for classifying Alzheimer’s disease into three (3) distinct categories, namely mild cognitive impairment, Alzheimer’s disease, and normal controls. The model was trained and evaluated using a 10-fold cross-validation sampling approach with a learning rate of 0.001 and 200 training epochs at each instance. The proposed model yielded notable results, such as an accuracy of 93.45% and an area under the curve value of 0.99 when trained on the three classes. The model further showed superior results on binary classification compared with existing methods. The model recorded 94.39%, 94.92%, and 95.62% accuracies for Alzheimer’s disease versus normal controls, Alzheimer’s disease versus mild cognitive impairment, and mild cognitive impairment versus normal controls classes, respectively.

Anxiety disorders among youth with substance use and associated factors in Northwest Ethiopia: A community-based study

by Mamaru Melkam, Demeke Demilew, Tilahun Kassew, Biruk Fanta, Sewbesew Yitayih, Kassahun Alemu, Yassin Muhammed, Berhanie Getnet, Eden Abetu, Gebrekidan Ewnetu Tarekeg, Mohammed Oumer, Goshu Nenko

Introduction

Anxiety disorder is an unpleasant emotional feeling with symptoms related to psychological and autonomic symptoms such as headache, perspiration, palpitations, dizziness, and stomach discomfort. The use of substances become a worldwide problem among youth which brings situation that leads to serious social and health-related problems. Anxiety disorders with substance use have a huge impact on their high prevalence, therapeutic issues, and poor prognosis on clinical effects. Although the prevalence of anxiety disorders is significant among young people who use substances, limited studies were conducted. Therefore, this study revealed the burden of anxiety disorders among youth with substance use and associated factors in Ethiopia.

Method

A community-based multi-stage with a simple random sampling technique was conducted. A total of 372 substance users study participants were recruited for this study. Alcohol, Smoking, and Substance Involvement Screening Tests, Depression Anxiety Stress Scales, and other tools were used to assess anxiety disorders with substance use and associated factors. Data were entered into Epi-data version 4.6, and exported to SPSS version 20 for further analysis. Bi-variables logistic regression analysis was employed to identify variables with a p-value of Results

From a total of 372 respondents the overall prevalence of anxiety disorders with substance use was 48.1%. Male sex [AOR = 1.99; 95% CI: (1.01–3.93)], low educational status of the father [AOR = 6.38 95%CI: (1.50–7.08)], and the presence of stress [AOR = 2.48; 95% CI: 2.48(2.43–4.40)] were significantly associated factors with anxiety disorders with substances use.

Conclusions and recommendations

The prevalence of anxiety disorders with substance use was 48.1% therefore; it is recommended that the zonal administration give collaborative work with the health bureau and facilitate awareness creation about the impact of substance abuse. Clinicians are recommended to mitigate anxiety disorders with substance use to get a good prognosis for clients with controlling their stress.

Challenges with pediatric antiretroviral therapy administration: Qualitative perspectives from caregivers and HIV providers in Kenya

by Michala Sliefert, May Maloba, Catherine Wexler, Frederick Were, Yvonne Mbithi, George Mugendi, Edward Maliski, Zachary Nicolay, Gregory Thomas, Shadrack Kale, Nicodemus Maosa, Sarah Finocchario-Kessler

Background

Current formulations of pediatric antiretroviral therapy (ART) for children with HIV present significant barriers to adherence, leading to drug resistance, ART ineffectiveness, and preventable child morbidity and mortality. Understanding these challenges and how they contribute to suboptimal adherence is an important step in improving outcomes. This qualitative study describes how regimen-related challenges create barriers to adherence and impact families.

Methods

We conducted key informant interviews (KIIs) with 30 healthcare providers and 9 focus group discussions (FGDs) with a total of 72 caregivers, across three public hospitals in Siaya and Mombasa Kenya. The KIIs and FGDs were audio recorded, translated, and transcribed verbatim. The transcripts were hand coded based on emergent and a-priori themes.

Results

Caregivers discussed major regimen-related challenges to adherence included poor palatability of current formulations, complex preparation, and administration (including measuring, crushing, dissolving, mixing), complex drug storage, and frequent refill appointments and how these regimen-related challenges contributed to individual and intrapersonal barriers to adherence. Caregivers discussed how poor taste led to child anxiety, refusal of medications, and the need for caregivers to use bribes or threats during administration. Complex preparation led to concerns and challenges about maintaining privacy and confidentiality, especially during times of travel. Providers corroborated this patient experience and described how these challenges with administration led to poor infant outcomes, including high viral load and preventable morbidity. Providers discussed how the frequency of refills could range from every 2 weeks to every 3 months, depending on the patient. Caregivers discussed how these refill frequencies interrupted work and school schedules, risked unwanted disclosure to peers, required use of financial resources for travel, and ultimately were a challenge to adherence.

Conclusion

These findings highlight the need for improved formulations for pediatric ART to ease the daily burden on caregivers and children to increase adherence, improve child health, and overall quality of life of families.

MAGA Republicans’ views of American democracy and society and support for political violence in the United States: Findings from a nationwide population-representative survey

by Garen J. Wintemute, Sonia L. Robinson, Elizabeth A. Tomsich, Daniel J. Tancredi

Background

Identifying groups at increased risk for political violence can support prevention efforts. We determine whether “Make America Great Again” (MAGA) Republicans, as defined, are potentially such a group.

Methods

Nationwide survey conducted May 13-June 2, 2022 of adult members of the Ipsos KnowledgePanel. MAGA Republicans are defined as Republicans who voted for Donald Trump in the 2020 presidential election and deny the results of that election. Principal outcomes are weighted proportions of respondents who endorse political violence, are willing to engage in it, and consider it likely to occur.

Findings

The analytic sample (n = 7,255) included 1,128 (15.0%) MAGA Republicans, 640 (8.3%) strong Republicans, 1,571 (21.3%) other Republicans, and 3,916 (55.3%) non-Republicans. MAGA Republicans were substantially more likely than others to agree strongly/very strongly that “in the next few years, there will be civil war in the United States” (MAGA Republicans, 30.3%, 95% CI 27.2%, 33.4%; strong Republicans, 7.5%, 95% CI 5.1%, 9.9%; other Republicans, 10.8%, 95% CI 9.0%, 12.6%; non-Republicans, 11.2%, 95% CI 10.0%, 12.3%; p Interpretation

MAGA Republicans, as defined, are more likely than others to endorse political violence. They are not more willing to engage in such violence themselves; their endorsement may increase the risk that it will occur.

❌