Conectar
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.Sickle cell disease (SCD) poses a significant global health burden, particularly affecting individuals in developing countries with constrained healthcare resources. While research on self-management in the context of SCD is emerging, it has predominantly focused on primary studies, and there is a notable dearth of evidence synthesis on SCD self-management in developing countries. This scoping review aims to identify and map self-management needs of individuals living with SCD, the strategies they employed to meet those needs, and the support systems available to them.
The review will be conducted following the Arksey and O’Malley’s (2005) 29 framework to comprehensively examine the landscape of SCD self-management research. Searches will be performed in PubMed, Scopus, Embase and Dimensions AI, with additional searches in other databases and grey literature. Indexed literature published in English from inception to January 2024 will be included. Reference list from included studies will also be searched manually. Two teams will be constituted to independently screen titles, abstracts and full text against the eligible criteria. Data will be extracted from included studies onto a customised data extraction form.
Ethical approval is not required for this review due to the fact that it synthesises information from available publications. The findings will be disseminated through publication in a peer-reviewed journal. Also, the findings will possibly be presented at relevant international and national conferences. This protocol has already been registered with the Open Science Framework. The study characteristics such as design and setting will be descriptively analysed and presented as graphs, tables and figures. Thematic analysis will also be conducted based on the study objectives and presented as a narrative summary.
Sexual and gender minority (SGM) populations in sub-Saharan Africa (SSA) are disproportionately impacted by HIV and often face multiple HIV-related stigmas. Addressing these stigmas could reduce SGM HIV vulnerability but little is known about how the stigmas operate and intersect. Intersectional stigma offers a lens for understanding the experiences of stigmatised populations and refers to the synergistic negative health effects of various systems of oppression on individuals with multiple stigmatised identities, behaviours or conditions. This review aims to (1) assess how often and in what ways an intersectional lens is applied in HIV-related stigma research on SGM populations in SSA and (2) understand how intersectional stigma impacts HIV risk in these populations.
Scoping review following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis extension for Scoping Reviews.
Public health and regional databases were searched in 2020 and 2022.
Articles in French and English on HIV-related stigma and HIV outcomes among men who have sex with men, women who have sex with women and/or transgender individuals in SSA.
Articles were screened and extracted twice and categorised by use of an intersectional approach. Study designs and stigma types were described quantitatively and findings on intersectional stigma were thematically analysed.
Of 173 articles on HIV-related stigma among SGM in SSA included in this review, 21 articles (12%) applied an intersectional lens. The most common intersectional stigmas investigated were HIV and same-sex attraction/behaviour stigma and HIV, same-sex attraction/behaviour and gender non-conformity stigma. Intersectional stigma drivers, facilitators and manifestations were identified across individual, interpersonal, institutional and societal socioecological levels. Intersectional stigma impacts HIV vulnerability by reducing HIV prevention and treatment service uptake, worsening mental health and increasing exposure to HIV risk factors.
Intersectional approaches are gaining traction in stigma research among SGM in SSA. Future research should prioritise quantitative and mixed methods investigations, diverse populations and intervention evaluation.
FreshRSS 