Browsing by Author "Odwee, Jonathan"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Has the HIV/AIDS epidemic changed sexual behaviour of high risk groups in Uganda?
    (African health sciences, 2003) Ntozi, James P. M.; Mulindwa, Innocent N.; Ahimbisibwe, Fred; Ayiga, Natal; Odwee, Jonathan
    Uganda, was the first country in sub-Saharan Africa to reverse its HIV/AIDS epidemic. Long distance drivers, prostitutes and barmaids have been identified as the groups that engage in risky sex, which promotes HIV transmission in Uganda and other countries across the continent. This paper investigates whether and why there were changes of sexual behaviour and practices among five risky groups in Uganda as a consequence of HIV/AIDS epidemic. Methodology The paper is based on data generated from a survey on ‘resistance to sexual behaviour change in the African AIDS epidemic’, which was conducted in the districts of Kabale, Kampala and Lira in 1999. For purposes of this paper, only data from the focus group discussions with high-risk groups have been analysed. These include commercial sex workers, street children, long haul truck drivers, bar maids and adolescents in three towns of Uganda (Kabale, Kampala, Lira). Results indicate that despite the HIV/AIDS epidemic, these groups had only changed their sexual behaviour a little, and they reported to be continuing with multiple sexual partners for a variety of reasons. The adolescents and street children were under peer pressure and a lot of sexual urge; commercial sex workers and bar maids attributed their risky behaviour to the need to survive due to the existing poverty; and the truck drivers reflected on the need for female company to reduce their stress while on the long lonely travels across Africa. Nevertheless, they are all aware and perceive people with multiple sexual partners as being highly vulnerable to contracting HIV and they all reported to have adopted condom use as an HIV preventive strategy. They also observed that married people were at a high risk of contracting HIV due to non-use of condoms in marital relationships and unfaithfulness of spouses. Conclusions Females engage in high-risk sexual relations as a means of economic survival, and perceive their acts as a strategy to improve their socio-economic well being. On the contrary, men in these high-risk categories do such acts out of pleasure and as avenues for attaining fulfilled sexual lives. The search for money among women and the constant desire for men to have sexual pleasure, which are greatly facilitated by their financial status are the forces behind reckless sexual behaviour among high-risk groups.
  • Thumbnail Image
    Item
    Parametric Versus Non-Parametric Models for Predicting Infant Mortality within Communities in Uganda using the 2016 Uganda Demographic and Health Survey Data
    (East African Journal of Health and Science, 2023) Odur, Benard; Nansubuga, Elizabeth; Odwee, Jonathan; Atuhaire, Leonard
    Machine learning techniques have been infrequently used to identify community-based infant mortality risks. Achieving SDG 3 Targets 3.2 and 3.3 could be expedited by early detection of at-risk infants within communities. This study aimed to devise a community-centric algorithm for predicting infant mortality. We analysed UDHS 2016 data containing birth records for 22,635 children born within the five years preceding the survey, excluding those born within a year of the interview date. Twelve machine learning models were evaluated for their predictive capabilities using the area under the receiver operating characteristic curve (AUC ROC) in Python. Data subsets were divided into training and testing sets in a 2:1 ratio. Among the evaluated models, CatBoost showed superior performance with an AUC ROC of 74.9%. The five most influential variables for the CatBoost model were postnatal care utilisation, paternal age, household size, preceding birth interval, and maternal age. While the algorithm’s best performance was achieved using 28 variables, it still exhibited robust predictive power when limited to the top 8 or 10 variables. Hence, CatBoost stands out as an effective tool for identifying community-based infant mortality risks