MSc (Applied Mathematics) / Department of Mathematics and Applied Mathematics / In this study, we develop a multiscale model of soil transmitted helminths in humans with a special reference to hookworm infection. Firstly, we develop a single scale model that comprises of five between host scale populations namely; susceptible humans, infected humans, eggs in the physical environment, noninfective worms in the physical environment and infective worms in the physical environment. Secondly, we extend the single scale model to incorporate within-host scales namely; infective larvae within-host, immature worms in small intestine, mature worm population and within-host egg population which resulted to a multiscale model. The models are analysed both numerically and analytically. The models are epidemiologically and mathematically well posed. Numerical simulation results show that there is a bidirectional relationship between the between-host and within-host scales. This is in agreement with the sensitivity analysis results, we noted that the same parameters that reduce reproductive number R0 are the same parameters that reduce the infective worms endemic equilibrium point. From the comparative effectiveness of hookworm interventions analysis results, we notice that any intervention combination that include wearing shoes controls and reduces the spread of the infection. The modelling framework developed in this study is vigorous to be applicable to other soil transmitted helminths infections / NRF

Neglected tropical diseases are parasitic and bacterial diseases mainly prevalent in developing countries affecting people living in poverty. The World Health Organization’s human rights-based approach emphasizes the “prevention, control, elimination and eradication of neglected tropical diseases” through the use of preventative chemotherapy, such as the mass administration of deworming drugs to improve people’s health.This research paper will take a deeper look at how WHO has been communicating NTDs to make them less ‘neglected’ and how the NTD discourse has been shaping development organizations’ action. In addition, it aims to investigate how successful mass deworming has really been in terms of the recent debate.This study is using a combination of a discourse analysis and qualitative interviews in order to investigate how the NTD discourse and recent initiatives by international organizations have contributed to making NTDs less neglected. It deconstructs representations of the ‘Other’ – the superiority of the ‘West’ over the ‘Rest’ – in relation to the NTD discourse and its inherent power structures. Discourses are analyzed to identify power relations between governments, development organizations, pharmaceutical industries, and recipients of deworming drugs as part of Kenya’s 2013 deworming campaign.The results showed that the NTD discourse has helped raise awareness for NTDs. NTDs and their debilitating effect on populations have been better and more widely communicated, making them less ‘neglected’. WHO and other development organizations’ actions have contributed to making NTDs more visible and have given NTDs higher priority on the global health agenda. Findings from this research study revealed that the ongoing debate has not had a negative impact on international funding. More research and development of a vaccine against NTDs is needed to find more ways to tackle these devastating diseases.

Over one billion people in developing countries are afflicted by parasitic infections caused by soil-transmitted helminths. These infections are treatable with cheap and safe medicine that is widely available. However, diagnosis of these infections has proven to be a bottleneck by the fact that it is time-consuming, requires expensive equipment and trained personnel to be consistent and accurate. This study aimed to investigate the viability and performance of five machine learning models and a 'modular neural network' approach to localize and classify the following parasite eggs in microscopic images: Ascaris lumbricoides, Trichuris trichuria, Hookworm and Schistosoma mansoni. These models were implemented and evaluated on the Nvidia Jetson AGX Xavier to establish that they fulfilled the specifications of 95\% specificity and sensitivity, but also a speed requirement of 40000 images per 24 hours. The results show that R-FCN ResNet101 was the best model produced in this study, which performed the best on average. However, it did not fulfill the specifications entirely but is still considered a success due to being an improvement to the current implementation at Etteplan. Evaluation of the modular neural network approach would require further investigation to verify the performance of the system, but the results indicate it could be a possible improvement to the off-the-shelf machine learning models. To conclude, the study showed that the data and data infrastructure provided by Etteplan has proven to be a very powerful tool in training machine learning models to classify and localize parasite eggs in stool samples. However, expansion of the data to reduce the imbalance between the representations of the classes but also include more patient information could improve the training and evaluation process of the models.