SMSalule Joseph Masangwi

Salule Joseph Masangwi

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Salule Joseph Masangwi has a total of 29 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Application of Extreme Gradient Boosting to predict NCD-HIV/AIDS comorbidity in young adults in Malawi

    by Ansley Kasambara, Mphatso S. Kamndaya, Salule J. Masangwi, Atupele Mulaga

    The fight to achieve Sustainable Development Goal 3.3 and 3.4 by 2030 requires data driven approaches and appropriate methodologies that would enable sound analyses of data. Non-communicable diseases and the comorbidity of non-communicable diseases and HIV/AIDS are prevalent in Sub-Saharan Africa. However, there is limited data to substantiate the burden in order to arrive at decisions on management and interventions. This study developed a model for prediction of NCD and NCD-HIV/AIDS cases among young adults using a machine learning method. A retrospective study design in which 17741 patient level data was collected from NCD Mastercards. A sub sample of 2763 young adults was selected and a machine learning algorithm was used to develop multiclass models on NCDs only and NCD-HIV/AIDS. Specifically, Extreme Gradient Boosting was used to model classification of NCD as well as NCD-HIV/AIDS cases. The NCD and NCD-HIV/AIDS comorbidity models were developed and classified different cases given patients socio-demographic features. The models performed well with both training and validation loss below 0.5 compared to 0.8 threshold. Metrics for the overall goodness of the models were all above 0.8 indicating particularly good model performance. Accuracy of the NCD only and NCD-HIV/AIDS models were 68% and 84%, respectively. The most influential factors among others for prediction in the NCD only and NCD-HIV/AIDS models were having no intervention (26.8%) and living in a city (45.6%) respectively. The models by the XGBoost algorithm correctly classified non-communicable diseases and NCD-HIV/AIDS comorbidity given a set of socio-demographic factors such as gender, different location aspects and availability of intervention. The models could be deployed and used for basic predictions on suspected individuals given their socio-demographic factors. Furthermore, the socio-demographic factors that significantly influence an individual having a non-communicable disease or NCD-HIV/AIDS would be used to design appropriate interventions to control the increase in the number of new cases.

  • Open Access

    Temporal analysis of non‐communicable diseases and NCD‐HIV/AIDS comorbidity in Malawi: A 4‐year retrospective study 2020–2022

    by Ansley Kasambara, Mphatso S. Kamndaya, Salule J. Masangwi, Atupele Mulaga

    Objective: Non‐communicable diseases are on the increase in the Sub‐Saharan region, which is also the epicentre of HIV/AIDS. There is limited published data on trends and forecasts of the comorbidity of non‐communicable diseases and HIV/AIDS in low‐ and middle‐income countries. Hence, the aim of the study was to examine current trends and forecasts for non‐communicable diseases and non‐communicable disease‐HIV/AIDS comorbidity.Methods: Data on 30,686 patients from 2019 to 2022 were extracted from the non‐communicable diseases Mastercards, from 70 health facilities in Malawi, using a form designed and implemented in KoboToolBox. All cases were aggregated to form weekly counts of non‐communicable diseases and non‐communicable disease‐HIV/AIDS comorbidity and visualised using time series plots. Then the data was subset by the prominent non‐communicable disease, which was hypertension and hypertension‐HIV/AIDS comorbidity weekly counts. Extreme Gradient Boosting (XGBoost), a machine learning model, was used for model fitting, generating predictions, and forecasting.Results: The forecasts showed that the counts of cases per week will range from 137 to 185 cases. Then specifically, hypertension and hypertension‐HIV/AIDS comorbidity case counts averaged approximately within the range of 111–124 new cases per week from 2023 to 2030. The hypertension‐HIV/AIDS comorbidity had forecasts ranging from 2 to 9 new cases per week. Although the number of new case counts per week had a consistent progression, the number of cases was on an increasing trend over time. Therefore, whether cases in general, hypertension and hypertension‐HIV/AIDS comorbidity cases, or hypertension‐HIV/AIDS comorbidity cases, the counts per week imply cumulatively higher case counts.Conclusions: Despite the consistency in the projection to 2030, there is a need to consider the upward trend of these cases and implement intervention measures such as sensitisation to control the number of cases. Otherwise, Malawi may not be able to achieve SDG3 targets by 2030.


  • Open Access

    Care-Seeking for Diarrhoea in Southern Malawi: Attitudes, Practices and Implications for Diarrhoea Control

    by Salule Masangwi, Neil Ferguson, Anthony Grimason, Tracy Morse, Lawrence Kazembe

    This paper examined care-seeking behaviour and its associated risk factors when a family member had diarrhoea. Data was obtained from a survey conducted in Chikwawa, a district in Southern Malawi. Chikwawa is faced with a number of environmental and socioeconomic problems and currently diarrhoea morbidity in the district is estimated at 24.4%, statistically higher than the national average of 17%. Using hierarchically built data from a survey of 1403 households nested within 33 communities, a series of two level binary logistic regression models with Bayesian estimation were used to determine predictors of care-seeking behaviour. The results show that 68% of mothers used oral rehydration solutions (ORS) the last time a child in their family had diarrhoea. However, when asked on the action they take when a member of their household has diarrhoea two thirds of the mothers said they visit a health facility. Most respondents (73%) mentioned distance and transport costs as the main obstacles to accessing their nearest health facility and the same proportion of respondents mentioned prolonged waiting time and absence of health workers as the main obstacles encountered at the health facilities. The main predictor variables when a member of the family had diarrhoea were maternal age, distance to the nearest health facility, school level, and relative wealth, household diarrhoea endemicity, and household size while the main predictor variables when a child had diarrhoea were existence of a village health committee (VHC), distance to the nearest health facility, and maternal age. Most households use ORS for the treatment of diarrhoea and village health committees and health surveillance assistants (HSAs) are important factors in this choice of treatment. Health education messages on the use and efficacy of ORS to ensure proper and prescribed handling are important. There is need for a comprehensive concept addressing several dimensions of management and proper coordination of delivery of resources and services; availability of adequate healthcare workers at all levels; affordability to accessibility of healthcare resources and services to all communities; acceptability and quality of care; intensification of health education messages on the use and management of ORS, and prompt and timely treatment of diarrhoeal illness.


  • Open Access

    The Pattern of Variation between Diarrhea and Malaria Coexistence with Corresponding Risk Factors in, Chikhwawa, Malawi: A Bivariate Multilevel Analysis

    by Salule Masangwi, Neil Ferguson, Anthony Grimason, Tracy Morse, Lawrence Kazembe

    Developing countries face a huge burden of infectious diseases, a number of which co-exist. This paper estimates the pattern and variation of malaria and diarrhea coexistence in Chikhwawa, a district in Southern Malawi using bivariate multilevel modelling with Bayesian estimation. A probit link was employed to examine hierarchically built data from a survey of individuals (n = 6,727) nested within households (n = 1,380) nested within communities (n = 33). Results show significant malaria [ ] and diarrhea [ ] variations with a strong correlation between them [ ] at household level. There are significant malaria [ ] and diarrhea [ ] variations at community level but with a small correlation [ ] between them. There is also significant correlation between malaria and diarrhea at individual level [ 0.241]. These results suggest a close association between reported malaria-like illness and diarrheal illness especially at household and individual levels in Southern Malawi.


  • Knowledge, awareness and practice of the importance of hand-washing amongst children attending state run primary schools in rural Malawi

    by Anthony Martin Grimason, Salule Joseph Masangwi, Tracy Dawn Morse, George Christopher Jabu, Tara Kate Beattie, Steven Elias Taulo, Kingsley Lungu

    A study was undertaken to determine the efficacy of hygiene practices in 2 primary schools in Malawi. The study determined: (1) presence of Escherichia coli on the hands of 126 primary school pupils, (2) knowledge, awareness and hygiene practices amongst pupils and teachers and (3) the school environment through observation. Pupil appreciation of hygiene issues was reasonable; however, the high percentage presence of E. coli on hands (71%) and the evidence of large-scale open defaecation in school grounds revealed that apparent knowledge was not put into practice. The standard of facilities for sanitation and hygiene did not significantly impact on the level of knowledge or percentage of school children's hands harbouring faecal bacteria. Evidence from pupils and teachers indicated a poor understanding of principles of disease transmission. Latrines and hand-washing facilities constructed were not child friendly. This study identifies a multidisciplinary approach to improve sanitation and hygiene practices within schools.


  • Open Access

    Pattern of Maternal Knowledge and Its Implications for Diarrhoea Control in Southern Malawi: Multilevel Thresholds of Change Analysis

    by Salule Joseph Masangwi, Anthony Martin Grimason, Tracy Dawn Morse, Lawrence Kazembe, Neil Ferguson, George Christopher Jabu

    A survey was conducted in Southern Malawi to examine the pattern of mothers’ knowledge on diarrhoea. Diarrhoea morbidity in the district is estimated at 24.4%, statistically higher than the national average at 17%. Using hierarchically built data from a survey, a multilevel threshold of change analysis was used to determine predictors of knowledge about diarrhoeal aetiology, clinical features, and prevention. The results show a strong hierarchical structured pattern in overall maternal knowledge revealing differences between communities. Responsible mothers with primary or secondary school education were more likely to give more correct answers on diarrhoea knowledge than those without any formal education. Responsible mothers from communities without a health surveillance assistant were less likely to give more correct answers. The results show that differences in diarrhoeal knowledge do exist between communities and demonstrate that basic formal education is important in responsible mother’s understanding of diseases. The results also reveal the positive impact health surveillance assistants have in rural communities.


  • Open Access

    Community knowledge variation, bed-net coverage and the role of a district healthcare system, and their implications for malaria control in southern Malawi

    by Salule Masangwi, Anthony Grimason, Tracy Morse, Neil Ferguson, Lawrence Kazembe

    This paper presents data on the pattern of knowledge of caregivers, bed-net coverage and the role of a rural district healthcare system, and their implications for malaria transmission, treatment, prevention and control in Chikhwawa, southern Malawi, using multi-level logistic regression modelling with Bayesian estimation. The majority of caregivers could identify the main symptoms of malaria, that the mosquito was the vector, and that insecticide-treated nets (ITN) could be used to cover beds as an effective preventative measure, although cost was a prohibitive factor. Use of bed nets displayed signifcant variation between communities. Groups that were more knowledgeable on malaria prevention and symptoms included young mothers, people who had attended school, wealthy individuals, those residing closest to government hospitals and health posts, and communities that had access to a health surveillance assistant (HSA). HSAs should be trained on malaria intervention programmes, and tasked with the responsibility of working with village health committees to develop community-based malaria intervention programmes. These programmes should include appropriate and affordable household improvement methods, identifcation of high-risk groups, distribution of ITNs and the incorporation of larval control measures, to reduce exposure to the vector and parasite. This would reduce the transmission and prevalence of malaria at community level.


  • Open Access

    Barriers to maternal health service use in Chikhwawa, Southern Malawi

    by C Kambala, T Morse, S Masangwi, P Mitunda

    Barriers to maternal health service use in Chikhwawa, Southern Malawi


  • Household and community variations and nested risk factors for diarrhoea prevalence in southern Malawi: A binary logistic multi-level analysis

    by Salule Joseph Masangwi, N. S. Ferguson, A. M. Grimason, T. D. Morse, G. Zawdie, L. N. Kazembe

    This paper examines household and community-level influences on diarrhoeal prevalence in southern Malawi. A Bayesian multi-level modelling technique is used in the estimation of hierarchically built data from a survey of individuals nested within households nested within communities. Households have strong unobserved influence on diarrhoeal illness ( = 4.476; 95% CI: 2.081, 6.871). A joint Wald test of significance shows that an individual's age [ ] and school [ ] have strong influence on an individual's diarrhoeal prevalence. An individual's history of malarial-like illness also has a strong positive relationship with diarrhoeal prevalence [β = 0.606, p = 0.000]. Household factors that influence diarrhoea include employment status of head of household [β = −0.619, p < 0.021], maternal age [β = −0.013, p < 0.003], and size of household [β = −0.669, p = 0.000]. The positive relationship between diarrhoea and malaria-like episodes highlights common risk factors hence the need for common approaches to combat the diseases. Significant household effects underline the importance of household considerations in policy issues.