AGWANG Daphne

Trainee Type:

Masters

Research Topics:

Comparing the performance of conventional statistical models against Machine learning models in predicting the risk of cardiovascular disease among HIV infected Patients at a specialized HIV care clinic in Kampala, Uganda.

Associated Institution:

Wits University, South Africa

Supervisor(s):

Professor David Guwatudde, Dr. Chris Arnold Balwanaki

ORCID ID: 0009-0002-2898-3793

AGWANG Daphne is a passionate Biostatistician and public health researcher with a strong belief in the power of data to improve lives. She holds a Bachelor’s of Science with Education (Maths/Physics) degree from Kyambogo University and is currently pursuing a Master’s degree in Biostatistics at Makerere University School of Public Health which is one of Africa’s leading centre for public health research and innovation.

Her current research focuses on comparing the performance of conventional statistical models against Machine learning models in predicting the risk of cardiovascular disease among HIV infected Patients at a specialized HIV care clinic in Kampala, Uganda. By combining advanced statistical methods with real world health data, Agwang aims to support early detection and enhance patient care strategies.

Beyond her academic pursuits, Agwang is committed to strengthening health systems through evidence-based research and innovation. Her work reflects a deep belief in the power of data to inform policy, drive equitable health interventions, and inspire transformative change across communities.

Outside of her academic work, she enjoys participating in public health outreach programs, and advocating for data-driven decision making in healthcare.

Agweng Fiona

Trainee Type:

Masters

Research Topics:

Spatio-temporal analysis of the influence of climate change on respiratory diseases in Kampala City, Uganda.

Associated Institution:

Makerere University

Supervisor(s):

Dr. Kasasa Simon, Prof. Atuyambe Lynn

ORCID ID: 0009-0009-3301-4824

Agweng Fiona is a graduate of the Master’s program in Biostatistics at Makerere University’s School of Public Health with a strong academic and professional background in public health data analysis and epidemiology. She holds a Bachelor’s degree in Business Statistics from Makerere University and has developed solid expertise in statistical programming and data visualization using R, STATA, Python, GIS, and advanced Microsoft Excel.

She has gained strong professional experience in public health data management and biostatistical analysis through roles with national and district-level health programs, as well as international development partners. As a Data Management Assistant and Biostatistician, she has led the design and implementation of digital data collection systems, strengthened data quality assurance and compliance frameworks, and conducted advanced statistical and spatial analyses to support surveillance, program monitoring, and performance evaluation.

Her current research focuses on a Spatio-temporal analysis of the influence of climate change on respiratory diseases in Kampala City, Uganda, examining how variations in climate and air quality affect the distribution and incidence of conditions such as asthma, COPD, and pneumonia across different urban divisions. This work aims to generate policy-relevant evidence to support climate-sensitive health planning and early warning systems in urban settings.

Amalia Ndamanguluka Katuwapo Muhongo

Trainee Type:

Masters

Research Topics:

Assessing the impact of climate change on public health and development in Africa: a spatial-temporal case study of malaria in Zambezi region, Namibia

Associated Institution:

University of Namibia (UNAM)

Supervisor(s):

Prof Oyedele Opeoluwa

ORCID ID: 0009-0007-9712-1077

Amalia Ndamanguluka Katuwapo Muhongo, a 37-year-old from Namibia, is a Chief Development Planner (Population and Statistics) at the Oshikoto Regional Council. She holds an Honours degree in Applied Statistics and is currently pursuing a Master of Science in Biostatistics at the University of Namibia, and she is grateful for the Master’s fellowship and the opportunity to be part of the SSCAB family, looking forward to collaboration.

Amkela Sheta-Sibanda

Trainee Type:

MSc

Research Topics:

Using Mobile Network Coverage and Routine Health Data to Model Delays in Seeking HIV/ART Care in Rural Sub-Saharan Africa.

Associated Institution:

University of Witwatersrand, South Africa

Supervisor(s):

Prof Tobias Chirwa

ORCID ID: 0009-0003-3284-8110

Amkela Sheta-Sibanda Is an MSc Epidemiology (Biostatistics) fellow under the SSACAB programme fellow at the School of Public Health, University of Witwatersrand. She holds a BSc in Operations Research and Statistics from the National University of Science and Technology (NUST), Zimbabwe, and a Postgraduate Diploma in Monitoring and Evaluation from Lupane State University. She has over two years of postgraduate experience in Monitoring and Evaluation within public health and development settings.

Her professional experience includes data management, analysis, and reporting for donor-funded health programmes, where she has worked with routine health information systems, electronic medical records, and large administrative datasets to support evidence-based decision-making. Her work has focused on improving data quality, analysing key performance indicators, and translating data into actionable insights for programme improvement.

Her research focuses on using mobile network coverage and routine health data to model delays in seeking HIV and antiretroviral therapy (ART) care in rural sub-Saharan Africa. Through the application of epidemiological and biostatistical methods, her work aims to generate evidence to better understand structural and access-related barriers to timely HIV care, with the goal of informing health system planning and targeted interventions in resource-limited settings.

Blessings Chirambo

Trainee Type:

MSc

Research Topics:

Design-Adjusted Analysis of Hierarchical Survey Data: Application to Perinatal Mortality in Malawi

Associated Institution:

University of Malawi, Malawi

Supervisor(s):

Dr. Jupiter Simbeye

ORCID ID: 0009-0009-2259-7649

Blessings Chirambo is a Master of Science in Biostatistics candidate at the University of Malawi. His research focuses on the application of advanced statistical methods for the analysis of complex survey data, with particular emphasis on design-adjusted multilevel modeling of perinatal mortality using nationally representative health survey data from Malawi. Blessings earned his BSc in Applied Statistics from the Catholic University of Malawi. He also holds a BSc in Education (Business Studies) and a Diploma in Statistics from the University of Malawi, as well as a Diploma in Education (Mathematics) from the Catholic University of Malawi.

Prior to and alongside his postgraduate studies, he has worked with national surveys and monitoring activities, gaining practical experience in statistical analysis and data interpretation. He is currently a secondary school teacher under the Ministry of Education, serving at Malindi Secondary School in Zomba. His research interests include survey methodology, multilevel modeling, and applied biostatistics for public health research in low resource settings.

Bongani Ncube

Trainee Type:

MSc

Research Topics:

Mapping hotspots for Type 2 Diabetes Mellitus (T2DM), leveraging spatial statistics and machine learning to uncover critical insights for better healthcare planning

Associated Institution:

University of Witwatersrand

Supervisor(s):

Professor Eustasius Musenge, Professor Tobias Chirwa

ORCID ID: 0009-0000-9624-0786

Bongani is a dedicated data scientist and mathematician, He holds a Bachelor of Science with Honours in Statistics from the University of Zimbabwe.

He brings expertise in statistical modelling and predictive analytics, blending mathematical rigor with real-world applications.

With a keen interest in Bayesian statistics, spatial statistics, and time-to-event studies for health research, Bongani's work focuses on improving lives. His current research explores mapping hotspots for Type 2 Diabetes Mellitus (T2DM), leveraging spatial statistics and machine learning to uncover critical insights for better healthcare planning.

Driven by a passion for education, Bongani actively champions machine learning and statistical learning, especially for newcomers. He adores working with the Tidyverse and Tidymodels in R, making data science not just accessible but also exciting. Through his thoughtful blogs, he demystifies complex concepts and shares his learning journey with a broad audience. Explore his insights and experiences on his website: bongani-ncube.netlify.app.

Brian Masafu

Trainee Type:

MSc

Research Topics:

Assessing the Impact of PCV for Sustaining its Benefits on Pneumococcal carriage and Invasive Disease in Ethiopia

Associated Institution:

KEMRI-Wellcome Trust, Kilifi, Kenya

Supervisor(s):

Dr. John Ojal

ORCID ID: 0000-0003-1537-0146

Brian Masafu is an MSc Research Fellow at KEMRI-Wellcome Trust Research Programme, specializing in statistical and mathematical modeling of infectious diseases. With a background in molecular biology, bioinformatics, and epidemiology, his research focuses on using dynamic transmission models to assess the impact and benefits of introducing the pneumococcal conjugate vaccine (PCV) in the Ethiopian population. By leveraging nasopharyngeal carriage data and mathematical modeling, he provides a cost-effective alternative to resource-intensive surveillance systems for measuring vaccine impact.

His research interests are in Infectious disease Epidemiology, Disease Modelling, vaccinology and Health Policies.

Brian is a proud recipient of the SSACAB II fellowship, which has supported his research endeavors.

Chemutai Nancy Kissa

Trainee Type:

MSc

Research Topics:

Machine learning and artificial intelligence models to predict hypertension occurrence among HIV infected Patients at a specialized HIV care clinic in Kampala, Uganda.

Associated Institution:

Makerere University

Supervisor(s):

Professor David Guwatudde, Dr. Chris Anold Balwanaki

ORCID ID: 0009-0003-2088-4085

Chemutai Nancy Kissa is a passionate Biostatistician and public health researcher with a strong belief in the power of data to improve lives. She holds a Bachelor’s degree in Business Statistics from Makerere University and is currently pursuing a Master’s degree in Biostatistics at the same institution School of Public Health which is one of Africa’s leading centre for public health research and innovation. Her current research focuses on developing machine learning and artificial intelligence models to predict hypertension occurrence among HIV infected Patients at a specialized HIV care clinic in Kampala, Uganda. By combining advanced statistical methods with real world health data, Nancy aims to support early detection and enhance patient care strategies.

Beyond her academic pursuits, Nancy is committed to strengthening health systems through evidence based research and innovation. Her work reflects a deep belief in the power of data to inform policy, drive equitable health interventions, and inspire transformative change across communities. Outside of her academic work, she enjoys participating in public health outreach programs, and advocating for data driven decision making in healthcare.

Emmanuel Guzani

Trainee Type:

MSc

Research Topics:

Modelling Time to Eat Unaided in South East Asian Children with Severe Malaria: A Comparison of Time-to-Event Survival Models.

Associated Institution:

University of Malawi

Supervisor:

Professor Mavuto Mukaka

ORCID ID: 0000-0002-7408-7554

Emmanuel Guzani is a Research Coordinator at the Centre for Development Management Systems (CEDEMAS) with a Master of Science in Biostatistics from the University of Malawi. He has a strong background in statistical science and health systems research, with expertise in survival analysis, impact evaluation, health financing, and public financial management. His research contributions span infectious disease epidemiology, health policy, and non-communicable diseases, supporting evidence-based planning and decision-making in Malawi.

As a 2025 World Bank Government Analytics Fellow, Emmanuel has strengthened his capacity in applied analytics for public sector performance. He has held roles in research coordination, data science, and project data management, where he has led data system development, quality assurance processes, stakeholder engagement, and multi-partner project coordination.

Emmanuel is proficient in advanced statistical and analytical tools including R, Stata, SPSS, Python, SQL, Power BI, and Tableau, as well as digital data collection platforms such as SurveyCTO, ODK, DHIS2, and KoBoToolbox. His work combines rigorous quantitative methods with practical public health applications to inform policy and program implementation.

Evelina Natangwe Sakeus

Trainee Type:

MSc

Research Topics:

Using Machine Learning Approaches to Enhance Population‑Based Prevention and Personalised Treatment of Tuberculosis, Asthma, and Chronic Respiratory Diseases in Namibia.

Associated Institution:

University of Namibia (UNAM)

Supervisor(s):

Prof Lillian Pazvakawambwa

ORCID ID: 0009-0006-9804-909X

Sakeus earned a Bachelor of Science with Honours in Statistics from the University of Namibia in 2019. During her undergraduate studies, she served as a Student Assistant Tutor in the Department of Statistics and Population Studies from July 2016 to October 2018, where her primary responsibility was to tutor first- and second-year students in various statistics modules.

After graduating, Sakeus interned as a Monitoring and Evaluation Officer at the Society for Family Health, a non-governmental organization. Currently, she is pursuing a Master of Science in Biostatistics at the University of Namibia. Her research focuses on using machine learning approaches to improve population-based prevention and personalized treatment for both communicable and non-communicable diseases in Namibia. Through her work, she aims to develop a predictive model that enhances these health strategies.

Felicity Nduku Musau

Trainee Type:

MSc

Research Topics:

Estimating SARS-CoV-2 viral dynamics from cross-sectional viral load distributions from samples collected in Kenya:A retrospective study.

Associated Institution:

Pwani University/KEMRI Wellcome Trust Research, Kenya

Supervisor(s):

Dr George Githinji, Dr Ivy Kombe,Dr Leornard Kiti

ORCID ID: 0009-0000-5534-8117

Felicity is an MSc Statistics student at Pwani University, sponsored by the Sub-Saharan Africa Advanced Consortium for Biostatistics (SSACAB) through the KEMRI–Wellcome Trust Research Programme (KWTRP). She holds a postgraduate diploma in Data Science and Machine Learning from Moringa School and a Bachelor of Science in Mathematics (Statistics) from Pwani University (2022).

Her research focuses on deepening the understanding of SARS-CoV-2 dynamics in Kenya by estimating viral dynamics from cycle threshold (Ct) value distributions. Felicity aspires to apply advanced statistical methods and computational models to conduct impactful research addressing both infectious and non-infectious global health challenges. As an emerging researcher, she is committed to leveraging data-driven approaches to inform policy and improve healthcare outcomes globally.

Fredrick Orwa

Trainee Type:

MSc

Research Topics:

Controlled Interrupted Time Series and traditional regression models to evaluate health policy and applicability to trends affecting infant mortality in Kilifi.

Associated Institution:

Moi University

Supervisor(s):

Professor Ann Mwangi

ORCID ID: 0009-0002-2898-3793

Fredrick Orwa is a Biostatistician and Data Manager with over six years of experience supporting epidemiological, clinical, and public health research across Kenya and Ethiopia. He specializes in statistical modeling, causal inference, and management of complex health datasets, with strong proficiency in R, Stata, SPSS, Python, SQL, REDCap, ODK, and Power BI. His work has contributed to large-scale studies including pneumococcal disease surveillance, vaccine trials, and multi-country data quality systems. Fredrick is currently pursuing an MSc in Biostatistics at Moi University as a Sub-Saharan Africa Consortium for Advanced Biostatistics (SSACAB) Fellow. His research focuses on causal inference methods—particularly controlled interrupted time series—for evaluating public health interventions, with applications in infectious disease epidemiology, maternal and child health, and health policy decision-making.

Houétchénou Gislain Fortuné Dovonou

Trainee Type:

MSc

Research Topics:

Causal and Structural Equation Modeling Applications in Epidemiology: A Systematic Review

Associated Institution:

University of Abomey-Calavi, Benin

Supervisor(s):

Pr. Dr. Ir. Romain L. Glèlè Kakaï

ORCID ID: 0009-0008-9577-1196

Houétchénou Gislain Fortuné Dovonou is a biostatistician trained at the University of Abomey-Calavi (Benin), with research interests in causal inference, structural equation modeling, and the application of advanced statistical methods to infectious disease epidemiology. His work focuses on using modern causal modeling tools to better understand multifactorial disease pathways and to support evidence-based public health decision-making in resource-limited settings.

Previous experience and qualifications: Bachelor’s degree in Agroeconomics, Sociology, and Rural Extension (2022), University of Abomey-Calavi, Benin.

Training and experience in regression modeling, generalized linear and multilevel models, structural equation modeling, and causal inference methods Applied work on malaria and other infectious disease data from surveys and routine surveillance systems.

Isaac Waluke Kundu

Trainee Type

MSc

Research Topic

Natural language processing for mapping free-text medical diagnosis to ICD-11 code

Associated Institution:

University of Nairobi

ORCID ID: 0009-0009-8833-4913

Isaac is a proficient Data Scientist with a strong background in statistics and mathematical analysis. He earned his BSc in Applied Statistics from Kisii University before advancing to an MSc in Mathematical Statistics at the same institution. His academic journey took a remarkable leap when he was awarded the prestigious APHREA-DST scholarship, enabling him to pursue an MSc in Data Science (Public Health) at the University of Nairobi. This opportunity allowed him to refine his expertise in Machine Learning, Deep Learning, and Big Data analytics.

His dedication to research earned him further recognition through a scholarship from the Sub-Saharan Consortium for Advanced Biostatistics Training (SSACAB). This opportunity facilitated his impactful research at KEMRI-Wellcome Trust, where he explored the application of NLP models for mapping free-text medical diagnoses and treatments to their corresponding ICD-11 codes.

With certifications in SPSS, Python, and R, Isaac is highly skilled in leveraging AI to tackle complex challenges. He is driven by the philosophy that "Data is the nutrition of AI," continuously pushing the boundaries of innovation in data science and public health.

Itesiwajuayo Babalola

Trainee Type:

MSc

Research Topics:

Exploring heterogeneity in random effects meta-analysis using finite mixture models

Associated Institution:

University of Pretoria

Supervisor(s):

Prof Samuel Manda, Dr Iketle Maharela

ORCID ID: 0009-0009-3875-8486

Itesiwajuayo Babalola is in their final year of their Master's in Advanced Data Analytics at the University of Pretoria and will soon submit their mini dissertation for final evaluation. Their research interests are in Biostatistics, including Mixture Modelling, Meta-analysis, Survival Analysis, and Competing Risk Analysis. Their highest qualification is an Honours in Mathematical Statistics at the University of Pretoria. They have experience in tutoring first-year students in Statistics. They have experience with R, Python, and SAS. During their final year of Master's, they participated in the 2025 ASA DataFest, held jointly by UP and Wits for the first time in South Africa. Their team came first for providing a well-rounded solution to the given problem using their statistical knowledge and teamwork.

Their mini dissertation topic was "Exploring Heterogeneity in Random Effects Meta-Analysis Using Finite Mixture Models," written under the supervision of Prof Samuel Manda (UP) and Dr Iketle Maharela (UP). Meta-analysis is a statistical approach to summarising results across multiple studies that answer the same question. A main model in meta-analysis is the random-effects (RE) model. This model assumes each study had a true effect size (e.g., odds ratio, risk ratio, etc.) that may be affected by error, and that these true effect sizes follow a single normal distribution. Their research notes a weakness in the RE model's assumption, supported by past literature. It extends the traditional model to account for cases in which the true effects may arise from a combination of distributions rather than a single normal distribution. The extension to the RE model is necessary for proper synthesis and inference in meta-analysis datasets from medical research, since inferences drawn from poor assumptions can lead to misleading conclusions.

Jackline Christopher Mahemba

Trainee Type:

MSc

Research Topics:

Durability of viral load suppression and associated factors among adolescents living with HIV in Tanzania

Associated Institution:

Kilimanjaro Christian Medical University College (KCMC)

Supervisor(s):

Prof. Henry Mwambi, Dr. Innocent B. Mboya

ORCID ID: 0009-0008-3079-9681

Dr. Jackline Christopher Mahemba is a Medical Doctor with strong clinical experience and a growing specialization in public health, epidemiology and data analysis. She holds a Bachelor of Doctor of Medicine and is currently pursuing an MSc. in Epidemiology and Applied Biostatistics at KCMC University, Tanzania.

She has extensive experience in HIV/AIDS program management, including data quality assurance and community outreach coordination. Her previous role as a COVID-19 Data Officer at the Africa Academy for Public Health (AAPH) strengthened her expertise in disease surveillance, reporting and data-driven decision-making.

Dr. Mahemba is highly skilled in STATA, Microsoft Excel and QGIS, with hands-on experience in quantitative data collection, cleaning and analysis.

Her current research, “Durability of viral load suppression and associated factors among adolescents living with HIV in Tanzania,” aims to generate insights that support HIV pandemic elimination efforts. As part of this work, she is particularly focused on demonstrating effective approaches for handling missing data in Tanzania’s large national HIV datasets; further strengthening her path towards becoming a skilled biostatistician.

Joseph Désiré KANDALA

Trainee Type:

MSc

Research Topics:

Assessment of the geographical distribution of determinants of malnutrition in children aged 0 to 59 months in the DRC and modelling using structural equations

Associated Institution:

University of Abomey-Calavi (Benin)

Supervisor(s):

Prof. Dr Romain Lucas GLELE KAKAÏ, Prof. Dr Ngianga Bakwin KANDALA

ORCID ID: 0009-0001-4517-7112

Joseph Désiré KANDALA is currently studying for a master’s degree in Biostatistics at the University of Abomey-Calavi (Benin), thanks to the support of the SSACAB II programme. He holds a degree in Agricultural Engineering in Natural Resource Management from the University of Kinshasa (DRC). With more than 15 years of experience at the Ministry of Environment, Sustainable Development and New Climate Economy (MEDD-NC) in the DRC, he held the position of Head of the Forest Inventory Office at the DIAF (Division of Forest Inventory and Management), where he actively participated in national forest inventory operations (IFN), environmental data analysis and the development of sustainable forest management plans. He also contributed to major initiatives related to climate change mitigation, biodiversity conservation and capacity building for young professionals in the forestry sector. His current areas of interest include statistical modelling, geospatial analysis and resource optimisation. His master’s research topic is entitled: ‘Assessment of the geographical distribution of determinants of malnutrition in children aged 0 to 59 months in the DRC and modelling using structural equations.’

Kiplimo Jepkonga Ann

Trainee Type:

MSc

Research Topics:

Evaluating the Effect of Facility-Based Active Case Finding on Tuberculosis Case Notification in Kenya: Interrupted Time Series and Spatiotemporal Analysis

Associated Institution:

Moi University, Kenya

Supervisor(s):

Prof Ann Mwangi, Dr Charles Mutai

ORCID ID: 0009-0007-3109-108X

Ann holds a bachelor’s degree in applied Statistics with computing passionate about research. She has worked at the Center for Respiratory Disease Research Centre (CRDR)- Kenya Medical Research Centre specializing in clinical trials as a Data Analyst. She has conducted TB prevalence survey for Nairobi County and THANDYS (TB, HIV, and Dysglycaemia), where she contributed to manuscript writing for the initial segment of the THANDYS study.

Currently, she got an opportunity to participate in a short four-month fellowship on infectious disease modelling where is working on this research topic Spatiotemporal Burden of HIV–TB Co-Infection in Kenya: Bayesian Age–Period–Cohort Analysis and Projections to 2035 and the output is to a policy brief.

Kisse Kamwela

Trainee Type:

MSc

Research Topics:

Trends and Predictors of Loss to Follow-Up Among HIV-Exposed Infants Less Than 18 Months in Tanzania

Associated Institution:

Kilimanjaro Christian Medical University College (KCMC)

Supervisor(s):

Dr. Innocent B. Mboya (PhD), Prof Emmanuel Mahande

ORCID ID: 0009-0007-3350-3535

She is a medical doctor and a second-year master’s student in Epidemiology and Biostatistics at KCMC University, with a strong interest in public health research focused on maternal and child health and HIV care. She holds a Doctor of Medicine (MD) degree and has clinical experience within the Tanzanian health system, including HIV care programs, maternal and child health services, and health data reporting.

She is currently strengthening her skills in epidemiology, biostatistics, data analysis, and scientific writing through her Master’s training. Her research examines trends and predictors of loss to follow-up among HIV-exposed infants under 18 months in Tanzania, with the goal of improving retention in PMTCT services and early infant diagnosis and treatment outcomes.

Madalitso Mtika

Trainee Type:

MSc

Research Topics:

Bivariate copula-based survival analysis of age at first birth and first birth interval in Malawi

Associated Institution:

University of Malawi

Supervisor(s):

Dr James Cholombo

ORCID ID: 0000-0002-7021-0199

Madalitso Mtika is a master's student at University of Malawi supported by SSACAB II program, copula survival analysis as a research focus. Earned bachelors of science (mathematics major) degree at Mzuzu university in 2017 and has served as secondary school teacher in government and now as field supervisor at JTI leaf Malawi.

Mashudu Junior Lucky Thagwana

Trainee Type:

MSc

Research Topics:

A simulation study on Bayesian network meta-analysis comparing multiple treatments simultaneously for binary outcomes.

Associated Institution:

University of Pretoria

Supervisor(s):

Prof. Samuel Manda, Dr. Najmeh Nakhaeirad

ORCID ID: 0009-0000-4620-5907

Mashudu Junior Lucky Thagwana holds a Bachelor of Science degree and a Bachelor of Science (Honours) degree in Mathematical Statistics from the University of Pretoria, South Africa. In late 2025, he completed a Master of Science degree in Advanced Data Analytics at the same institution.

His master’s dissertation focused on network meta-analysis (NMA), describing its methodological framework and empirically evaluating the usability of NMA models, with particular emphasis on comparing frequentist and Bayesian modelling approaches. This work extends traditional pairwise meta-analysis by enabling the simultaneous comparison of multiple interventions or treatments, allowing for more comprehensive evidence synthesis.

With a strong foundation in statistical modelling and data-driven methodologies, he has developed a keen interest in advancing analytical techniques for research and applied settings. Under the supervision of Professor Samuel Manda and Dr Najmeh Nakhaeirad of the University of Pretoria, he was inspired by the values of intellectual curiosity, critical thinking, and perseverance, which have played a central role in shaping his development as a researcher.

Memory Makuta

Trainee Type:

MSc

Research Topics:

Assessing Methods for Detecting Outliers in Meta-Analysis

Associated Institution:

University of Malawi

Supervisor(s):

Professor Samuel Manda

ORCID ID: 0009-0007-7601-8257

Memory Makuta holds a Bachelor of Science degree in Mathematical Science and is currently pursuing a Master of Science in Biostatistics at the University of Malawi. She works as a Monitoring, Evaluation, and Learning Specialist at One Acre Fund. With over seven years of experience in quantitative data collection and analysis, she specializes in cleaning and analyzing data using STATA. In her current role, she oversees data collection, manages various projects, leads teams, trains staff on data quality management, and ensures team performance. Memory is passionate about quality data and believes that a well-trained team is essential for accurate data collection. She is also working on a research project titled "Assessing Methods for Detecting Outliers in Meta-Analysis" which involves a simulation study and illustrative examples. In this project, she is evaluating several outlier detection models and comparing their effectiveness in identifying outliers.

MINABA Sêgnimaké Tatiana Carine

Trainee Type:

MSc

Research Topics:

Mediating effects of Non-Vaccine Interventions on Malaria Dynamics: A comparison of Partial Least Squares and Covariance-Based Structural Equation Modeling

Associated Institution:

University of Abomey-Calavi, Benin

Supervisor(s):

Prof. Romain Lucas GLÈLÈ KAKAÏ

ORCID ID: 0009-0002-0571-3395

MINABA Sêgnimaké Tatiana Carine is a biostatistician and data scientist, an SSACAB scholarship recipient, and an ambassador for the Women AI and Data Academy, currently pursuing an MSc in Biostatistics at the University of Abomey-Calavi, Benin. She specializes in statistical modeling and AI applications for public health and infectious diseases. She has led and contributed to several impactful projects, including AI solutions for public service access, water quality assessment, breast cancer prediction, and emergency blood supply coordination. Her current research investigates the mediating effects of non-vaccine interventions on malaria dynamics using Partial Least Squares and Covariance-Based Structural Equation Modeling.

Munyaradzi Ndumeya

Trainee Type:

MSc

Research Topics:

Copula-Driven Feature Selection for High-Dimensional Survival Prediction and Personalised Cancer Treatment in African Genomic Data

Associated Institution:

University of the Witwatersrand, South Africa

Supervisor(s):

Prof Tobias Chirwa, Prof Eustasius Musenge, Dr. Jacob Majakwara (Co-supervisor)

ORCID ID: 0009-0007-0400-1018

Munyaradzi Ndumeya is an MSc fellow in Biostatistics at the University of the Witwatersrand (Wits), supported by the SSACAB program. His research focuses on developing and applying novel Copula-based models and machine learning techniques for highdimensional gene expression data analysis. The project aims to identify significant genetic biomarkers by integrating cluster analysis and dimensionality reduction within an AI framework. The overall objective is enhancing personalised treatment for patients with cancer, as a non-communicable diseases in Africa.

Munyaradzi earned his BSc (Honours) in Mathematical Statistics from the University of the Witwatersrand. He has served as a tutor in the School of Statistics and Actuarial Science at Wits. His primary research interests include copula modelling, machine learning, gene selection and gene expression.

Mwikali Nzau

Trainee Type:

MSc

Research Topics:

Statistical Modeling of the Effectiveness of the Social Health Authority (SHA) and its Impact on Access to Healthcare Services in Nairobi County

Associated Institution:

University of Nairobi, Kenya

Supervisor(s):

Dr. Kamanu

ORCID ID: 0009-0009-0623-109X

Mwikali is an MSc Biostatistics student at the University of Nairobi and a fellow of the SSACAB II programme. She specialises in health systems research, statistical modelling, and evidence-based health policy, focusing on the application of quantitative methods to evaluate health financing mechanisms and improve healthcare access in low- and middle-income countries.

She holds a Bachelor of Science in Economics and Statistics from Kabarak University (2019–2023) and has professional experience as a statistical analyst at the Kitui County Government, where she contributed to economic planning, budgeting, monitoring and evaluation, and data-driven policy analysis.

Proficient in R, Python, SPSS, Excel, and data visualisation tools, Mwikali has developed interactive R Shiny dashboards and professional analytics websites, translating complex data into actionable insights to inform health and policy decision-making.

Nabirye Phiona Milly

Trainee Type:

MSc

Research Topics:

Climate variability on agricultural crop yield and nutritional outcomes among children aged 6-59 months

Associated Institution:

University of Abomey-Calavi, Benin

Supervisor(s):

Prof. Nazarius Mbona, Mr. James Serubugo

ORCID ID: 0009-0004-6940-3286

Nabirye Phiona Milly is a passionate biostatistician and public health researcher with a Bachelors degree in Economics and Statistics from Kyambogo University. She is currently pursuing a Master’s degree in Biostatistics at Makerere University, where her research focuses on the effects of climate variability on agricultural crop yield and nutritional outcomes among children aged 6-59 months.

Phiona is deeply passionate about data and its power to inform evidence based decision making in health and public policy. She believes that well collected and properly analyzed data is essential for understanding complex health challenges, designing effective interventions, and shaping policies that improve population wellbeing. Through her training and experience, she is committed to using data to translate research findings into practical insights that support better health outcomes, equitable resource allocation, and informed policy choices, particularly in low and middle income settings.

She is now keen to build on both her practical experience and advanced statistical training to contribute meaningfully to research in public health, medicine and disease modeling.

Naomi Akitwi

Trainee Type:

MSc

Research Topics:

Using Mobile Network Coverage and Routine Health Data to Model Delays in Seeking HIV/ART Care in Rural Sub-Saharan Africa.

Associated Institution:

University of Nairobi, Kenya

Supervisor(s):

Prof Mwaniki

ORCID ID: 0009-0006-6089-6496

Naomi Akitwi is a data QA/QC and statistical programming professional with 4+ years of experience in data validation, analysis, and reporting. Currently working in carbon data quality assurance, she brings strong expertise in R and SAS, along with a solid foundation in generating statistical datasets and outputs for clinical research. Naomi is detail-oriented, highly analytical, and adept at communicating complex technical results to diverse.

Naomi earned her BSc. in Statistics from University of Nairobi in 2018. Before pursuing her Master’s degree, she worked as a statistical programmer at Phastar Kenya Ltd., where she was responsible for developing, validating, and delivering submission-ready clinical datasets in compliance with regulatory standards. She supported clinical research studies by producing high-quality analysis datasets and statistical outputs, performing independent validations, and ensuring data integrity, traceability, and adherence to industry guidelines. This experience built a strong foundation in clinical data standards, quality control, and regulatory-compliant programming that continues to inform her work today.

Household-Level Carbon Emission Reductions from Stove Transitions: A Paired Sample and Logistic Regression Approach to Estimating Climate Mitigation and Health Co-Benefits in Kenya

Ngongo Moses

Trainee Type:

MSc

Research Topics:

Cardiovascular disease (CVD) risk prediction among people living with HIV (PLHIV) in central Namibia

Associated Institution:

University of Abomey-Calavi, Benin

Supervisor(s):

Prof. Lilian Pazvakavamba, Mr. L. Unandapo

ORCID ID: 0009-0001-2754-0467

Moses earned an Honours degree in Statistics in 2018 and completed a short course in Biostatistics for Health Researchers at Stellenbosch University, South Africa. He has held several data management roles in Namibia, including Data Clerk and Data Consultant, and is currently working as a Statistician. He has also undertaken extensive training in data handling and analysis through both online and in-person programmes in Namibia.

His current research focuses on cardiovascular disease (CVD) risk prediction among people living with HIV (PLHIV) in central Namibia, specifically at Katutura State Hospital and Windhoek Central Hospital. The study aims to compare the performance of traditional statistical models and machine learning approaches in predicting CVD risk. It addresses two main questions: (i) how conventional statistical models compare with machine learning models in predicting CVD risk among PLHIV, and (ii) how risk scores generated by the newly developed predictive model compare with those from the HIV-CARDIO-PREDICT score.

Noel Atyang Papai

Trainee Type:

MSc

Research Topics:

Predicting Time to Treatment Failure in Child Wasting Using Multi-State Markov and Survival Models: Evidence from Tiaty (ASAL), Baringo County

Associated Institution:

University of Nairobi, Kenya

Supervisor(s):

Dr. Linda Adhiambo Musinga

ORCID ID: 0009-0006-3112-9159

Noel is a MEAL professional with experience supporting health and nutrition programmes in humanitarian and development contexts across Kenya, particularly in Arid and Semi-Arid Lands (ASALs). She specializes in health systems strengthening, health information systems, and data-driven decision-making, with strong expertise in applied statistical analysis, epidemiological modelling, and the use of routine and survey data to inform programme performance.

She holds a Bachelor of Science in Statistics and is pursuing a Master of Science in Medical Statistics at the University of Nairobi. Noel has worked with organizations including Save the Children, FHI 360, and Action Against Hunger, leading studies, assessments, and advanced data analytics initiatives.

Her current research applies survival analysis and multi-state Markov models to examine treatment outcomes among children with acute malnutrition in ASAL settings, aiming to generate evidence to improve programme planning, resource allocation, and child wasting management in resource-constrained contexts.

Nontobeko Robin Mnisi

Trainee Type:

MSc

Research Topics:

Blood Pressure Variability And Its Association With Mortality In Rural Northeast South Africa, 2015-2024: A Machine Learning Approach.

Associated Institution:

University of the Witwatersrand

Supervisor(s):

Dr Glory Chidumwa

ORCID ID: 0009-0008-0776-3242

Nontobeko Robin Mnisi is a dedicated data professional with over four years of experience in data administration, analysis, and project management, particularly in the health and research sectors. She holds a BSc in Mathematical Science and a BSc (Honours) in Statistics from the University of Limpopo. Nontobeko has worked with prominent institutions such as the Wits Health Consortium, contributing to impactful projects including the ARK (Agincourt Research Knowledge) initiative.

Her expertise spans data quality control, SQL-based data extraction, health research analytics, and the development of dynamic data dashboards using tools like R and Dash. She is currently engaged in research focused on improving mortality estimation through enhanced verbal autopsy validation, employing machine learning and Bayesian techniques.

Nontobeko is passionate about using statistical methods to drive evidence-based decision-making in public health. She combines technical rigor with a strong commitment to meaningful, community-focused research.

Odhiambo John Andrew

Trainee Type:

MSc

Research Topics:

Gender-Differential Burden of Respiratory & Cardiovascular Diseases from Household and Occupational Air Pollution in Sub-Saharan Africa (2000–2021)

Associated Institution:

University of Nairobi, Kenya.

Supervisor(s):

Prof. Patrick G.O. Weke, Dr. Jasmit Shah

ORCID ID: 0009-0009-2063-3060

Odhiambo John Andrew is a Data Associate at the Brain and Mind Institute, Aga Khan University. He holds a Bachelor’s degree in Mathematical Statistics from the University of Nairobi and is currently in his final year of a Master’s degree in Health Data Science. His research interests lie at the intersection of environmental health, epidemiology, and data science, with a focus on gender-differential health burdens attributable to air pollution in Sub-Saharan Africa. He applies advanced statistical modeling and population health analytics to inform equitable public health policy and climate-health interventions.

Odhiambo has over five years of experience in data analysis and research within public health and development sectors. He has worked with organizations including Aga Khan University, Population Council, Ciheb Kenya, and Compassion International, contributing to epidemiological studies, data management systems, and statistical modeling projects. He is proficient in R, Python, Stata, and advanced quantitative methods, with experience in survival analysis, machine learning, and large-scale health data analysis. His current research examines the gender-differential burden of respiratory and cardiovascular diseases attributable to household and occupational air pollution in Sub-Saharan Africa (2000–2021). The study investigates temporal trends, inequality patterns, and structural determinants influencing disease burden, with the aim of informing equitable environmental health policy and climate-health strategies.

Rashid Shukran

Trainee Type:

MSc

Research Topics:

Leveraging mobile-based symptom tracking and artificial Intelligence for early community -Level detection of Neglected Tropical Diseases (NTDS) in semi-urban Kenya.

Associated Institution:

University of Nairobi, Kenya

Supervisor(s):

Prof Elisha Abade

ORCID ID: 0009-0009-0431-1803

Rashid Shukran is a postgraduate student at the University of Nairobi, pursuing MSc in Public Health Data Science. He holds a BSc Degree in Medical Biochemistry from JKUAT University and has gained practical experience in biomedical research and diagnostic work at KEMRI as well as laboratory diagnostics at Nyumbani Diagnostic Laboratory, Karen. Rashid has a strong interest in applying data-driven and digital health approaches to strengthen disease surveillance, early detection, and evidence-based public health decision-making. He is supported by the SSACAB II Program, which focuses on building advanced capacity in health research and innovation across Sub-Saharan Africa. His academic interests lie at the intersection of public health, data science, and artificial intelligence to address priority health challenges in resource-limited settings.

The research focuses on leveraging mobile-based symptom tracking and artificial intelligence (AI) to enable early community-level detection of Neglected Tropical Diseases (NTDs) in semi-urban Kenya. It addresses persistent challenges of under-reporting and delayed health-seeking behavior associated with diseases such as schistosomiasis, leishmaniasis, and lymphatic filariasis.

The study involves the design and pilot implementation of a mobile and USSD-based reporting platform that allows community members to report symptoms in real time. AI-driven algorithms analyze submitted data to generate predictive alerts for suspected NTD cases, which are validated in collaboration with local health facilities. By integrating digital health innovation with existing health systems, the research aims to strengthen disease surveillance, improve early referral pathways, and enhance community engagement. The work contributes to advancing Kenya’s Universal Health Coverage (UHC) agenda and aligns with the WHO NTD Roadmap 2030.

Surya Nondomè Ludmila AHAMIDE

Trainee Type:

MSc

Research Topic:

Direct and Indirect Effects of Determinants of Malaria Dynamics in West Africa: A Spatial Bayesian Structural Equation Modelling Approach.

Associated Institution:

University of Abomey-Calavi, Benin

Supervisor:

Prof. Romain GLELE KAKAI, Dr. ir. Valère SALAKO

ORCID ID: 0009-0008-5866-4455

Surya Nondomè Ludmila AHAMIDE is an agricultural engineer with a major in Natural Resource Management from the University of Abomey-Calavi, Benin, and a Master’s degree in Biostatistics from the Doctoral School of Agronomic and Water Sciences (ED-SAE). Her early work in agricultural engineering fostered a strong interest in quantitative methods, leading her to specialize in applied statistics. Her engineering thesis, supervised by Professor Romain Glèlè Kakai, focused on species-specific and multi-species allometric models for biomass estimation, with emphasis on the effect of sample size on model accuracy.

Motivated to advance her expertise in statistical modeling, she conducted her Master’s research under Prof. Romain Glèlè Kakai and Dr. Ir. Valère Salako on “Direct and Indirect Effects of Determinants of Malaria Dynamics in West Africa: A Spatial Bayesian Structural Equation Modelling Approach.” Using longitudinal data from sixteen West African countries (2011–2021), she applied Bayesian Spatial SEM to model the interactions of climatic, demographic, socioeconomic, and institutional factors affecting malaria transmission. Her findings highlighted weak health system performance, limited access to sanitation, and structural vulnerabilities as major contributors to malaria burden, demonstrating that malaria persists not only as a vector-borne disease but also as a symptom of deeper systemic challenges.

Her work emphasizes the importance of integrated public health, infrastructural, demographic, and climate-adaptive policies to address malaria sustainably in West Africa.

Sydney Sambo

Trainee Type:

MSc

Research Topics:

Modelling childhood malaria in case study of Liberia (MIS 2022)

Associated Institution:

University of KwaZulu-Natal

Supervisor(s):

Prof Faustin Habyarimana, Shaun Ramroop

ORCID ID: 0000-0003-1817-5311

Sydney Sambo is an aspiring data scientist and emerging biostatistician with a strong foundation in quantitative analysis, research methods, and evidence-based problem-solving. He is currently pursuing a Master of Science in Statistics while gaining practical experience as a Biostatistics and Statistical Programming Intern at Parexel. Previously, he worked as a Data Analyst and Reporting Officer at the Department of Education, contributing to data quality assurance, performance reporting, and dashboard development.

He brings experience in statistical analysis, programming, and data management, including work with clinical trial datasets, SDTM mapping, and regulatory-aligned data standards. He holds a Bachelor of Science degree and is completing a Master’s in Statistics, with additional training in SAS, R, and applied biostatistical methods.

His current research investigates the spatial distribution and determinants of malaria among children under five in Liberia, addressing missing data through multiple imputation and using statistical modelling to identify key predictors of malaria risk. The study aims to provide actionable evidence to inform targeted public health interventions and improve malaria surveillance.

Tebello Karabo Ntene

Trainee Type:

MSc

Research Topics:

Predictive Modelling of disease progression in clinical medicine through a machine learning driven biostatistical framework based on Extreme Values.

Associated Institution:

University of the Witwatersrand, South Africa

Supervisor(s):

Prof Tobias Chirwa

ORCID ID: 0000-0001-8252-3179

Tebello Karabo Ntene holds a bachelor’s degree in Statistics and Economics, complemented by an Honours degree in Risk Analysis. He has since dedicated his academic and professional pursuits to the advancement of health data, cultivating expertise in the management, interpretation, and strategic application of health information systems.

He has served at the Free State Department of Health as a Senior Statistical Advisor in Research, where his work has contributed to strengthening evidence-based decision-making within public health structures. His scholarly interests lie in the rigorous analysis of clinical disease trends as a mechanism for driving targeted clinical interventions and systemic improvements in healthcare delivery.

Notably, he has applied Extreme Value Theory in the analysis of sports performance records and aspires to translate these statistical models into healthcare contexts, with the aim of enhancing risk prediction, outbreak preparedness, and clinical outcome modeling within health systems.

Tiwonge Martha Lungu

Trainee Type:

MSc

Research Topics:

Machine learning approach to predict risk factors of stroke in Malawi

Associated Institution:

University of Malawi

Supervisor(s):

Prof Lawrence Kazembe

ORCID ID: 0000-0002-2344-0397

Tiwonge Lungu is a Biostatistician and educator who recently completed her Master of Science in Biostatistics at the school of applied sciences, University of Malawi (UNIMA), supported by the SACCAB II initiative. Her master’s research focused on using machine learning (classification and tree-based methods) to predict stroke risk factors in Malawi.

She holds a Bachelor of Science degree in Mathematical Sciences Education (specializing Statistics and Computing) and a Master of Science degree in Biostatistics from the University of Malawi. She currently works with the Ministry of education in Malawi specifically as a Mathematics and Computer Studies teacher. She is an aspiring data scientist seeking new opportunities to learn and develop professionally.

She is committed to leveraging data-driven approaches to evaluate and monitor health related projects. While investing into and encouraging young talent to pursue data and technology related fields, she seeks a position to transition into applied biostatistics ensuring hands-on contribution to the field of health data science. She believes that, by combining pedagogical experience with technical skills in data analysis, she can contribute meaningfully to the design implementation of initiatives that improve community health and well-being

Vusumuzi Mabasa

Trainee Type:

MSc

Research Topics:

Multi-Omics Integration for Identifying DNA Methylation-Driven Prognostic Biomarkers in Endometrial Cancer: A Computational Biology Study

Associated Institution:

University of the Witwatersrand

Supervisor(s):

Prof Musenge, Dr Awol Seid Ebrie

ORCID ID: 0000-0002-4423-2204

Vusumuzi Mabasa is a Master’s candidate in Epidemiology (Biostatistics) at the School of Public Health, Faculty of Health Sciences, University of the Witwatersrand. His research focuses on computational and statistical methods for cancer biomarker discovery, with a particular emphasis on multi-omics data integration. His current work investigates DNA methylation–driven prognostic biomarkers in endometrial cancer using large-scale public datasets from The Cancer Genome Atlas (TCGA). Employing advanced bioinformatics pipelines, penalized survival models, and deep learning–based regulatory inference, his research aims to improve molecular risk stratification and prognostic modelling in cancer. His academic interests lie at the intersection of biostatistics, epigenomics, survival analysis, and translational cancer research, with a strong motivation to develop analytically rigorous and reproducible methods relevant to low- and middle-income country settings.

Yamkela L Mayise

Trainee Type:

MSc

Research Topics:

Modelling under-five child mortality in Tanzania including estimation of heterogeneity

Associated Institution:

University of KwaZulu-Natal

Supervisor(s):

Prof. Henry Mwambi

ORCID ID: 0000-0002-6175-5082

Yamkela is a highly skilled statistician and data scientist preparing to pursue a PhD in Biostatistics at the University of KwaZulu-Natal. He holds a multidisciplinary academic background, including a BSc in Data Science (Computer Science and Statistics), an Honours in Statistics, and a Master of Science in Statistics, bridging the gap between theoretical statistics and computational efficiency.

He has extensive experience in tutoring, excelling at making complex statistical concepts accessible to students. His passion for health data was further strengthened during a visit to the University of the Witwatersrand sponsored by SSACAB II, where he advanced his expertise in analyzing health-related datasets, particularly focusing on under-five child mortality. His current research sits at the intersection of advanced statistical methodologies and machine/deep learning, with a focus on high-dimensional survival and longitudinal data to improve prediction of health outcomes over time.