Data Science Frontiers
Research Seminar in Data Science - Rwanda
The seminar series is focused on both applied and theoretical aspects of data science. On the one hand, it is a place to exchange insights on developments in research and research methodologies; on the other hand, it is a place to discuss how to apply those techniques in order to address development challenges. In particular, talks focus on the following areas:
Applications of machine learning and artificial intelligence
Mathematical approaches to machine learning
Topics in algorithm development and design
Applications of statistics, economics, business, computer science, and engineering using big data and data analytics
Quantum information and related topics
We welcome suggestions for speakers concerning new and exciting developments in both theoretical and applied aspects of data science. If you would like to suggest a speaker, or give us feedback, please get in touch with Molly Mutesi at mmutesi@nexteinstein.org
Next Event
Friday, October 14
Similien Ndagijimana
PREDICTION OF STUNTING AMONG CHILDREN UNDER FIVE AGES IN RWANDA USING MACHINE LEARNING TECHNIQUES
Abstract:
Introduction: Rwanda reported the rate at 33% in 2020. Globally, deaths from malnutrition
stand at 45% of child deaths. According to the World Health Organization's (WHO) goal to
reduce malnutrition by 3.9% per year, all countries must define appropriate strategies. Data
science and machine learning are currently important contributors to predicting and assessing the
outcomes of patients. Hence, developing a model capable of predicting stunting in Rwandan
children is critical, so that the best options for early diagnosis or detection of stunting, as well as
treatment, can be made a policy priority for the community and health services.
Methods: The Rwanda Demographic and Health Survey (RDHS) 2019-2020 was utilized as
secondary data. Using stratified 10-fold cross-validation, different Machine learning classifiers
were trained to predict stunting status. The prediction models were compared using a variety of
metrics, including accuracy, sensitivity, specificity, F1 score, and AUC, and the best model was
chosen.
Results: The Gradient Boosting Classifier developed the best model, revealing that the training
accuracy was 80.49 % based on the performance indicators of several models. Based on the
confusion matrix, the test accuracy, sensitivity, specificity, and F1 were calculated, yielding the
model's ability to classify stunting cases correctly at 79.33%, identify stunted children correctly
at 72.51%, and categorize non-stunted children correctly at 94.49%, with an area under the curve
of 0.89. The model found that the mother's height, television watching, the child's age, province,
mother education, birth weight childbirth size were the most important predictors of stunting
status.
Recommendation: Therefore, machine-learning techniques may be used not only in Rwanda but
also worldwide to construct an accurate model that can detect the early stages of stunting and
offer the best predictive attributes to help in the prevention and control of stunting in Rwandan
children under the age of five.
Mailing List
Sign up here to join our mailing list. As member of the mailing list, you will receive announcements about the upcoming seminar, and details about how to join.
Format
Seminars are held online, the presentations are recorded and videos are made available upon request. If you want to access a recording of one of the seminars, please get in touch with Molly Mutesi at mmutesi@nexteinstein.org . A list of past seminars can be found here, including the talk slides in case the speakers have shared them. All seminars, unless otherwise stated, are held ever second Friday at 14:00 CAT. The invitation will be shared via email. To receive the link, please sign up to our mailing list above.
Organizing Committee
Charles Nzaramyimana (ACE-DS, University of Rwanda) Email: nzaramyimanac@gmail.com
Franca Hoffmann (QLA, AIMS-Carnegie Research Chair in Data Science; Hausdorff Center for Mathematics, University of Bonn, Professor) Email: fhoffmann@quantumleapafrica.org
Kabano Ignace (ACE-DS, University of Rwanda) Email: kabanoignace@gmail.com
Molly Mutesi (QLA, AIMS, Project Coordinator) Email: mmutesi@nexteinstein.org
Chanelle Matadah Manfouo (QLA, AIMS, PhD Student) Email: cmatadah@quantumleapafrica.org
Jennifer Batamuliza (ACE-DS, University of Rwanda, PhD Student) Email: bajelo2000@yahoo.co.uk
Muhammed Semakula (University of Rwanda, PhD Student) Email: semakulam@gmail.com