Machine Learning Techniques for Predicting Malaria: Unpacking Emerging Challenges and Opportunities for Tackling Malaria in Sub-saharan Africa

Mbunge, Elliot; Milham, Richard C.; Sibiya, Maureen Nokuthula; Takavarasha, Sam

doi:10.1007/978-3-031-35314-7_30

Cited by 4 publications

References 73 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Utilizing a novel high-resolution malaria dataset for climate-informed predictions with a deep learning transformer model

Pillay,

Minakawa,

Kim

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Climatic factors influence malaria transmission via the effect on the Anopheles vector and Plasmodium parasite. Modelling and understanding the complex effects that climate has on malaria incidence can enable important early warning capabilities. Deep learning applications across fields are proving valuable, however the field of epidemiological forecasting is still in its infancy with a lack of applied deep learning studies for malaria in southern Africa which leverage quality datasets. Using a novel high resolution malaria incidence dataset containing 23 years of daily data from 1998 to 2021, a statistical model and XGBOOST machine learning model were compared to a deep learning Transformer model by assessing the accuracy of their numerical predictions. A novel loss function, used to account for the variable nature of the data yielded performance around + 20% compared to the standard MSE loss. When numerical predictions were converted to alert thresholds to mimic use in a real-world setting, the Transformer’s performance of 80% according to AUROC was 20–40% higher than the statistical and XGBOOST models and it had the highest overall accuracy of 98%. The Transformer performed consistently with increased accuracy as more climate variables were used, indicating further potential for this prediction framework to predict malaria incidence at a daily level using climate data for southern Africa.

show abstract

Utilizing a novel high-resolution malaria dataset for climate-informed predictions with a deep learning transformer model

Pillay,

Minakawa,

Kim

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

Machine Learning Models for Identifying Factors Influencing and Predicting Malaria Among Children Under Five Years in Nigeria

Faremi,

Akinnuwesi,

Mbunge

et al. 2024

2024 Conference on Information Communications Technology and Society (ICTAS)

View full text Add to dashboard Cite

A Graphical User Interface Based on Logistic Regression Approach for Malarial Detection

Kumar,

Sarkar

2024

Preprint

View full text Add to dashboard Cite

Malaria (a mosquito-infected disease) is one of the deadliest communicable diseases in the world. The disease causes a significant global health challenge. According to the World Health Organisation (WHO), millions of deaths occur every year worldwide. The mortality rate poses a challenge to authority and management. Over the years, mathematical and machine learning (ML)-based techniques have been developed to mitigate the scenario. In this study, ML-based prediction techniques are investigated to predict the presence of malaria in individuals. More specifically, three ML-based techniques—Logistic Regression (LR), Support Vector Machine (SVM), and Random Forest (RF)—are employed to differentiate their prediction performance (namely, classification accuracy, precision, recall, and F-score) over a created database (D) consisting of 350 records. Among the adopted techniques, the LR technique shows overall better performance over the test data chosen from D. A graphical user interface (GUI) based on LR is also developed to detect the presence or absence of malaria in any individual.

show abstract

Machine Learning Techniques for Predicting Malaria: Unpacking Emerging Challenges and Opportunities for Tackling Malaria in Sub-saharan Africa

Cited by 4 publications

References 73 publications

Utilizing a novel high-resolution malaria dataset for climate-informed predictions with a deep learning transformer model

Utilizing a novel high-resolution malaria dataset for climate-informed predictions with a deep learning transformer model

Machine Learning Models for Identifying Factors Influencing and Predicting Malaria Among Children Under Five Years in Nigeria

A Graphical User Interface Based on Logistic Regression Approach for Malarial Detection

Contact Info

Product

Resources

About