Explainable Artificial Intelligence in Multimodal Malaria Prediction: A Systematic Review and Roadmap Integrating Climate Change, Parasite Genomics, and Public Health Decision Support
DOI:
https://doi.org/10.30871/jaic.v10i2.12347Keywords:
Explainable Artificial Intelligence, Multimodal Machine Learning, Malaria Prediction, Climate Change and Health, Parasite Genomics, Causal Artificial Intelligence, Computational Epidemiology, Interpretable Machine Learning, Public Health Decision SupportAbstract
Malaria remains a persistent global public health burden, particularly in sub-Saharan Africa, requiring predictive systems that are both accurate and clinically interpretable. Although artificial intelligence (AI) has significantly improved malaria forecasting and diagnosis, real-world deployment remains constrained by opaque “black-box” decision pathways and fragmented modelling approaches that analyse climatic, genomic, and clinical drivers in isolation. This systematic review synthesises contemporary evidence on Explainable Artificial Intelligence (XAI) applications in malaria prediction, integrating climate vulnerability and parasite genomic insights. The review was conducted and reported in accordance with PRISMA 2009 guidelines. Four databases (PubMed, IEEE Xplore, SpringerLink, and ScienceDirect) were systematically searched, yielding 161 records; 12 studies published between 2020 and 2025 met the inclusion criteria. The restricted timeline reflects the recent surge in model-agnostic interpretability methods such as SHAP and LIME. Findings indicate that ensemble learning models, particularly Random Forest and XGBoost, demonstrate robust predictive performance and strong post hoc interpretability in climate-driven and clinical forecasting contexts. In contrast, deep learning architectures, including Convolutional Neural Networks and Transformers, excel in image-based and genomic classification tasks but require interpretability overlays to mitigate opacity. Despite methodological advances, Causal AI remains underutilised, limiting current models' capacity to simulate intervention scenarios and inform policy decision-making. Furthermore, no fully unified multimodal framework that integrates climatic, genomic, and clinical features into a single explainable architecture was identified. This review not only synthesises trends in algorithmic performance and interpretability but also establishes a strategic roadmap for developing unified, policy-integrated multimodal XAI systems that support transparent malaria risk prediction amid accelerating climate change and parasite evolutionary dynamics.
Downloads
References
[1] D. I. Stanisic and M. F. Good, “Malaria Vaccines : Progress to Date,” BioDrugs, vol. 37, no. 6, pp. 737–756, 2023, doi: 10.1007/s40259-023-00623-4.
[2] B. Traoré, O. Koutou, and B. Sangaré, “A global mathematical model of malaria transmission dynamics with structured mosquito population and temperature variations,” 2020, doi: 10.1016/j.nonrwa.2019.103081ï.
[3] D. G. P, S. T, Woods W, S. N, and Potere, “Climate impacts on Malaria in Africa,” New Sci., vol. 205, no. 2752, p. 24, 2024.
[4] J. Li, H. Jean, D. David, F. Khrystyna, and P. Lei, “Current Status of Malaria Control and Elimination in Africa : Epidemiology , Diagnosis , Treatment , Progress and Challenges,” pp. 561–579, 2024.
[5] K. Chinemerem et al., “Economic burden of malaria on developing countries : A mini review,” Parasite Epidemiol. Control, vol. 30, no. May, p. e00435, 2025, doi: 10.1016/j.parepi.2025.e00435.
[6] S. Rajab, J. Nakatumba-Nabende, and G. Marvin, “Interpretable Machine Learning Models for Predicting Malaria,” 2023 2nd Int. Conf. Smart Technol. Syst. Next Gener. Comput. ICSTSN 2023, pp. 1–6, 2023, doi: 10.1109/ICSTSN57873.2023.10151538.
[7] WHO, World malaria World malaria report report. 2024.
[8] A. S. Faremi et al., “Machine Learning Models for Identifying Factors Influencing and Predicting Malaria Among Children Under Five Years in Nigeria,” 2024 Conf. Inf. Commun. Technol. Soc. ICTAS 2024 - Proc., pp. 88–94, 2024, doi: 10.1109/ICTAS59620.2024.10507142.
[9] R. L. Spreng et al., “Identification of RTS,S/AS01 vaccine–induced humoral biomarkers predictive of protection against controlled human malaria infection,” JCI Insight, vol. 9, no. 19, pp. 1–17, 2024, doi: 10.1172/jci.insight.178801.
[10] M. S. Rahman and M. A. B. Shiddik, “Unraveling global malaria incidence and mortality using machine learning and artificial intelligence–driven spatial analysis,” Sci. Rep., vol. 15, no. 1, pp. 1–11, 2025, doi: 10.1038/s41598-025-12872-0.
[11] A. Johannssen and N. Chukhrova, “The crucial role of explainable artificial intelligence (XAI) in improving health care management,” Health Care Manag. Sci., pp. 1–6, 2025, doi: 10.1007/s10729-025-09720-y.
[12] T. Fisher, S. Rojas-Galeano, and D. Fernandez-Reyes, “Specialist hybrid models with asymmetric training for malaria prevalence prediction,” Front. Public Heal., vol. 11, no. 3, 2023, doi: 10.3389/fpubh.2023.1207624.
[13] P. Jain, J. Meena, P. Pandey, Vidisha, P. Shelke, and V. K. Gupta, “A New Era of Malaria’s Disease Control using AI-Driven Predictive Models,” Proc. - 3rd Int. Conf. Adv. Comput. Comput. Technol. InCACCT 2025, pp. 455–461, 2025, doi: 10.1109/InCACCT65424.2025.11011356.
[14] M. Learning et al., “The Indonesian Journal of Computer Science,” vol. 14, no. 2, pp. 2357–2386, 2025.
[15] W. Deelder, E. Manko, J. E. Phelan, S. Campino, L. Palla, and T. G. Clark, “Geographical classification of malaria parasites through applying machine learning to whole genome sequence data,” Sci. Rep., vol. 12, no. 1, pp. 1–10, 2022, doi: 10.1038/s41598-022-25568-6.
[16] D. K. Muriithi, V. W. Lumumba, O. O. Awe, and D. M. Muriithi, “An Explainable Artificial Intelligence Models for Predicting Malaria Risk in Kenya,” Eur. J. Artif. Intell. Mach. Learn., vol. 4, no. 1, pp. 1–8, 2025, doi: 10.24018/ejai.2025.4.1.47.
[17] D. Nsanzabandi and P. Nizeyimana, “Enhancing Malaria Incidence Prediction Using Weather Variables: A Comparative Study of Gradient Boosting and Random Forest Regression Models,” 2024 IEEE SmartBlock4Africa Emerg. Resilient Technol. Build. Secur. African Nations, SmartBlock4Africa 2024, pp. 1–10, 2024, doi: 10.1109/SmartBlock4Africa61928.2024.10779551.
[18] L. Mpofu, B. Ndlovu, S. Dube, M. Muduva, F. Jacqueline, and K. Maguraushe, “Predictive Model for Hospital Readmission of Diabetic Patients,” 2024, doi: 10.46254/af05.20240252.
[19] M. Sibindi et al., “A Predictive Model for Personalized Healthcare Management for Patients with Chronic Diseases,” 2024, doi: 10.46254/EU07.20240164.
[20] I. Murere, B. Ndlovu, S. Dube, and M. Muduva, “Comparative Analysis of Machine Learning Techniques for Predicting Diabetes,” vol. 2030, no. Mozaffarian 2020, 2024, doi: 10.46254/EU07.20240073.
[21] A. M. G. Alhejaily, “Artificial intelligence in healthcare (Review),” Biomedical Reports, vol. 22, no. 1. Spandidos Publications, 2025, doi: 10.3892/br.2024.1889.
[22] B. Ncube, M. Dzikiti, A. Nyoni, M. Ncube, and B. M. Ndlovu, “Effectiveness of Machine Learning algorithms in predicting Monkey Pox ( Mpox ): A Systematic Literature Review,” 2024, doi: 10.46254/EU07.202400.
[23] K. H. de C. Monteiro et al., “Integrating machine learning and spatial clustering for malaria case prediction in Brazil’s Legal Amazon,” BMC Infect. Dis., vol. 25, no. 1, 2025, doi: 10.1186/s12879-025-11193-x.
[24] G. V. C. Sekhar and C. Alemu, “Comparative analysis of machine learning models for malaria detection using validated synthetic data: a cost-sensitive approach with clinical domain knowledge integration,” Sci. Rep., vol. 15, no. 1, pp. 1–13, 2025, doi: 10.1038/s41598-025-10231-7.
[25] M. T. Pillay et al., “Utilizing a novel high-resolution malaria dataset for climate-informed predictions with a deep learning transformer model,” Sci. Rep., vol. 13, no. 1, pp. 1–15, 2023, doi: 10.1038/s41598-023-50176-3.
[26] S. H. Cherif, Z. A. Elaouaber, L. F. Kazi Tani, A. Gaouar, and T. Taleb, “Enhanced Malaria Detection Using Convolutional Neural Networks with SHAP and LIME for Model Interpretability,” PAIS 2025 - Proceeding 7th Int. Conf. Pattern Anal. Intell. Syst., pp. 1–5, 2025, doi: 10.1109/PAIS66004.2025.11126471.
[27] O. O. Awe, P. N. Mwangi, S. K. Goudoungou, R. V. Esho, and O. S. Oyejide, “Explainable AI for enhanced accuracy in malaria diagnosis using ensemble machine learning models,” BMC Med. Inform. Decis. Mak., vol. 25, no. 1, p. 162, Apr. 2025, doi: 10.1186/s12911-025-02874-3.
[28] B. Ndlovu, K. Maguraushe, and O. Mabikwa, “Machine Learning and Explainable AI for Parkinson’s Disease Prediction: A Systematic Review,” Indones. J. Comput. Sci., vol. 14, no. 2, 2025, doi: https://doi.org/10.33022/ijcs.v14i2.4837.
[29] R. Agrawal, T. Gupta, S. Gupta, S. Chauhan, P. Patel, and S. Hamdare, “Fostering trust and interpretability: integrating explainable AI (XAI) with machine learning for enhanced disease prediction and decision transparency,” Diagnostic Pathol. , vol. 20, no. 1, 2025, doi: 10.1186/s13000-025-01686-3.
[30] S. S. Sibanda and B. Ndlovu, “Explainable Transformer and Machine Learning Models in Predicting Tuberculosis Treatment Outcomes . A Systematic Review,” J. Appl. Informatics Comput., vol. 10, no. 1, pp. 150–164, 2026,doi: 10.30871/jaic.v10i1.11846.
[31] T. Ngwazi and B. Ndlovu, “Early Detection of Diabetic Retinopathy Through Explainable AI Models : A Systematic Review,” Int. J. Informatics Dev., vol. 14, no. 2, pp. 616–628, 2025, doi: 10.14421/ijid.2025.5200.
[32] O. Mabikwa, B. Ndlovu, and K. Maguraushe, “A Comparative Analysis of Machine Learning Techniques and Explainable AI on Voice Biomarkers for Effective Parkinson ’ s Disease Prediction,” vol. 7, no. 3, pp. 2196–2228, 2025, doi: 10.51519/journalisi.v7i3.1172.
[33] M. A. De Cola et al., “Impact of seasonal malaria chemoprevention on prevalence of malaria infection in malaria indicator surveys in Burkina Faso and Nigeria,” BMJ Glob. Heal., vol. 7, no. 5, pp. 1–11, 2022, doi: 10.1136/bmjgh-2021-008021.
[34] H. Chamboko and B. Ndlovu, “Twitter ( X ) Sentiment Analysis on Monkeypox : A Systematic Literature Review,” vol. 14, no. 2, pp. 629–639, 2025, doi: 10.14421/ijid.2025.5196.
[35] M. J. Page et al., “The PRISMA 2020 statement: an updated guideline for reporting systematic reviews,” 2021, doi: 10.1136/bmj.n71.
[36] C. Rotejanaprasert et al., “Projecting malaria elimination in Thailand using Bayesian hierarchical spatiotemporal models,” Sci. Rep., vol. 13, no. 1, pp. 1–11, 2023, doi: 10.1038/s41598-023-35007-9.
[37] S. S. Yadav, V. J. Kadam, S. M. Jadhav, S. Jagtap, and P. R. Pathak, “Machine learning based malaria prediction using clinical findings,” 2021 Int. Conf. Emerg. Smart Comput. Informatics, ESCI 2021, no. Lmm, pp. 216–222, 2021, doi: 10.1109/ESCI50559.2021.9396850.
[38] S. Hadebe, B. Ndlovu, and K. Maguraushe, “Managing Diabetes Using Machine Learning and Digital Twins,” Indones. J. Innov. Appl. Sci., vol. 5, no. 2, pp. 145–162, 2025, doi: 10.47540/ijias.v5i2.1981.
[39] O. T. Chikumo and B. Ndlovu, “Transformer-based Models for Cardiovascular Disease Predictions from Electronic Health Records : A Systematic Review,” J. Appl. Informatics Comput., vol. 10, no. 1, 2026, doi:10.30871/jaic.v10i1.11899.
[40] J. Machemedze and B. Ndlovu, “Transformer-Based Models for Electronic Health Records and Omics in Healthcare : A Systematic Literature Review,” J. Appl. Informatics Comput., vol. 10, no. 1, pp. 90–105, 2026,doi: 10.30871/jaic.v10i1.11893.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Nalenhle Ndlovu, Belinda Ndlovu
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
