Evaluating Rectal Artesunate for Management of Childhood Malaria in Ogun State, Nigeria: Machine Learning and Explainable AI (XIA) Approach to Community-Based Acceptability and Safety

• Authors: O. A. Agbeyangi , S. O. Sam-Wobo
• Languages of publication: EN

Abstracts

EN

A community-based study investigated the acceptability, utilization, and barriers to adopting rectal artesunate (Plasmotrim Rectocap 50 and 200 mg) for malaria management among parents of 905 children under five years, 113 Primary Healthcare Practitioners, and 74 Patient Medicine Vendors across 183 rural communities in eight local government areas (LGAs) of Ogun State, Nigeria. Ethical approvals were obtained, and data collection included structured questionnaires and interactive sessions with parents, Primary Healthcare Practitioners, and Vendors to gather demographic data, utilization trends, and perceptions. Data obtained were entered into MS Excel 2016 and analysed using SPSS version 20 to test for an association. Machine learning techniques, including Random Forest, Support Vector Machine (SVM), and Logistic Regression, were applied to analyse data, identify patterns, and optimize predictive modelling. Results showed that 87.6% of parents had not used suppository drugs for malaria treatment, and 100% had not used rectal artesunate for their children, though they expressed universal acceptance (100%), high satisfaction (99.5%), and perceived effectiveness (100%). 87.6% of medical practitioners had not used suppository drugs, and 92.9% had not used rectal artesunate for children. However, 94.7% indicated willingness to adopt it, citing satisfaction (94.7%) and effectiveness (92%). Among vendors, 64.9% had not sold suppository drugs, and 95.9% had not sold rectal artesunate, though 83.9% expressed willingness. Comparative analysis across LGAs revealed variability in utilization (50-80%) and acceptability (65-85%). Machine learning models achieved high predictive performance. Random Forest demonstrated 85% accuracy (AUC: 0.89) for efficacy prediction, SVM achieved 82% accuracy (AUC: 0.86) for utilization prediction, and Logistic Regression showed strong performance for acceptability (78%, AUC: 0.82) and treatment preference (80%, AUC: 0.83). SHAP analysis identified key predictors, including child’s age, socio-economic status, and prior suppository use. Explainable AI (XAI) insights recommended targeted interventions, such as parental education, healthcare worker training, and subsidies to address barriers.

Keywords

EN

Acceptability; Children; Machine Learning; Malaria; Ogun State; Rectal Artesunates; Safety

Discipline

• MEDICAL_BIOLOGY: MEDICAL BIOLOGY

• Publisher: Scientific Publishing House „DARWIN”
• Journal: World News of Natural Sciences
• Year: 2025
• Volume: 60
• Pages: 87-114

Contributors

author

O. A. Agbeyangi

• Department of Public Health, Federal University of Technology Akure, Akure, Ondo State. Nigeria

author

S. O. Sam-Wobo

• Department of Pure and Applied Zoology, Federal University of Agriculture, Abeokuta, Nigeria

References

• [1] Mbishi, J.V., Suleiman, C., Pankras, L., Huda J.O., Heavenlight, A.P., John, A. and Isaac Y.A. 2024. Malaria in under-five children: prevalence and multi-factor analysis of high-risk African countries. BMC Public Health 24: (1687), 1-10
• [2] Awor, P., Kimera, J., Athieno, P, et al. 2022. Acceptability of pre-referral rectal artesunate for severe malaria in children under 5 years by health workers and caregivers in the Democratic Republic of the Congo, Nigeria and Uganda. Malar J 2022, 21: 322
• [3] Hetzel M.W., Okitawutshu J, Tshefu A, et al. 2022. Effectiveness of rectal artesunate as pre-referral treatment for severe malaria in children under 5 years of age:a multi-country observational study. BMC Med 20: 343
• [4] Gomes, M.F., Faiz, M.A. and Gyapong G.O. 2009. Pre-Referral Rectal Artesunate to Prevent Death and Disability in Severe Malaria: A Placebo-Controlled Trial. Lancet, 373: 557-566
• [5] White NJ. 2022. Severe malaria. Malar J. 21(1): 284
• [6] Simba, D.O., Kakoko, D.C., Warsame, M., Premji, Z., Gomes, M.F., Tomson, G. and Johansson E. 2010. Understanding Caretakers’ Dilemma in Deciding Whether or Not to Adhere With Referral Advice after Pre-Referral Treatment with Rectal Artesunate. Malaria Journal, 9: 123
• [7] Brunner N.C., Omoluabi E, Awor P, et al. 2022. Prereferral rectal artesunate and referral completion among children with suspected severe malaria in the Democratic Republic of the Congo, Nigeria and Uganda. BMJ Glob Health 7: e008346
• [8] Sam-Wobo, S.O., Agbeyangi, O.A., Ekpo, U.F. Akinloye, O.A., Mafiana, C.F. and Adeleke, M.A. 2012. Rectal Artesunate, their Utilization and Parental Perception in the Management of Malaria in Children from Abeokuta, South-Western Nigeria. Journal of Vector-Borne and Zoonotic Diseases, 12(2): 151-155
• [9] Ogwu, M.C., Izah, S.C. (2025). Artificial Intelligence and Machine Learning in Tropical Disease Management. In: Technological Innovations for Managing Tropical Diseases. Health Information Science. Springer, Cham, 155–182
• [10] Ibeneme S, Karamagi H, Muneene D, Goswami K, Chisaka N, Okeibunor J. Strengthening Health Systems Using Innovative Digital Health Technologies in Africa. Front Digit Health. 2022, 4: 854339
• [11] Aldoseri A, Al-Khalifa KN, Hamouda AM. Re-Thinking Data Strategy and Integration for Artificial Intelligence: Concepts, Opportunities, and Challenges. Appl Sci (Basel) 2023; 13: 7082
• [12] Vora LK, Gholap AD, Jetha K, Thakur RRS, Solanki HK, Chavda VP. Artificial Intelligence in Pharmaceutical Technology and Drug Delivery Design. Pharmaceutics. 2023; 15: 1916
• [13] Yang C.C. 2022. Explainable artificial intelligence for predictive modeling in healthcare. J. Healthc. Inform. Res. 6: 228-239
• [14] Pawar, U., Shea, D.O., Rea,S., Reilly R.O. 2020. Incorporating Explainable Artificial Intelligence (XAI) to aid the Understanding of Machine Learning in the Healthcare Domain, in: AICS, 169-180
• [15] Subhan A., Filza A., Ali S.I., Zenun K., Sher M.D., Muhammad M. 2023. The enlightening role of explainable artificial intelligence in medical & healthcare domains: A systematic literature review. Computers in Biology and Medicine 166; 107555
• [16] Gupta, G., Khan, S., Guleria, V., Almjally, A., Alabduallah, B. I., Siddiqui, T., Albahlal, B. M., Alajlan, S. A., & AL-subaie, M. (2023). DDPM: A Dengue Disease Prediction and Diagnosis Model Using Sentiment Analysis and Machine Learning Algorithms. Diagnostics, 13(6), 1093
• [17] Nishan MDNH. AI-powered drug discovery for neglected diseases: accelerating public health solutions in the developing world. J Glob Health. 2025;15:03002.
• [18] Alzubaidi L, Zhang J, Humaidi AJ, Al-Dujaili A, Duan Y, Al-Shamma O, et al. Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. J Big Data. 2021; 8: 53
• [19] S. Secinaro, D. Calandra, A. Secinaro, V. Muthurangu, P. Biancone The role of artificial intelligence in healthcare: a structured literature review BMC Med. Inform. Decis. Mak. 21 (2021) 1-23
• [20] Pennisi, F.; Pinto, A.; Ricciardi, G.E.; Signorelli, C.; Gianfredi, V. The Role of Artificial Intelligence and Machine Learning Models in Antimicrobial Stewardship in Public Health: A Narrative Review. Antibiotics 2025, 14, 134
• [21] Inthavilay, S., Franchard, T., Meimei, Y., Ashley, E.A. and Barennes, H. 2010. Knowledge and Acceptability of the Rectal Treatment Route in Laos and Its Application for Pre-Referral Emergency Malaria Treatment. Malaria Journal, 9: 342
• [22] Hirji, K.F., and Premji, Z.G. 2011. Pre-Referral Rectal Artesunate in Severe Malaria: Flawed Trial. Trials, 12: 188
• [23] Phiri TB, Kaunda-Khangamwa BN, Bauleni A, Chimuna T, Melody D, Kalengamaliro H, et al. Feasibility, acceptability and impact of integrating malaria rapid diagnostic tests and pre-referral rectal artesunate into the integrated community case management programme a pilot study in Mchinji district Malar. J Malawi 2016, 21: 15:177
• [24] Mvumbi PM, Musau J, Faye O, Situakibanza H, Okitolonda E. Adherence to the referral advice after introduction of rectal artesunate for pre-referral treatment of severe malaria at the community level: a noninferiority trial in the democratic Republic of the Congo. Malar J. 2019; 18: 438
• [25] Siribie M, Ajayi IO, Nsungwa-Sabiiti J, Sanou AK, Jegede AS, Afonne C, et al. Compliance with referral advice after treatment with prereferral rectal artesunate: a study in 3 sub-Saharan African countries. Clin Infect Dis. 2016; 63: S283-9
• [26] Lambiris M.J., Venga G.N., Ssempala R, et al. 2023. Health system readiness and the implementation of rectal artesunate for severe malaria in sub-Saharan Africa: an analysis of real-world costs and constraints. The Lancet Global Health, Volume 11, Issue 2, e256 - e264
• [27] Cox SN, Guidera KE, Simon MJ, Nonyane BA, Brieger W, Bornman MS, et al. Interactive malaria education intervention and its effect on community participant knowledge: the malaria awareness program in Vhembe district, Limpopo, South Africa. Int Q Community Health Educ. 2018, 38: 147-58
• [28] Lacey Hester, Nityanand Jain, Mai Sugimoto, Masako Shimato, Ieva Reine & Kevin Oria (2023): Combating malaria in Kenya through collaborative population health education: a systematic review and pilot case study. Infectious Diseases, 10: 1-20
• [29] Mgoqo N, Mogane P, Chakane PM. Parents/ caregivers’ perceptions towards use of analgesic suppositories in paediatric elective surgery. Afr J Paediatr Surg 2023, 20, 124-1219
• [30] Lengeler C, Burri C, Awor P, Athieno P, Kimera J, Tumukunde G, et al. (2022) Community access to rectal artesunate for malaria (CARAMAL): A large-scale observational implementation study in the Democratic Republic of the Congo, Nigeria and Uganda. PLOS Glob Public Health 2(9): e0000464
• [31] Bi, A. (2023). Research and application of artificial intelligence in disease prediction. Applied and Computational Engineering, 6(1), 356-363

• Document Type: article