Submission ID 118456
| Issue/Objective | : Sub-Saharan Africa region (SSA) is disproportionately affected by Antimicrobial Resistance (AMR), accounting for approximately 23.5 deaths per 100,000 people in the area. Antimicrobial resistance is projected to grow to over 4 million mortality rate per annum in Sub-Saharan Africa by 2050 if left unchecked and would account for 40% of global antimicrobial resistance mortality. This public health burden of antimicrobial resistance is worsened by feeble healthcare status in the region, characterized by poor healthcare infrastructures, weak AMR surveillance system, and lack of access to essential medicines. However, this study aims to investigate the feasibility and scalability of annexing machine learning in AMR surveillance systems in SSA. |
|---|---|
| Methodology/Approach | : A comprehensive search of keywords " machine learning " , " antimicrobial resistance ". " surveillance system", " feasibility " "scalability" , and " sub-Saharan Africa" were inserted into GOOGLE , PUBMED , WEB OF SCIENCE , and COCHRANE LIBRARY databases Besides, only the most relevant papers to the aims of the study were thoroughly reviewed and included in the final result. |
| Results | : the study showed that the incorporation of machine learning (ML) into antimicrobial resistance (AMR) surveillance systems in sub-Saharan Africa (SSA) presents both benefits and challenges. However, factors like data scarcity, and infrastructure limitations coupled with ethical concerns may hinder the successful implementation of the ML AMR surveillance system in the area. The study also showed that Scaling machine learning solutions is complicated by the region's heterogeneous healthcare system and disparate degrees of technological development thereby making it difficult to integrate and expand these technologies, even if machine learning (ML) can process and analyze enormous volumes of data rapidly. However, the study suggests possible factors that facilitate the successful integration of ML in AMR surveillance systems in SSA, and these include Comprehensive Data Collection, Interdisciplinary Collaboration, Ethical Frameworks, and Infrastructure Development. |
| Discussion/Conclusion | : In sub-Saharan Africa, incorporating machine learning into AMR surveillance systems has enormous potential to enhance public health outcomes. However, overcoming obstacles about infrastructure, data availability, and ethical issues is necessary to realize this potential. |
| Presenters and affiliations | Quadri FOLORUNSO OBAFEMI AWOLOWO UNIVERSITY,OAU ,ILE -IFE ,OSUN STATE ,NIGERIA Quadri FOLORUNSO OBAFEMI AWOLOWO UNIVERSITY,OAU ,ILE -IFE ,OSUN STATE ,NIGERIA |
