preprint · Preprints.org
A retrospective study of 1,022 snakebite cases treated between January and June 2024 at a specialist hospital in northeastern Nigeria examined patient characteristics and clinical results. Most patients were adult males, with adults making up 62 percent and males 72 percent of the overall cohort. Factors influencing outcomes such as recovery, amputation, tissue debridement, and death included patient age, sex, and the delay between being bitten and presenting at hospital. Men who arrived more than four hours after a bite were identified as the highest-risk group for poor outcomes. Machine learning algorithms, including XGBoost, random forest, and logistic regression, were evaluated to forecast outcomes. The XGBoost model achieved an area under the curve of 0.484 with full patient features and 0.529 with a simplified subset. Although smaller feature sets yielded slight performance gains, further research is required to build robust models.
Snakebite envenoming causes significant mortality and long-term disability in sub-Saharan Africa. Understanding how presentation delays and demographic factors affect recovery helps identify individuals at greatest risk. Demonstrating the feasibility and current limitations of machine learning in resource-limited clinics provides a foundation for developing automated triage systems that can improve antivenom deployment and clinical decision-making in rural hospitals.
This work represents early-stage research into machine learning-driven decision support tools for low-resource healthcare centres. While potential future applications include software to triage snakebite patients and guide antivenom distribution, the current models demonstrate low predictive accuracy. Substantial further data collection, algorithmic refinement, and clinical validation are required before any operational diagnostic software can be developed.
AI-generated from the published abstract. Always read the original work before citing.
The Snakebite Treatment and Research Hospital (SBTRH) is a leading center for snakebite envenoming care and research in sub-Saharan Africa, treating over 2,500 snakebite patients annually. Despite routine data collection, routine analyses are seldom conducted to identify trends or guide clinical practices. This study retrospectively analyzed 1,022 snakebite cases at SBTRH from January to June 2024. Most patients were adults (62%) and were predominantly male (72%). Key factors such as age, sex, and time between bite and hospital presentation were associated with outcomes, including recovery, amputation, debridement, and death. Adult males who took more than four hours to arrive to hospital were identified as a high-risk group for poor outcomes. Using patient characteristics, an XGBoost model was developed, which achieved an area under the received-operator curve (AUROC) of 0.484 with all patient characteristics, and 0.529 when using a simplified subset of characteristics. Model performance was compared to random-forest and logistic regression models. In general, for all models, performance tended to increase slightly when using a simplified set of features, which may be of significance to resource-limited settings like SBTRH, however, more research is needed to build more robust models. These findings underscore the need for targeted interventions for high-risk groups, optimization of antivenom administration strategies and integration of machine learning-driven decision support tools in low-resource-limited clinical settings.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.20944/preprints202501.1652.v1
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
