Healthcare workers’ priorities of WHO snakebite strategic objectives for the control and prevention of snakebite envenoming in Ghana: A machine learning statistical design of experiment modeling

Background Snakebite is a severe neglected tropical disease (NTD) that affects 2.5 million people each year, resulting in the deaths of 81,000–138,000 individuals, including rural villagers, agricultural workers, and children. The World Health Organization (WHO) has set strategic objectives to halve the deaths and disabilities caused by snakebite envenoming (SBE) by 2030. This study used innovative research methods, such as the statistical design of experiments and machine learning (ML), to explore health-care workers’ priorities in Ghana regarding the WHO’s strategic objectives for controlling and preventing SBE. The goal was to identify their priority needs to guide the development of a research agenda and relevant interventions or policies that prioritize local needs while aligning with the WHO’s strategic objectives for SBE control and prevention. Method In this cross-sectional study, we employed a MaxDiff statistical design to collect data on the prioritization of the WHO strategic objectives for SBE from 137 healthcare workers in the Kwahu Afram Plains North and South districts of the Eastern Region of Ghana from August to December 2024. We divided the final dataset using a hold-back validation method, maintaining a training-to-validation ratio of 70:30. For data analysis, we utilized a diverse range of five machine learning models: Ridge Regression, Elastic Net, LASSO, a Generalized Regression Model with Pruned Forward Selection, and Forward Selection. To compare the performance of these models, we used several key metrics, including Akaike Information Criterion corrected (AICc), the Bayesian Information Criterion (BIC), the Root Average Squared Error (RASE), negative log-likelihood, and the total time taken to fit each model. Results The Ridge regression model appeared as the best candidate among the ML models used in this study. Its superior predictive performance justifies the computational cost it requires, making it the preferred option for applications that prioritize both predictive performance and computational efficiency. This model consistently predicted key WHO strategic objectives for preventing and controlling SBE. Of the objectives, ‘Ensuring safe and effective treatment’ had the highest priority, followed by ‘Strength-ening health systems’, ‘Empowering and engaging communities’ and ‘Increasing part-nerships, coordination, and resources’. This underscores their order of importance for local initiatives. Therefore, these strategies must be prioritized when designing local policies, relevant interventions, and research agendas. Conclusion By utilizing a MaxDiff statistical experiment design and five machine learning models, participants prioritized the WHO strategic objectives for preventing and controlling SBE in Ghana. Our findings provide essential insights into local policy-making and intervention strategies and for shaping research agendas in Ghana. A local action plan is urgently needed, prioritizing ‘Ensuring safe and effective treatment’ at the community level, followed by ‘Strengthening health systems’, ‘Empowering and engaging communities’, and ‘Increasing partnerships, coordination, and resources’. Prioritizing these strategies in Ghana is crucial for supporting the WHO’s goal of reducing the global SBE burden by 50% by 2030. The success of these strategies hinges on the active involvement of the Ministry of Health and the Ghana Health Service in their implementation at the local level and within the health system.