Vaccine value profile for Hookworm.

Hookworm, a parasitic infection, retains a considerable burden of disease, affecting the most underprivileged segments of the general population in endemic countries and remains one of the leading causes of mild to severe anemia in Low and Middle Income Countries (LMICs), particularly in pregnancy and children under 5. Despite repeated large scale Preventive Chemotherapy (PC) interventions since more than 3 decades, there is broad consensus among scholars that elimination targets set in the newly launched NTD roadmap will require additional tools and interventions. Development of a vaccine could constitute a promising expansion of the existing arsenal against hookworm. Therefore, we have evaluated the biological and implementation feasibility of the vaccine development as well as the added value of such a novel tool. Based on pipeline landscaping and the current knowledge on key biological aspects of the pathogen and its interactions with the host, we found biological feasibility of development of a hookworm vaccine to be moderate. Also, our analysis on manufacturing and regulatory issues as well as potential uptake yielded moderate implementation feasibility. Modelling studies suggest a that introduction of a vaccine in parallel with ongoing integrated interventions (PC, WASH, shoe campaigns), could substantially reduce burden of disease in a cost - saving mode. Finally a set of actions are recommended that might impact positively the likelihood of timely development and introduction of a hookworm vaccine.

Feature importance: Opening a soil-transmitted helminth machine learning model via SHAP.

In the field of landscape epidemiology, the contribution of machine learning (ML) to modeling of epidemiological risk scenarios presents itself as a good alternative. This study aims to break with the "black box" paradigm that underlies the application of automatic learning techniques by using SHAP to determine the contribution of each variable in ML models applied to geospatial health, using the prevalence of hookworms, intestinal parasites, in Ethiopia, where they are widely distributed; the country bears the third-highest burden of hookworm in Sub-Saharan Africa. XGBoost software was used, a very popular ML model, to fit and analyze the data. The Python SHAP library was used to understand the importance in the trained model, of the variables for predictions. The description of the contribution of these variables on a particular prediction was obtained, using different types of plot methods. The results show that the ML models are superior to the classical statistical models; not only demonstrating similar results but also explaining, by using the SHAP package, the influence and interactions between the variables in the generated models. This analysis provides information to help understand the epidemiological problem presented and provides a tool for similar studies.