Health Intervention Evaluation Using Semantic Explainability and Causal Reasoning

Abstract

As serious public health problems require complex responses, health interventions often involve multiple components implemented by groups including policy experts, social workers, and health practitioners. The success or failure of an intervention depends on many different factors, ranging from available resources to characteristics of the targeted public health issue and community to the complex mechanics relating cause and effects of the actions performed. In this paper, we present a novel formal methodology to evaluate public health interventions, policies, and programs. Our method uses the theory of change (TOC) approach along with logic models that define the intervention under consideration to generate a causal diagram and an ontology-based inference model for causal description. The resulting causal diagram will then be compared to existing knowledge and data to determine whether the intervention is coherent, internally consistent and its goals are achievable in the allotted time with the resources provided. The contextual knowledge and semantics provided by the ontology will generate a more explainable, understandable, and trustworthy approach to compare and assess different interventions based on their shared goals. Depending upon the quality and quantity of data available we perform a mix of qualitative and quantitative evaluation of the interventions. This study uses smoking cessation interventions to showcase the proposed methodology in action.