Artificial intelligence in critical synthesis of public health responses to violence: A novel application to UK violence prevention policy

OBJECTIVES: Artificial intelligence (AI) systems are increasingly applied in public health, yet their use for analysing fragmented, multi-sectoral policy landscapes remains underdeveloped. This study aimed to describe the development and preliminary exploration of an AI-enabled tool designed to synthesise evidence from violence-related policy documents in the UK. STUDY DESIGN: An exploratory, proof-of-concept case study. METHODS: A corpus of publicly available UK policy and strategy documents on violence (N = 343) was compiled through expert review, manual searches of government and third sector organisation websites, and automated web scraping. We used the corpus to train an existing AI framework and deployed it through a question-answer interface. Stakeholders were invited to pose natural-language questions about violence policy and consider the system's utility and the usefulness of its outputs. RESULTS: Stakeholders reported that the AI-enabled tool facilitated flexible interrogation of violence-related policy documents and supported identification of recurring framings, sectoral differences, and potential policy siloes. Feedback indicated that the system improved the efficiency and transparency of cross-sectoral policy analysis, particularly in the initial stages of an inquiry. CONCLUSIONS: This short communication provides early insight into the potential of AI-enabled tools to support public health policy analysis by structuring and synthesising complex documentary evidence. Such functionality is particularly relevant in areas requiring cross-sectoral collaboration. Further work is required to formally evaluate performance, assess bias, and explore impacts of AI on real-world decision-making prior to wider implementation.