A Scalable Interoperable Data Science System for Trauma-Informed Care: Enhancing ACE Interventions with Real-Time Analytics, AI-Powered Insights, and Clinical Decision Support

Abstract

Adverse Childhood Experiences (ACEs) remain a critical public health challenge, with long-term effects on physical health, mental well-being, and socioeconomic outcomes. Despite ongoing trauma-informed care (TIC) initiatives, existing systems lack integrated, real-time data analytics and accessible decision-support tools for stakeholders. This paper presents the design and development of a scalable, interoperable Data Science Management Application (DSMA) conceptualized for Resilient Georgia to support ACE prevention and TIC implementation. The proposed prototype integrates an interactive visualization dashboard, an AI-powered chatbot for natural-language querying, an ACE risk-tracking tool, and an automated reportgeneration pipeline. The application is developed in a research context, using synthetic and representative datasets to demonstrate the system’s capabilities while preserving data privacy. Preliminary user feedback from domain stakeholders indicates strong perceived usability and relevance, particularly in visualization clarity and natural-language interaction. The system demonstrates the potential to identify regional disparities, improve access to complex data, and support data-driven decision-making. However, the platform has not yet been deployed in real-world settings, and formal quantitative validation of chatbot accuracy, report reliability, and risk assessment performance remains future work. This study contributes a human-centered, AI-enabled framework for scalable public health data systems, providing a foundation for future development, validation, and deployment in traumainformed care environments.