Why can't Epidemiology be automated (yet)?

2025-07-21

AI Summary

Epidemiological research remains largely manual due to unclear potentials and bottlenecks of AI—especially generative AI—across its methodological pipeline. This study presents the first systematic mapping of generative AI applications across the full epidemiological workflow: literature review, data coding, statistical analysis, manuscript writing, and dissemination. We propose and empirically validate the “agent-based AI system” paradigm: an autonomous framework that designs analytical workflows, orchestrates toolchains for end-to-end execution, and generates complete scholarly manuscripts. Empirical evaluation demonstrates significant gains in coding accuracy and administrative efficiency, with partial end-to-end automation achieved; however, output quality exhibits task- and domain-specific heterogeneity. The study identifies critical limitations—including model reasoning deficits and restricted access to sensitive health data—and underscores bidirectional collaboration between epidemiologists and AI engineers as essential for real-world deployment. Ultimately, it advances a human–AI co-inquiry paradigm for epidemiological science.

Technology Category

• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Philosophy and Ethics of AI: AI & Epistemology
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Recent advances in artificial intelligence (AI) - particularly generative AI - present new opportunities to accelerate, or even automate, epidemiological research. Unlike disciplines based on physical experimentation, a sizable fraction of Epidemiology relies on secondary data analysis and thus is well-suited for such augmentation. Yet, it remains unclear which specific tasks can benefit from AI interventions or where roadblocks exist. Awareness of current AI capabilities is also mixed. Here, we map the landscape of epidemiological tasks using existing datasets - from literature review to data access, analysis, writing up, and dissemination - and identify where existing AI tools offer efficiency gains. While AI can increase productivity in some areas such as coding and administrative tasks, its utility is constrained by limitations of existing AI models (e.g. hallucinations in literature reviews) and human systems (e.g. barriers to accessing datasets). Through examples of AI-generated epidemiological outputs, including fully AI-generated papers, we demonstrate that recently developed agentic systems can now design and execute epidemiological analysis, albeit to varied quality (see https://github.com/edlowther/automated-epidemiology). Epidemiologists have new opportunities to empirically test and benchmark AI systems; realising the potential of AI will require two-way engagement between epidemiologists and engineers.

Problem

• Identify tasks in Epidemiology suitable for AI automation
• Assess limitations of AI in epidemiological research
• Explore AI's role in enhancing research productivity

Innovation

• Generative AI accelerates epidemiological research tasks
• Agentic systems design and execute epidemiological analysis
• AI benchmarks require epidemiologist-engineer collaboration