ArticleOne health (Amsterdam, Netherlands)2026
Multi-model large-scale AI framework for avian influenza surveillance and preparedness: Harnessing large language models to enhance risk communication, real-time decision support, and public health response strategies.
Article in One health (Amsterdam, Netherlands), 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Not yet cited in PubMed.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
0 citing papers in PubMed.
No citing paper in PubMed yet.
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
4 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Avian influenza remains a persistent threat to global health security, with serious consequences for food systems, trade, and pandemic preparedness. To address gaps in public health communication and stakeholder-specific decision-making, this study evaluated the capacity of large language models (LLMs) to provide accurate, context-sensitive, and ethically sound guidance in the context of avian influenza. Employing a multi-model, stakeholder-stratified evaluation framework, we tested four advanced generative AI models, namely, ChatGPT-4o (OpenAI), Grok (xAI), Gemini 1.5 Pro (Google), and DeepSeek R1 (DeepSeek), across two complementary tasks: (i) structured querying of 34 domain-specific items covering virological, epidemiological, veterinary, and global public health domains; and (ii) response generation to 16 synthetic vignettes simulating outbreak scenarios involving diverse societal roles. Results showed that Gemini 1.5 Pro demonstrated the highest factual accuracy (91.2% fully correct responses), followed by Grok (85.3%), ChatGPT-4o (82.4%), and DeepSeek R1 (82.4%). Vignette analysis further revealed model-specific communicative strengths and ethical orientations, ranging from procedural pragmatism to stakeholder-mapping and human-centered design. While Gemini excelled in blending empathetic and pedagogical reasoning, Grok offered implementation-oriented guidance, ChatGPT-4o emphasized legal-normative clarity, and DeepSeek R1 favored structural and institutional analysis. Collectively, our findings highlight the promise and limitations of current LLMs as tools for biosurveillance, risk communication, and cross-sectoral pandemic preparedness. They also emphasize the necessity of rigorous, role-aware benchmarking to ensure equitable and contextually appropriate integration of generative AI in public health infrastructures.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.