EpiLens links outbreak studies to help track epidemiology data
EpiLens: Lightweight RAG for Epidemiological Knowledge Acquisition
Computation and LanguageDigital Libraries
Summary
Scientists need to understand what studies exist and the data they use to prepare for outbreaks like COVID or mpox. Mapping all related studies by hand is slow, and AI alone can make mistakes in naming sources. The authors created EpiLens, a tool that quickly organizes many papers, classifies them, and links findings to exact parts of the original documents. EpiLens works without special training data and can group studies by disease and what they estimate, like how easily a virus spreads or how deadly it is.
What this means in practice
- •For public health data teams: Organize and classify outbreak-related research papers by parameter type to improve data tracking and reporting during epidemics.
- •For medical knowledge managers: Link epidemiological estimates directly to source documents to support rapid data validation and literature review.
Authors
Vincenzo Perri, Ciro Cattuto, Daniela Paolotti
Abstract
To prepare for future outbreaks, researchers need to know what studies have been done and what data they use. Mapping a large literature by hand is slow, while large language models alone can misstate or conflate sources. We present EpiLens, a lightweight, open-source retrieval-augmented generation package that applies a fixed retrieval template and output schema to every paper in a corpus and links outputs to source passages. We build a corpus of 2,297 papers from the sources of a multi-pathogen parameter study and evaluate EpiLens's paper-classification workflow against 214 manually labelled papers. Without task-specific training data, the classifier matches or exceeds the tested supervised and zero-shot baselines across four tasks. The study's early extraction sheets cite published sources for 327 estimates. We link each estimate to a cited document or to corpus studies included by a review. Then, we use the classifier's labels to compare the papers associated with different parameters and pathogens. EpiLens labels more papers linked to reproduction numbers than fatality risks as model-based (54% versus 22%, compared with 62% versus 24% in the manual labels). The gap is consistent with the frequent use of transmission models to estimate reproduction numbers and persists within each of five pathogens compared. Beyond the contrast between parameters, the model-based share of papers linked to incubation-period estimates differs by pathogen: 55% for SARS-CoV-2 versus 6% for mpox.