Accelerating Disease Model Parameter Extraction - An LLM-Based Ranking Approach to Select Initial Studies For Literature Review Automation

Aug 4, 2026

Upload by Eden

Climate change and expanding human intrusion into natural ecosystems increase demand for disease spread models to forecast and plan for zoonotic outbreaks. Accurate parameterization relies on data from diverse sources, including scientific literature, yet manual systematic literature reviews create major bottlenecks due to time, resource costs, and human error. This work evaluates a large language model as an assessor for screening prioritisation in climate-sensitive zoonotic disease research using question–answer framing and zero-shot chain-of-thought prompting. The method reduces screening effort by at least 70% at a 95% recall target, validates results across four disease datasets with rainfall, and outputs explainable AI rationales for ranked articles.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages27

Reading Time1 h 8 min

AccessFree to download

Abstract

Introduction

Zoonotic disease modeling and parameter needs

Systematic literature reviews as bottlenecks

Challenges in climate-sensitive, multidisciplinary research

Role of automation and large language models

Article Accelerating Disease Model Parameter Extraction: An LLM-Based Ranking Approach to Select Initial Studies For Literature Review Automation Masood Sujau 1, *, Masako Wada 1, Emilie Vallée 1, Natalie Hillis 1 and Teo Sušnjak 2 Academic Editor: Karin Verspoor Received: 15 January 2025 Revised: 4 March 2025 Accepted: 21 March 2025 Published: 26 March 2025 Citation: Sujau, M.; Wada, M.; Vallée, E.; Hillis, N.; Sušnjak, T. Accelerating Disease Model Parameter Extraction: AnLLM-Based Ranking Approach to Select Initial Studies For Literature Review Automation. Mach. Learn. Knowl. Extr. 2025, 7, 28. [https://](https://)[ ](https://)[doi.org/10.3390/make7020028](doi.org/10.3390/make7020028) [Copyright:](Copyright:) © 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://creativecommons.org/](https://creativecommons.org/)[ ](https://creativecommons.org/)[licenses/by/4.0/](licenses/by/4.0/)) . 1 School of Veterinary Science, Massey University, Palmerston North 4442, New Zealand; [m.wada@massey.ac.nz](m.wada@massey.ac.nz) (M.W.); [e.vallee@massey.ac.nz](e.vallee@massey.ac.nz) (E.V.) 2 School of Mathematical and Computational Sciences, Massey University, Auckland 0632, New Zealand; [t.susnjak@massey.ac.nz](t.susnjak@massey.ac.nz) * [Correspondence: mmsujau@massey.ac.nz](Correspondence: mmsujau@massey.ac.nz) Abstract: As climate change transforms our environment and human intrusion into natural ecosystems escalates, there is a growing demand for disease spread models to forecast and plan for the next zoonotic disease outbreak. Accurate parametrization of these models requires data from diverse sources, including the scientific literature. Despite the abundance of scientific publications, the manual extraction of these data via systematic literature reviews remains a significant bottleneck, requiring extensive time and resources, and is susceptible to human error. This study examines the application of a large language model (LLM) as an assessor for screening prioritisation in climate-sensitive zoonotic disease research. By framing the selection criteria of articles as a question–answer task and utilising zero-shot chain-of-thought prompting, the proposed method achieves a saving of at least 70% work effort compared to manual screening at a recall level of 95%(NWSS@95%) . This was validated across four datasets containing four distinct zoonotic diseases and a critical climate variable (rainfall) . The approach additionally produces explainable AI rationales for each ranked article. The effectiveness of the approach across multiple diseases demonstrates the potential for broad application in systematic literature reviews. The substantial reduction in screening effort, along with the provision of explainable AI rationales, marksan important step toward automated parameter extraction from the scientific literature. Keywords: large language models in systematic reviews; automated AI literature screening; zero-shot relevancy ranking; climate-sensitive zoonotic disease modelling; information retrieval in medical literature; systematic literature review automation; biomedical text mining for disease tracking; AI-assisted disease surveillance 1. Introduction Zoonotic diseases are becoming increasingly more prevalent due to increased interactions among, humans, livestock, wildlife, disease vectors, and pathogens, exacerbated by climate change and rapid human expansion into natural habitats [1,2] . Globally, zoonotic diseases have disproportionately impacted impoverished livestock workers in low-and middle-income countries, and are responsible for millions of human deaths every year [3] . To address this threat, there is a mounting need for systems to forecast and model the spread of diseases, thereby aiding public health planning and supporting early warning systems [

FAQs

What problem does the study target in disease model parameter extraction?

It targets the manual bottleneck in extracting parameters from scientific literature during systematic literature reviews, which is time-consuming, resource-intensive, and prone to human error.

How does the proposed LLM method prioritize studies for screening?

It frames article selection criteria as a question–answer task and applies zero-shot chain-of-thought prompting to perform relevancy ranking at a target recall level.

What performance and validation results are reported?

The approach saves at least 70% of screening work at a 95% recall target and is validated across four datasets covering four zoonotic diseases using a critical climate variable (rainfall).

What additional output does the approach provide beyond ranking?

It generates explainable AI rationales for each ranked article to support transparency in the selection process.

Aug 4, 2026

Upload by Eden