Accepted for/Published in: JMIR AI
Date Submitted: Jul 30, 2025
Open Peer Review Period: Jul 21, 2025 - Sep 15, 2025
Date Accepted: Apr 10, 2026
(closed for review but you can still tweet)
AI-assisted Systematic Literature Review for the Analysis of the Economic Burden of Pneumococcal Disease
ABSTRACT
Background:
Automated systematic literature review (SLR) may reduce the workload and the errors associated with manual review, enabling faster, up-to-date reviews even with increasing publication volumes. Large language model (LLM) has demonstrated strong capabilities in understanding unstructured human languages. However, few studies have explored the potential of a comprehensive LLM platform to streamline the entire SLR process from article screening to data extraction.
Objective:
To investigate the feasibility of applying an LLM-based system to assist with SLR development.
Methods:
We developed an Intelligent SLR system (ISLaR 2.0) powered by LLM and applied it to a use-case of the economic burden of pneumococcal disease (PD) literature. First, we established the inclusion and exclusion criteria for the SLR. Next, we defined the data elements related to economic burden and domain knowledge, along with guidelines for applying these definitions. Finally, we used the criteria and data element specification to develop LLM prompts for screening and data extraction. For data extraction, we identified relevant study characteristics and economic burden outcomes. We evaluated ISLaR 2.0’s performance against a gold standard of 50 expert-curated PD articles, using standard metrics (accuracy, precision, recall, and F1 score). We also conducted a qualitative analysis to describe errors made by the system.
Results:
ISLaR 2.0 performed well in abstract and full-text screening (F1 scores: abstract screening, 86.27; full-text screening, 87.18) and data extraction from text (F1 scores: study details, 92.83; economic burden outcomes, 79.76). The F1 score for data extraction of tabular economic burden outcome data was 94.83. The qualitative analysis revealed two main challenges in extracting economic burden details: misclassification of cost category and failure to extract relevant information.
Conclusions:
ISLaR 2.0 enabled efficient execution of an SLR regarding the economic burden of PD. The platform allows users to flexibly define and modify criteria and data elements, supporting its use across a broad range of health research topics. Clinical Trial: N/A
Citation
Per the author's request the PDF is not available.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.