Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Jun;43(6):647-650.
doi: 10.1007/s40273-025-01481-4. Epub 2025 Apr 10.

Artificial Intelligence as a New Research Ally? Performing AI-Assisted Systematic Literature Reviews in Health Economics

Sietse van Mossel  1   2 , Martijn Johan Oude-Wolcherink  3 , Rafael Emilio de Feria Cardet  4 , Lioe-Fee de Geus-Oei  1   2   5 , Dennis Vriens  6 , Hendrik Koffijberg  3 , Sopany Saing  7   8
Affiliations

Artificial Intelligence as a New Research Ally? Performing AI-Assisted Systematic Literature Reviews in Health Economics

Sietse van Mossel et al. Pharmacoeconomics. 2025 Jun.
No abstract available

PubMed Disclaimer

Conflict of interest statement

Declarations. Funding: The authors declare that no funds, grants or other support were received during the preparation of this research letter. Conflicts of Interest: Sietse van Mossel, Martijn Johan Oude-Wolcherink, Rafael Emilio de Feria Cardet, Lioe-Fee de Geus-Oei, Dennis Vriens, Hendrik Koffijberg and Sopany Saing have no conflicts of interest that are directly relevant to the content of this research letter. Ethics Approval: Not applicable. Consent to Participate: Not applicable. Consent for Publication: Not applicable. Availability of Data and Material: The software codes and datasets generated/analysed on which the reported results in this research letter rely are publicly available using the following Zenodo link: https://zenodo.org/record/8217881 . The originally published search strategies and title/abstract screening criteria are publicly available using the following https://doi.org/10.1007/s40273-024-01447-y . Code Availability: The software codes on which the reported results in this research letter rely are publicly available using the following Zenodo link: https://zenodo.org/record/8217881 . Authors’ Contributions: All authors contributed to the study’s conception and design. Material preparation, data collection and analysis were performed by SvM and MOW. The first draft of the manuscript was written by SvM and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.

Figures

Fig. 1
Fig. 1
Accuracy per iteration (grey lines) and as a median value for all iterations (red line). In panels a and b, ASReview Software has to start screening random articles to find relevant articles, thus no prior knowledge. In panels c and d, ASReview Software was informed with one relevant and one irrelevant article, resulting in lower variation. Median accuracy levels are, however, similar. In panels a and panel c, accuracy for articles originally included for full-text review is depicted. In panels b and d, accuracy for articles originally included for data extraction is depicted. Generally, articles included for data extraction in the original full manual screening were found early in the artificial intelligence-assisted screening process
Fig. 2
Fig. 2
Overview of the opportunities and next steps before widespread implementation of artificial intelligence (AI) tools for semi-autonomous and fully autonomous title and abstract screening. Practical guidance, verification and validation checklists should be further developed. Simultaneously, further validation efforts and head-to-head comparisons of AI tools should be performed. Thereafter, AI-guided screening might be used and allowed as a second or third reviewer option, and to update existing reviews with minimal time investments. The latter should be thoroughly validated. In parallel, similar evaluation and validation efforts may be performed focusing on AI-guided data extraction. SLRs systematic literature reviews
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Cosby K, Yang D, Fineberg HV. Assessing diagnostic performance. NEJM Evid. 2024. 10.1056/EVIDra2300232. - PubMed
    1. Blaizot A, Veettil SK, Saidoung P, Moreno-Garcia CF, Wiratunga N, Aceves-Martins M, et al. Using artificial intelligence methods for systematic review in health sciences: a systematic review. Res Synth Methods. 2022;13:353–62. - PubMed
    1. Johnson EE, O’Keefe H, Sutton A, Marshall C. The systematic review toolbox: keeping up to date with tools to support evidence synthesis. Syst Rev. 2022. 10.1186/s13643-022-02122-z. - PMC - PubMed
    1. Van Dijk SHB, Brusse-Keizer MGJ, Bucsán CC, Van Der Palen J, Doggen CJM, Lenferink A. Artificial intelligence in systematic reviews: promising when appropriately used. BMJ Open. 2023;13: e072254. - PMC - PubMed
    1. Hamel C, Kelly SE, Thavorn K, Rice DB, Wells GA, Hutton B. An evaluation of DistillerSR’s machine learning-based prioritization tool for title/abstract screening: impact on reviewer-relevant outcomes. BMC Med Res Methodol. 2020. 10.1186/s12874-020-01129-1. - PMC - PubMed

LinkOut - more resources