AI and Machine Learning for Evidence Syntheses: How You Can Partner with the HSL

UNC Health Sciences Librarians partner on systematic reviews and can apply three different types of predictive AI based on the project's needs. You can find more information on each type on our How Does Predictive AI/ML Work? page.

1. Unsupervised Machine Learning (Clustering): Clusters citations into groups based on common words. Groups can provide insights into themes occurring in the literature and be used to refine the search strategy.
2. Semi-Supervised Machine Learning (Supervised Clustering): Groups citations based on similarity to known relevant citations. Clusters with more known relevant citations can be prioritized for screening.
3. Supervised Machine Learning: Learns from training data to prioritize relevant citations and provides a cut off on when to stop screening.

Current UNC and UNC Health affiliates can contact us if you would like to use any of these tools.

We also offer support with other commercially available tools, such as Covidence and Microsoft Copilot. You can find more information about these tools on our Generative AI & Other Tools page.

Our expert librarians can help you:

• Select appropriate AI tools for your research needs
• Set up and configure tools for optimal results
• Develop effective search strategies
• Ensure methodological rigor

UNC Librarian Co-Authored Publications using AI & Machine Learning Techniques

1. Rich A, McGorray E, Baldwin-SoRelle C, Cawley M, Grigg K, Beach LB, Phillips G, Poteat T. Automated tools for systematic review screening methods: an application of machine learning for sexual orientation and gender identity measurement in health research. JMLA. 2025;113(1):31-8. https://doi.org/10.5195/jmla.2025.1860
2. Cawley M, Carlson R, Vest TA, Eckel SF. Machine learning-assisted literature screening for a medication-use process-related systematic review. Am J Health Syst Pharm. Published online November 22, 2024. doi:10.1093/ajhp/zxae357
3. Singichetti B, Dodd A, Conklin JL, Hassmiller Lich K, Sabounchi NS, Naumann RB. Trends and Insights from Transportation Congestion Pricing Policy Research: A Bibliometric Analysis. Int J Environ Res Public Health. 2022;19(12). doi:10.3390/ijerph19127189
4. Christenson EC, Cronk R, Atkinson H, Bhatt A, Berdiel E, Cawley M, Cho G, Coleman CK, Harrington C, Heilferty K, Fejfar D, Grant EJ, Grigg K, Joshi T, Mohan S, Pelak G, Shu Y, Bartram J. Evidence map and systematic review of disinfection efficacy on environmental surfaces in healthcare facilities. Int J Environ Res Public Health. 2021;18(21). doi:10.3390/ijerph182111100
5. Anderson DM, Cronk R, Fejfar D, Pak E, Cawley M, Bartram J. Safe Healthcare Facilities: A Systematic Review on the Costs of Establishing and Maintaining Environmental Health in Facilities in Low- and Middle-Income Countries. Int J Environ Res Public Health. 2021;18(2). doi:10.3390/ijerph18020817
6. Varghese A, Agyeman-Badu G, Cawley M. Deep learning in automated text classification: a case study using toxicological abstracts. Environ Syst Decis. Published online February 27, 2020. doi:10.1007/s10669-020-09763-2
7. Cawley M, Beardslee R, Beverly B, Hotchkiss A, Kirrane E, Sams R, Varghese A, Wignall J, Cowden J. Novel text analytics approach to identify relevant literature for human health risk assessments: A pilot study with health effects of in utero exposures. Environ Int. 2020;134:105228. doi:10.1016/j.envint.2019.105228
8. Varghese A, Hong T, Hunter C, Agyeman-Badu G, Cawley M. Active learning in automated text classification: a case study exploring bias in predicted model performance metrics. Environ Syst Decis. Published online January 17, 2019:1-12. doi:10.1007/s10669-019-09717-3
9. Varghese A, Cawley M, Hong T. Supervised clustering for automated document classification and prioritization: a case study using toxicological abstracts. Environ Syst Decis. Published online December 26, 2017. doi:10.1007/s10669-017-9670-5