{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T12:01:36Z","timestamp":1791460896281,"version":"4.3.4"},"reference-count":157,"publisher":"Cambridge University Press (CUP)","license":[{"start":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T00:00:00Z","timestamp":1791417600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["cambridge.org"],"crossmark-restriction":true},"short-container-title":["Res. synth. methods"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Evidence synthesis (ES) is costly and time-intensive. Artificial intelligence (AI) tools are increasingly used to automate or semi-automate ES tasks. We conducted a living rapid review of AI tools that automate or semi-automate ES tasks. We searched for published articles and preprints through MEDLINE, Embase, and the Association for Computing Machinery Digital Library from January 1, 2021 through October 15, 2025, supplemented by hand-searching. We included existing reviews to capture evaluations before 2021. Screening was conducted in duplicate at the title\/abstract level, with single full-text screening and data extraction verified by a second reviewer. We included 134 studies. Performance varied by task and evaluation approach. Search automation tools showed poor recall (median 17%), although human-in-the-loop approaches improved performance. Tools for identifying randomized controlled trials demonstrated high median recall (98%) and precision (92%). Semi-automated abstract screening tools using active learning reduced screening burden by approximately 50% while maintaining 95% recall. Large language models demonstrated variable accuracy for abstract screening (median 88% recall), full-text screening (median 96% recall), and data extraction (median 63% accuracy). Risk of bias (RoB) assessment tools showed moderate agreement with human reviewers for the Cochrane RoB tool version 1 (median 71%) but performed less well with other RoB tools. AI tools can meaningfully reduce burden in study design identification and abstract screening but perform inconsistently across other evidence synthesis tasks. Tools for search automation, data extraction, and RoB assessment require further development. No existing tool can currently replace human expertise.<\/jats:p>","DOI":"10.1017\/rsm.2026.10118","type":"journal-article","created":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T11:42:26Z","timestamp":1791459746000},"page":"1-25","update-policy":"https:\/\/doi.org\/10.1017\/policypage","source":"Crossref","is-referenced-by-count":0,"title":["Artificial intelligence tools for evidence synthesis in the biomedical field: A living rapid review and evidence map"],"prefix":"10.1017","author":[{"given":"Gaelen P.","family":"Adam","sequence":"first","affiliation":[{"id":[{"id":"https:\/\/ror.org\/05gq02987","id-type":"ROR","asserted-by":"publisher"}],"name":"Brown University School of Public Health"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Melinda","family":"Davies","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/00t60zh31","id-type":"ROR","asserted-by":"publisher"}],"name":"Kaiser Permanente Division of Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eduardo","family":"Caputo","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/05gq02987","id-type":"ROR","asserted-by":"publisher"}],"name":"Brown University School of Public Health"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1357-1088","authenticated-orcid":false,"given":"Htun Ja","family":"Mai","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/05gq02987","id-type":"ROR","asserted-by":"publisher"}],"name":"Brown University School of Public Health"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erin","family":"Coppola","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/00t60zh31","id-type":"ROR","asserted-by":"publisher"}],"name":"Kaiser Permanente Division of Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haley","family":"Holmer","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/03jmfdf59","id-type":"ROR","asserted-by":"publisher"}],"name":"Scientific Resource Center for the AHRQ EPC Program"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8708-9962","authenticated-orcid":false,"given":"Edi","family":"Kuhn","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/03jmfdf59","id-type":"ROR","asserted-by":"publisher"}],"name":"Scientific Resource Center for the AHRQ EPC Program"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ethan M.","family":"Balk","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/05gq02987","id-type":"ROR","asserted-by":"publisher"}],"name":"Brown University School of Public Health"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas A.","family":"Trikalinos","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/05gq02987","id-type":"ROR","asserted-by":"publisher"}],"name":"Brown University School of Public Health"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ilya","family":"Ivlev","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/00t60zh31","id-type":"ROR","asserted-by":"publisher"}],"name":"Kaiser Permanente Division of Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Holly R.","family":"Wethington","sequence":"additional","affiliation":[{"name":"Evidence-Based Practice Program, Agency for Healthcare Research and Quality"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"56","published-online":{"date-parts":[[2026,10,8]]},"reference":[{"key":"S1759287926101185_r122","doi-asserted-by":"publisher","DOI":"10.1111\/jnu.12628"},{"key":"S1759287926101185_r132","doi-asserted-by":"publisher","DOI":"10.1002\/jrsm.1761"},{"key":"S1759287926101185_r134","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.l4898"},{"key":"S1759287926101185_r11","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2025.111746"},{"key":"S1759287926101185_r25","doi-asserted-by":"publisher","DOI":"10.1002\/cesm.70050"},{"key":"S1759287926101185_r136","doi-asserted-by":"publisher","DOI":"10.7326\/0003-4819-155-8-201110180-00009"},{"key":"S1759287926101185_r5","doi-asserted-by":"publisher","DOI":"10.2217\/cer.13.17"},{"key":"S1759287926101185_r154","doi-asserted-by":"publisher","DOI":"10.1002\/cesm.70046"},{"key":"S1759287926101185_r147","doi-asserted-by":"publisher","DOI":"10.1002\/cesm.12041"},{"key":"S1759287926101185_r156","unstructured":"[156] Thomas, J , Hair, K , Noel-Storr, A. Responsible use of AI in evidence synthesis (RAISE 2026) 2: building and evaluating AI evidence synthesis tools. 2025."},{"key":"S1759287926101185_r108","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1038\/s41746-025-01457-w","article-title":"Language models for data extraction and risk of bias assessment in complementary medicine","volume":"8","author":"Lai","year":"2025","journal-title":"NPJ Digit Med."},{"key":"S1759287926101185_r137","doi-asserted-by":"crossref","DOI":"10.1093\/ejo\/cjae011","article-title":"Enhancing systematic reviews in orthodontics: a comparative examination of GPT-3.5 and GPT-4 for generating PICO-based queries with tailored prompts and configurations","volume":"46","author":"Demir","year":"2024","journal-title":"Eur J Orthod."},{"key":"S1759287926101185_r22","doi-asserted-by":"publisher","DOI":"10.1002\/cesm.70045"},{"key":"S1759287926101185_r123","doi-asserted-by":"publisher","DOI":"10.2196\/70450"},{"key":"S1759287926101185_r115","doi-asserted-by":"publisher","DOI":"10.1101\/2024.02.20.24303083"},{"key":"S1759287926101185_r129","doi-asserted-by":"publisher","DOI":"10.1002\/cesm.70048"},{"key":"S1759287926101185_r128","doi-asserted-by":"publisher","DOI":"10.1101\/2023.11.19.23298727"},{"key":"S1759287926101185_r16","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2016.01.021"},{"key":"S1759287926101185_r70","doi-asserted-by":"publisher","DOI":"10.1016\/j.hlpt.2024.100943"},{"key":"S1759287926101185_r127","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocv044"},{"key":"S1759287926101185_r59","doi-asserted-by":"publisher","DOI":"10.1101\/2024.09.06.24313186"},{"key":"S1759287926101185_r86","doi-asserted-by":"publisher","DOI":"10.1186\/s13643-024-02590-5"},{"key":"S1759287926101185_r20","doi-asserted-by":"publisher","DOI":"10.1136\/rapm-2024-106231"},{"key":"S1759287926101185_r46","first-page":"551","article-title":"Machine learning-assisted literature screening for a medication-use process-related systematic review","volume":"82","author":"Cawley","year":"2024","journal-title":"Am J Health Syst Pharm"},{"key":"S1759287926101185_r157","doi-asserted-by":"publisher","DOI":"10.1017\/rsm.2025.10058"},{"key":"S1759287926101185_r3","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2021.05.019"},{"key":"S1759287926101185_r109","doi-asserted-by":"publisher","DOI":"10.1097\/JS9.0000000000002215"},{"key":"S1759287926101185_r88","doi-asserted-by":"publisher","DOI":"10.1002\/jrsm.1762"},{"key":"S1759287926101185_r91","doi-asserted-by":"publisher","DOI":"10.1186\/s13643-015-0067-6"},{"key":"S1759287926101185_r38","first-page":"406","article-title":"Testing a filtering strategy for systematic reviews: evaluating work savings and recall","volume":"2022","author":"Proescholdt","year":"2022","journal-title":"AMIA Jt Summits Transl Sci Proc"},{"key":"S1759287926101185_r111","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1186\/s13643-023-02351-w","article-title":"Evaluation of a prototype machine learning tool to semi-automate data extraction for systematic literature reviews","volume":"12","author":"Panayi","year":"2023","journal-title":"Syst Rev."},{"key":"S1759287926101185_r30","doi-asserted-by":"publisher","DOI":"10.1080\/02763869.2024.2440848"},{"key":"S1759287926101185_r114","doi-asserted-by":"publisher","DOI":"10.2196\/68666"},{"key":"S1759287926101185_r135","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.i4919"},{"key":"S1759287926101185_r101","doi-asserted-by":"publisher","DOI":"10.7326\/ANNALS-25-00739"},{"key":"S1759287926101185_r7","doi-asserted-by":"publisher","DOI":"10.1017\/rsm.2025.16"},{"key":"S1759287926101185_r41","doi-asserted-by":"publisher","DOI":"10.1101\/2024.07.01.24309767"},{"key":"S1759287926101185_r60","doi-asserted-by":"publisher","DOI":"10.1002\/jrsm.1715"},{"key":"S1759287926101185_r83","doi-asserted-by":"publisher","DOI":"10.1186\/s13643-021-01635-3"},{"key":"S1759287926101185_r28","volume-title":"Fast Clinical Trial Identification Using Fuzzy-Search Elastic Searches: Retrospective Validation with High-Quality Cochrane Benchmark","author":"Otte","year":"2023"},{"key":"S1759287926101185_r71","doi-asserted-by":"publisher","DOI":"10.34133\/hds.0322"},{"key":"S1759287926101185_r64","doi-asserted-by":"publisher","DOI":"10.1186\/s13643-024-02609-x"},{"key":"S1759287926101185_r125","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2024.12687"},{"key":"S1759287926101185_r67","doi-asserted-by":"crossref","first-page":"e76252","DOI":"10.2196\/76252","article-title":"Automated literature screening for hepatocellular carcinoma treatment through integration of 3 large language models: methodological study","volume":"13","author":"Pan","year":"2025","journal-title":"JMIR Med Inform."},{"key":"S1759287926101185_r130","doi-asserted-by":"publisher","DOI":"10.1002\/jrsm.1749"},{"key":"S1759287926101185_r139","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymeth.2014.11.006"},{"key":"S1759287926101185_r15","unstructured":"[15] Effective Health Care Program, Agency for Healthcare Research and Quality. Machine learning tools to (semi-)automate evidence synthesis: a rapid review and evidence map. 2026."},{"key":"S1759287926101185_r32","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591703"},{"key":"S1759287926101185_r78","doi-asserted-by":"publisher","DOI":"10.1101\/2024.12.10.24318803"},{"key":"S1759287926101185_r73","doi-asserted-by":"publisher","DOI":"10.1101\/2023.12.15.23300018"},{"key":"S1759287926101185_r79","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2025.106035"},{"key":"S1759287926101185_r100","doi-asserted-by":"publisher","DOI":"10.1002\/jrsm.1710"},{"key":"S1759287926101185_r36","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0283342"},{"key":"S1759287926101185_r103","doi-asserted-by":"publisher","DOI":"10.1186\/s13643-024-02523-2"},{"key":"S1759287926101185_r8","doi-asserted-by":"publisher","DOI":"10.1016\/j.puhe.2026.106220"},{"key":"S1759287926101185_r24","doi-asserted-by":"publisher","DOI":"10.1089\/lap.2024.0277"},{"key":"S1759287926101185_r98","doi-asserted-by":"publisher","DOI":"10.1002\/cesm.70033"},{"key":"S1759287926101185_r48","doi-asserted-by":"publisher","DOI":"10.2196\/67488"},{"key":"S1759287926101185_r77","unstructured":"[77] Wilkins, D. Automated title and abstract screening for scoping reviews using the GPT-4 large language model. arXiv preprint arXiv:231107918. 2023."},{"key":"S1759287926101185_r1","doi-asserted-by":"publisher","DOI":"10.4135\/9781036234942"},{"key":"S1759287926101185_r121","doi-asserted-by":"crossref","first-page":"394","DOI":"10.1136\/bmjebm-2023-112597","article-title":"Integrating large language models in systematic reviews: a framework and case study using ROBINS-I for risk of bias assessment","volume":"29","author":"Hasan","year":"2024","journal-title":"BMJ Evid Based Med"},{"key":"S1759287926101185_r89","doi-asserted-by":"publisher","DOI":"10.1007\/s00264-022-05672-y"},{"key":"S1759287926101185_r23","doi-asserted-by":"publisher","DOI":"10.1002\/cesm.70059"},{"key":"S1759287926101185_r58","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-024-02203-8"},{"key":"S1759287926101185_r151","doi-asserted-by":"publisher","DOI":"10.1186\/s13643-021-01700-x"},{"key":"S1759287926101185_r145","doi-asserted-by":"publisher","DOI":"10.1002\/cesm.70037"},{"key":"S1759287926101185_r26","doi-asserted-by":"publisher","DOI":"10.2196\/68592"},{"key":"S1759287926101185_r37","doi-asserted-by":"publisher","DOI":"10.1002\/jrsm.1287"},{"key":"S1759287926101185_r80","doi-asserted-by":"publisher","DOI":"10.1101\/2025.08.11.25333429"},{"key":"S1759287926101185_r35","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocu025"},{"key":"S1759287926101185_r39","doi-asserted-by":"publisher","DOI":"10.1093\/jamiaopen\/ooac015"},{"key":"S1759287926101185_r40","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2020.11.003"},{"key":"S1759287926101185_r43","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-025-02569-3"},{"key":"S1759287926101185_r52","doi-asserted-by":"publisher","DOI":"10.1186\/s13643-024-02575-4"},{"key":"S1759287926101185_r144","doi-asserted-by":"crossref","first-page":"2235","DOI":"10.1111\/jdv.20237","article-title":"Appraisal of AI-generated dermatology literature reviews","volume":"38","author":"Passby","year":"2024","journal-title":"J Eur Acad Dermatol Venereol."},{"key":"S1759287926101185_r110","doi-asserted-by":"publisher","DOI":"10.1002\/cesm.70058"},{"key":"S1759287926101185_r118","doi-asserted-by":"publisher","DOI":"10.7326\/M22-0092"},{"key":"S1759287926101185_r96","doi-asserted-by":"publisher","DOI":"10.2196\/22422"},{"key":"S1759287926101185_r21","doi-asserted-by":"publisher","DOI":"10.1016\/j.acra.2025.08.014"},{"key":"S1759287926101185_r42","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocae166"},{"key":"S1759287926101185_r90","doi-asserted-by":"publisher","DOI":"10.1002\/jrsm.1311"},{"key":"S1759287926101185_r76","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-62058-5"},{"key":"S1759287926101185_r69","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocaf050"},{"key":"S1759287926101185_r53","doi-asserted-by":"publisher","DOI":"10.1186\/s13643-020-01528-x"},{"key":"S1759287926101185_r9","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2021.12.005"},{"key":"S1759287926101185_r51","doi-asserted-by":"publisher","DOI":"10.1200\/CCI.19.00043"},{"key":"S1759287926101185_r116","unstructured":"[116] Yun, HS , Pogrebitskiy, D , Marshall, IJ , Wallace, BC . Automatically extracting numerical results from randomized controlled trials with large language models. arXiv preprint arXiv:240501686. 2024."},{"key":"S1759287926101185_r18","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2022.06.007"},{"key":"S1759287926101185_r85","doi-asserted-by":"crossref","first-page":"256","DOI":"10.1186\/s12874-020-01129-1","article-title":"An evaluation of DistillerSR\u2019s machine learning-based prioritization tool for title\/abstract screening\u2014impact on reviewer-relevant outcomes","volume":"20","author":"Hamel","year":"2020","journal-title":"BMC Med Res Methodol."},{"key":"S1759287926101185_r49","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinane.2025.112030"},{"key":"S1759287926101185_r133","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.d5928"},{"key":"S1759287926101185_r119","doi-asserted-by":"publisher","DOI":"10.1101\/2024.07.16.24310483"},{"key":"S1759287926101185_r95","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-11-55"},{"key":"S1759287926101185_r120","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2017.12.015"},{"key":"S1759287926101185_r92","doi-asserted-by":"publisher","DOI":"10.2196\/69700"},{"key":"S1759287926101185_r68","unstructured":"[68] Robinson, A , Thorne, W , Wu, BP , et al. Bio-sieve: exploring instruction tuning large language models for systematic review automation. arXiv preprint arXiv:230806610. 2023."},{"key":"S1759287926101185_r13","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1186\/s13643-025-02842-y","article-title":"The landscape of artificial intelligence tools and platforms for evidence synthesis: a scoping review","volume":"15","author":"MSA","year":"2026","journal-title":"Syst Rev"},{"key":"S1759287926101185_r82","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-019-0992-8"},{"key":"S1759287926101185_r44","doi-asserted-by":"publisher","DOI":"10.7326\/ANNALS-24-02189"},{"key":"S1759287926101185_r113","doi-asserted-by":"publisher","DOI":"10.1007\/s41669-024-00476-9"},{"key":"S1759287926101185_r140","doi-asserted-by":"publisher","DOI":"10.1093\/jamiaopen\/ooaa042"},{"key":"S1759287926101185_r142","doi-asserted-by":"publisher","DOI":"10.1101\/2023.10.31.23297818"},{"key":"S1759287926101185_r57","doi-asserted-by":"publisher","DOI":"10.1186\/s13643-016-0263-z"},{"key":"S1759287926101185_r87","doi-asserted-by":"publisher","DOI":"10.1016\/j.envint.2020.105623"},{"key":"S1759287926101185_r56","doi-asserted-by":"publisher","DOI":"10.2196\/48996"},{"key":"S1759287926101185_r148","doi-asserted-by":"crossref","first-page":"e55827","DOI":"10.2196\/55827","article-title":"Evaluation of RMES, an automated software tool utilizing AI, for literature screening with reference to published systematic reviews as case-studies: development and usability study","volume":"8","author":"Sugiura","year":"2024","journal-title":"JMIR Form Res."},{"key":"S1759287926101185_r6","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-024-02320-4"},{"key":"S1759287926101185_r81","doi-asserted-by":"publisher","DOI":"10.1101\/2025.08.24.25334314"},{"key":"S1759287926101185_r94","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1186\/s13643-023-02334-x","article-title":"Increasing the efficiency of study selection for systematic reviews using prioritization tools and a single-screening approach","volume":"12","author":"Waffenschmidt","year":"2023","journal-title":"Syst Rev"},{"key":"S1759287926101185_r99","doi-asserted-by":"publisher","DOI":"10.1016\/j.jdent.2025.105846"},{"key":"S1759287926101185_r4","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.f139"},{"key":"S1759287926101185_r10","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocaf030"},{"key":"S1759287926101185_r45","doi-asserted-by":"publisher","DOI":"10.1101\/2024.06.01.24308323"},{"key":"S1759287926101185_r66","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2024.20496"},{"key":"S1759287926101185_r2","doi-asserted-by":"publisher","DOI":"10.1016\/j.conctc.2019.100443"},{"key":"S1759287926101185_r126","article-title":"Risk of bias assessment of diagnostic accuracy studies using QUADAS 2 by large language models","volume":"15","author":"Leucu\u021ba","year":"2025","journal-title":"Diagnostics (Basel)"},{"key":"S1759287926101185_r150","doi-asserted-by":"publisher","DOI":"10.1016\/j.jval.2024.10.2293"},{"key":"S1759287926101185_r62","doi-asserted-by":"publisher","DOI":"10.1016\/j.jval.2025.08.002"},{"key":"S1759287926101185_r138","doi-asserted-by":"publisher","DOI":"10.1186\/s13643-022-02045-9"},{"key":"S1759287926101185_r107","doi-asserted-by":"publisher","DOI":"10.1002\/jrsm.1732"},{"key":"S1759287926101185_r72","article-title":"Validation of Synthesa AI, a large language model-based screening tool for systematic reviews: results from nine pharmacologic studies","author":"Teperikidis","year":"2022","journal-title":"J Cardiovasc Pharmacol"},{"key":"S1759287926101185_r102","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-021-01354-2"},{"key":"S1759287926101185_r33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2501.16255"},{"key":"S1759287926101185_r93","doi-asserted-by":"publisher","DOI":"10.1186\/s13643-020-01324-7"},{"key":"S1759287926101185_r31","doi-asserted-by":"publisher","DOI":"10.3928\/01477447-20231220-02"},{"key":"S1759287926101185_r47","doi-asserted-by":"publisher","DOI":"10.1136\/bjo-2024-326254"},{"key":"S1759287926101185_r152","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365-2753.2003.00411.x"},{"key":"S1759287926101185_r19","doi-asserted-by":"publisher","DOI":"10.2196\/53164"},{"key":"S1759287926101185_r65","doi-asserted-by":"publisher","DOI":"10.2196\/52758"},{"key":"S1759287926101185_r61","first-page":"904","article-title":"Large language model-assisted systematic review: validation based on Cochrane review data","volume":"327","author":"Kim","year":"2025","journal-title":"Stud Health Technol Inform"},{"key":"S1759287926101185_r29","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2022.104928"},{"key":"S1759287926101185_r106","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1186\/1472-6947-10-56","article-title":"ExaCT: automatic extraction of clinical trial characteristics from journal publications","volume":"10","author":"Kiritchenko","year":"2010","journal-title":"BMC Med Inform Decis Mak."},{"key":"S1759287926101185_r117","doi-asserted-by":"publisher","DOI":"10.1002\/jrsm.1398"},{"key":"S1759287926101185_r146","doi-asserted-by":"publisher","DOI":"10.1186\/s12903-025-06982-4"},{"key":"S1759287926101185_r14","unstructured":"[14] Effective Health Care Program, Agency for Healthcare Research and Quality. Research protocol: tools to (semi-)automate evidence synthesis. 2026."},{"key":"S1759287926101185_r75","doi-asserted-by":"publisher","DOI":"10.1145\/3624918.3625322"},{"key":"S1759287926101185_r84","doi-asserted-by":"publisher","DOI":"10.1007\/s10567-025-00519-5"},{"key":"S1759287926101185_r97","doi-asserted-by":"crossref","unstructured":"[97] Janoudi, G , Uzun, M , Jurdana, M , Hutton, B. Evaluating Loon Lens Pro\u2122, an AI-driven tool for full-text screening in systematic reviews: a validation study. 2025. https:\/\/doi.org\/10.1101\/2025.02.11.25322087.","DOI":"10.1101\/2025.02.11.25322087"},{"key":"S1759287926101185_r105","first-page":"313","article-title":"Novel AI applications in systematic review: GPT-4 assisted data extraction, analysis, review of bias","volume":"30","author":"Kim","year":"2025","journal-title":"BMJ Evid Based Med."},{"key":"S1759287926101185_r112","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2018.08.023"},{"key":"S1759287926101185_r27","doi-asserted-by":"publisher","DOI":"10.1016\/j.isci.2025.113559"},{"key":"S1759287926101185_r141","doi-asserted-by":"crossref","first-page":"587","DOI":"10.1002\/jrsm.1317","article-title":"Discriminating between empirical studies and nonempirical works using automated text classification","volume":"9","author":"Langlois","year":"2018","journal-title":"Res Synth Methods."},{"key":"S1759287926101185_r149","doi-asserted-by":"publisher","DOI":"10.1016\/j.jdent.2024.105259"},{"key":"S1759287926101185_r63","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2018.12.001"},{"key":"S1759287926101185_r153","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-022-01649-y"},{"key":"S1759287926101185_r12","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocaf063"},{"key":"S1759287926101185_r55","doi-asserted-by":"publisher","DOI":"10.1186\/s13643-019-1222-2"},{"key":"S1759287926101185_r34","first-page":"460","article-title":"Evaluation of a popular large language model in orthopedic literature review: comparison to previously published reviews","volume":"13","author":"Yao","year":"2025","journal-title":"Arch Bone Jt Surg"},{"key":"S1759287926101185_r74","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-022-01631-8"},{"key":"S1759287926101185_r50","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2411962122"},{"key":"S1759287926101185_r124","doi-asserted-by":"publisher","DOI":"10.1159\/000544857"},{"key":"S1759287926101185_r131","doi-asserted-by":"publisher","DOI":"10.1002\/cesm.70044"},{"key":"S1759287926101185_r17","doi-asserted-by":"publisher","DOI":"10.1093\/jamiaopen\/ooae098"},{"key":"S1759287926101185_r104","doi-asserted-by":"publisher","DOI":"10.1002\/cesm.70036"},{"key":"S1759287926101185_r143","doi-asserted-by":"publisher","DOI":"10.5662\/wjm.v15.i4.102290"},{"key":"S1759287926101185_r54","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-020-01031-w"},{"key":"S1759287926101185_r155","unstructured":"[155] Adam, GP . Advancing the semi-automation of literature identification for evidence synthesis: evaluation measure prioritization, training data development, and language model implementation. Brown University School of Public Health; 2024. https:\/\/repository.library.brown.edu\/studio\/item\/bdr:d56axgw9\/"}],"container-title":["Research Synthesis Methods"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cambridge.org\/core\/services\/aop-cambridge-core\/content\/view\/S1759287926101185","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T11:42:37Z","timestamp":1791459757000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cambridge.org\/core\/product\/identifier\/S1759287926101185\/type\/journal_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,8]]},"references-count":157,"alternative-id":["S1759287926101185"],"URL":"https:\/\/doi.org\/10.1017\/rsm.2026.10118","relation":{},"ISSN":["1759-2879","1759-2887"],"issn-type":[{"value":"1759-2879","type":"print"},{"value":"1759-2887","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,8]]},"assertion":[{"value":"\u00a9 The Author(s), 2026. Published by Cambridge University Press on behalf of The Society for Research Synthesis Methodology","name":"copyright","label":"Copyright","group":{"name":"copyright_and_licensing","label":"Copyright and Licensing"}},{"value":"This is an Open Access article, distributed under the terms of the Creative Commons Attribution licence (https:\/\/creativecommons.org\/licenses\/by\/4.0), which permits unrestricted re-use, distribution and reproduction, provided the original article is properly cited.","name":"license","label":"License","group":{"name":"copyright_and_licensing","label":"Copyright and Licensing"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}