{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T14:59:16Z","timestamp":1789052356376,"version":"build-2803163510"},"reference-count":59,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T00:00:00Z","timestamp":1771286400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T00:00:00Z","timestamp":1774396800000},"content-version":"vor","delay-in-days":36,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Syst Rev"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>The process of developing and updating an evidence gap map (EGM) is based on the principles of systematic reviews and requires extensive time and financial resources. Artificial intelligence (AI) tools, like prioritisation screening (PS), integrated into programmes such as EPPI-Reviewer (ER) and Copilot 365, can potentially mimic human performance in systematic review processes. ER is a subscription-based web application employed by systematic review groups, while Copilot 365, integrated into Microsoft 365, offers real-time assistance. Although ER shows promise in speeding up screening, the optimal threshold for accuracy remains unclear. Additionally, there is no evidence on the effectiveness of any version of Copilot in systematic review and EGM processes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>Assess the accuracy and efficiency of Copilot 365 and PS integrated into ER at different stages of an EGM update, comparing it to human performance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We will conduct both manual and automated screening of references, full-text screening, data extraction, and critical appraisal. Two reviewers will independently screen studies for inclusion, extract data, and appraise included studies, resolving conflicts through discussion. We will assess the accuracy and efficiency of Copilot 365 and ER at different EGM update stages, comparing them to human performance. To evaluate the PS accuracy, we will use 20% and 40% manual screening thresholds, calculating the proportion of relevant references prioritised by PS and the total relevant citations missed. We will compare Copilot 365\u2019s full-text screening accuracy to reviewers\u2019 decisions and assess consistency using Cohen\u2019s Kappa. For automated data extraction and appraisal, we will manually inspect 20% of Copilot 365\u2019s outputs, comparing them to reviewers\u2019 results, measuring consistency with Cohen\u2019s Kappa, and evaluating time savings by comparing the time taken for manual extraction versus using Copilot 365.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>This study will offer insights into ER\u2019s accuracy in screening small samples of citations and potentially guide future applications in this context. Additionally, by evaluating Copilot 365, which shares similar features with other AI tools, we will gain a broader understanding of its applicability and limitations in evidence synthesis, making the results relevant to other AI applications in this field.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Systematic review registration<\/jats:title>\n                    <jats:p>\n                      Registered at Open Science Framework:\n                      <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/doi.org\/10.17605\/OSF.IO\/49BX8\" ext-link-type=\"uri\">https:\/\/doi.org\/10.17605\/OSF.IO\/49BX8<\/jats:ext-link>\n                      .\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s13643-026-03101-4","type":"journal-article","created":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T02:54:39Z","timestamp":1771296879000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Study protocol for evaluating automation of systematic review processes with EPPI-Reviewer and Copilot 365 in updating the cataract evidence gap map"],"prefix":"10.1186","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4808-2266","authenticated-orcid":false,"given":"Bhavisha","family":"Virendrakumar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hugh Sharma","family":"Waddington","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pauline","family":"Scheelbeek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emma","family":"Jolley","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elena","family":"Schmidt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,2,17]]},"reference":[{"issue":"4","key":"3101_CR1","doi-asserted-by":"publisher","first-page":"e1125","DOI":"10.1002\/cl2.1125","volume":"16","author":"H White","year":"2020","unstructured":"White H, Albers B, Gaarder M, Kornor H, Littell J, Marshall Z, et al. Guidance for producing a Campbell evidence and gap map. Campbell Syst Rev. 2020;16(4):e1125.","journal-title":"Campbell Syst Rev"},{"issue":"Suppl 1","key":"3101_CR2","doi-asserted-by":"publisher","first-page":"i68","DOI":"10.1093\/inthealth\/ihab072","volume":"14","author":"E Jolley","year":"2022","unstructured":"Jolley E, Virendrakumar B, Pente V, Baldwin M, Mailu E, Schmidt E. Evidence on cataract in low- and middle-income countries: an updated review of reviews using the evidence gap maps approach. Int Health. 2022;14(Suppl 1):i68\u201383.","journal-title":"Int Health"},{"issue":"11","key":"3101_CR3","doi-asserted-by":"publisher","first-page":"1455","DOI":"10.1136\/bjophthalmol-2015-308156","volume":"100","author":"B Virendrakumar","year":"2016","unstructured":"Virendrakumar B, Jolley E, Gordon I, Bascaran C, Schmidt E. Availability of evidence on cataract in low\/middle-income settings: a review of reviews using evidence gap maps approach. Br J Ophthalmol. 2016;100(11):1455\u201360.","journal-title":"Br J Ophthalmol"},{"key":"3101_CR4","doi-asserted-by":"crossref","unstructured":"Edwards KM, Song B, Porciello J, Engelbert M, Huang M, F. A. AI-accelerated design of evidence synthesis for global development. Computation and language. 2023.","DOI":"10.1115\/DETC2023-116962"},{"issue":"1","key":"3101_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.4073\/cmdp.2018.2","volume":"14","author":"A Saran","year":"2018","unstructured":"Saran A, White H. Evidence and gap maps: a comparison of different approaches. Campbell Syst Rev. 2018;14(1):1\u201338.","journal-title":"Campbell Syst Rev"},{"key":"3101_CR6","doi-asserted-by":"crossref","unstructured":"Thomas J, McNaught J, S. A. Applications of text mining within systematic reviews. Res Synth Methods. 2011;2(1):1\u201314.","DOI":"10.1002\/jrsm.27"},{"issue":"11","key":"3101_CR7","doi-asserted-by":"publisher","first-page":"2156","DOI":"10.1038\/s41433-024-02961-1","volume":"38","author":"Vision Loss Expert Group of the Global Burden of Disease S","year":"2024","unstructured":"Vision Loss Expert Group of the Global Burden of Disease S, Blindness GBD, Vision Impairment C. Global estimates on the number of people blind or visually impaired by cataract: a meta-analysis from 2000 to 2020. Eye (Lond). 2024;38(11):2156\u201372.","journal-title":"Eye (Lond)"},{"key":"3101_CR8","unstructured":"Pesudovs P, Lansingh VC, Kempen JH, Steinmetz JD, Briant PS, Varma R, et al. Cataract-related blindness and vision impairment in 2020 and trends over time in relation to VISION 2020: the Right to Sight: an analysis for the Global Burden of Disease Study. iovs. 2021;62(8):3523."},{"issue":"3","key":"3101_CR9","doi-asserted-by":"publisher","first-page":"100164","DOI":"10.1016\/j.xops.2022.100164","volume":"2","author":"DJ Lindegger","year":"2022","unstructured":"Lindegger DJ, Wawrzynski J, Saleh GM. Evolution and applications of Artificial Intelligence to cataract surgery. Ophthalmol Sci. 2022;2(3):100164.","journal-title":"Ophthalmol Sci"},{"issue":"1","key":"3101_CR10","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1186\/s13643-018-0740-7","volume":"7","author":"E Beller","year":"2018","unstructured":"Beller E, Clark J, Tsafnat G, Adams C, Diehl H, Lund H, et al. Making progress with the automation of systematic reviews: principles of the International Collaboration for the Automation of Systematic Reviews (ICASR). Syst Rev. 2018;7(1):77.","journal-title":"Syst Rev"},{"key":"3101_CR11","doi-asserted-by":"crossref","unstructured":"Torre\u2011L\u00f3pez J, Ram\u00edrez A, JR. R. Artifcial intelligence to automate the systematic review of scientifc literature. Computing. 2023;105:2171\u201394.","DOI":"10.1007\/s00607-023-01181-x"},{"issue":"4","key":"3101_CR12","doi-asserted-by":"publisher","first-page":"e1194","DOI":"10.1002\/cl2.1194","volume":"17","author":"H Chirgwin","year":"2021","unstructured":"Chirgwin H, Cairncross S, Zehra D, Sharma Waddington H. Interventions promoting uptake of water, sanitation and hygiene (WASH) technologies in low- and middle-income countries: an evidence and gap map of effectiveness studies. Campbell Syst Rev. 2021;17(4):e1194.","journal-title":"Campbell Syst Rev"},{"key":"3101_CR13","unstructured":"IBM. What is artificial intelligence (AI)? 2024. Available from: https:\/\/www.ibm.com\/topics\/artificial-intelligence."},{"key":"3101_CR14","unstructured":"Co. BM. What is deep learning AI? A simple guide with 8 practical examples 2024. Available from: https:\/\/bernardmarr.com\/what-is-deep-learning-ai-a-simple-guide-with-8-practical-examples\/."},{"key":"3101_CR15","unstructured":"IBM. What is NLP? 2024. Available from: https:\/\/www.ibm.com\/topics\/natural-language-processing."},{"key":"3101_CR16","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1186\/s13643-015-0012-8","volume":"4","author":"A O'Mara-Eves","year":"2015","unstructured":"O\u2019Mara-Eves A, Thomas J, McNaught J, Miwa M, Ananiadou S. Using text mining for study identification in systematic reviews: a systematic review of current approaches. Syst Rev. 2015;4:22.","journal-title":"Syst Rev"},{"key":"3101_CR17","unstructured":"Scheelbeek P, Bond M, Callaghan M, Minx J, Hadida G, O\u2019Mara-Eves A, et al. Digital evidence synthesis tools for climate & health: barriers and enablers for enhanced use of DESTs in the climate & health field. London, UK. 2024."},{"key":"3101_CR18","unstructured":"Bond M, Finnerty A, O'Mara-Eaves A, O'Driscoll P, Thomas J, Minx J, et al. Digital evidence synthesis tool evaluations EPPI visualiser database. 2024. Available from: https:\/\/eppi.ioe.ac.uk\/eppi-vis\/login\/open?webdbid=435."},{"issue":"1","key":"3101_CR19","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1186\/s13643-022-02122-z","volume":"11","author":"EE Johnson","year":"2022","unstructured":"Johnson EE, O\u2019Keefe H, Sutton A, Marshall C. The Systematic Review Toolbox: keeping up to date with tools to support evidence synthesis. Syst Rev. 2022;11(1):258.","journal-title":"Syst Rev"},{"key":"3101_CR20","unstructured":"Bond M, Khosravi H, Bergdahl N, Buntins K, De Laat M, Oxley E, et al. Digital evidence synthesis tools in educational technology research: a systematic mapping review. Pre-print. 2023."},{"issue":"5","key":"3101_CR21","doi-asserted-by":"publisher","first-page":"e33219","DOI":"10.2196\/33219","volume":"10","author":"K Cowie","year":"2022","unstructured":"Cowie K, Rahmatullah A, Hardy N, Holub K, Kallmes K. Web-based software tools for systematic literature review in medicine: systematic search and feature analysis. JMIR Med Inform. 2022;10(5):e33219.","journal-title":"JMIR Med Inform"},{"issue":"1","key":"3101_CR22","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1002\/jrsm.1093","volume":"5","author":"I Shemilt","year":"2014","unstructured":"Shemilt I, Simon A, Hollands GJ, Marteau TM, Ogilvie D, O\u2019Mara-Eves A, et al. Pinpointing needles in giant haystacks: use of text mining to reduce impractical screening workload in extremely large scoping reviews. Res Synth Methods. 2014;5(1):31\u201349.","journal-title":"Res Synth Methods"},{"key":"3101_CR23","doi-asserted-by":"crossref","unstructured":"Shemilt I, Khan N, Park S, J. T. Use of cost-effectiveness analysis to compare the efficiency of study identification methods in systematic reviews. Syst Rev. 2016;5(1):140.","DOI":"10.1186\/s13643-016-0315-4"},{"key":"3101_CR24","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1016\/j.jclinepi.2020.11.003","volume":"133","author":"J Thomas","year":"2021","unstructured":"Thomas J, McDonald S, Noel-Storr A, Shemilt I, Elliott J, Mavergames C, et al. Machine learning reduced workload with minimal risk of missing studies: development and evaluation of a randomized controlled trial classifier for Cochrane Reviews. J Clin Epidemiol. 2021;133:140\u201351.","journal-title":"J Clin Epidemiol"},{"key":"3101_CR25","doi-asserted-by":"publisher","first-page":"401","DOI":"10.12688\/f1000research.51117.1","volume":"10","author":"L Schmidt","year":"2021","unstructured":"Schmidt L, Finnerty Mutlu AN, Elmore R, Olorisade BK, Thomas J, Higgins JPT. Data extraction methods for systematic review (semi)automation: update of a living systematic review. F1000Res. 2021;10:401.","journal-title":"F1000Res"},{"issue":"3","key":"3101_CR26","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1002\/jrsm.1398","volume":"11","author":"S Armijo-Olivo","year":"2020","unstructured":"Armijo-Olivo S, Craig R, Campbell S. Comparing machine and human reviewers to evaluate the risk of bias in randomized controlled trials. Res Synth Methods. 2020;11(3):484\u201393.","journal-title":"Res Synth Methods"},{"key":"3101_CR27","doi-asserted-by":"crossref","unstructured":"Alshami A, Elsayed M, Ali E, Eltoukhy A, T. Z. Harnessing the power of ChatGPT for automating systematic review process: methodology, case study, limitations, and future directions. Systems. 2023;11:351.","DOI":"10.3390\/systems11070351"},{"key":"3101_CR28","doi-asserted-by":"publisher","first-page":"106244","DOI":"10.1016\/j.ssci.2023.106244","volume":"167","author":"O Oviedo-Trespalacios","year":"2023","unstructured":"Oviedo-Trespalacios O, Peden A, Cole-Hunter T, Costantini A, Haghani M, Rod J, et al. The risks of using ChatGPT to obtain common safety-related information and advice. Safety Science. 2023;167:106244.","journal-title":"Safety Science."},{"issue":"1","key":"3101_CR29","doi-asserted-by":"publisher","first-page":"290","DOI":"10.1186\/s13643-024-02666-2","volume":"13","author":"AM O'Connor","year":"2024","unstructured":"O\u2019Connor AM, Clark J, Thomas J, Spijker R, Kusa W, Walker VR, et al. Large language models, updates, and evaluation of automation tools for systematic reviews: a summary of significant discussions at the eighth meeting of the International Collaboration for the Automation of Systematic Reviews (ICASR). Syst Rev. 2024;13(1):290.","journal-title":"Syst Rev"},{"key":"3101_CR30","doi-asserted-by":"crossref","unstructured":"Li F, Ruijs N, Y. L. Ethics & AI: a systematic review on ethical concerns and related strategies for designing with AI in healthcare. AI. 2023;4(1):28\u201353.","DOI":"10.3390\/ai4010003"},{"key":"3101_CR31","doi-asserted-by":"publisher","first-page":"542","DOI":"10.1016\/j.csbj.2024.08.005","volume":"24","author":"D Muhammad","year":"2024","unstructured":"Muhammad D, Bendechache M. Unveiling the black box: a systematic review of Explainable Artificial Intelligence in medical image analysis. Comput Struct Biotechnol J. 2024;24:542\u201360.","journal-title":"Comput Struct Biotechnol J"},{"key":"3101_CR32","unstructured":"TechTarget. BERT language model 2024. Available from: https:\/\/www.techtarget.com\/searchenterpriseai\/definition\/BERT-language-model."},{"issue":"2","key":"3101_CR33","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1016\/j.oneear.2023.12.011","volume":"7","author":"AJ Sietsma","year":"2024","unstructured":"Sietsma AJ, Theokritoff E, Biesbroek R, Canosa IV, Thomas A, Callaghan M, et al. Machine learning evidence map reveals global differences in adaptation action. One Earth. 2024;7(2):280\u201392.","journal-title":"One Earth"},{"issue":"11","key":"3101_CR34","doi-asserted-by":"publisher","first-page":"966","DOI":"10.1038\/s41558-021-01168-6","volume":"11","author":"M Callaghan","year":"2021","unstructured":"Callaghan M, Schleussner C-F, Nath S, Lejeune Q, Knutson TR, Reichstein M, et al. Machine-learning-based evidence and attribution mapping of 100,000 climate impact studies. Nat Clim Chang. 2021;11(11):966\u201372.","journal-title":"Nat Clim Chang"},{"key":"3101_CR35","unstructured":"EPPI Centre, . EPPI Reviewer 2024. Available from: https:\/\/eppi.ioe.ac.uk\/cms\/Default.aspx?tabid=2914."},{"key":"3101_CR36","unstructured":"EPPI Centre. EPPI-reviewer 4 software for research synthesis: user manual 2018."},{"key":"3101_CR37","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1186\/s13643-020-01324-7","volume":"9","author":"AY Tsou","year":"2020","unstructured":"Tsou AY, Treadwell JR, Erinoff E, Schoelles K. Machine learning for screening prioritization in systematic reviews: comparative performance of Abstrackr and EPPI-Reviewer. Syst Rev. 2020;9:73.","journal-title":"Syst Rev"},{"issue":"1","key":"3101_CR38","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1186\/s13643-020-01521-4","volume":"9","author":"MW Callaghan","year":"2020","unstructured":"Callaghan MW, Muller-Hansen F. Statistical stopping criteria for automated screening in systematic reviews. Syst Rev. 2020;9(1):273.","journal-title":"Syst Rev"},{"key":"3101_CR39","unstructured":"Microsoft. Copilot for Microsoft 365 2024. Available from: https:\/\/www.microsoft.com\/en-gb\/microsoft-365\/business\/copilot-for-microsoft-365?ef_id=_k_CjwKCAjwzIK1BhAuEiwAHQmU3iU1xH2bvbiFg83bqMv5ZS9CC_-b3PRKPOCRk8_KIES3gOWfYJa4ABoCgYsQAvD_BwE_k_&OCID=AIDcmmorqeo08r_SEM__k_CjwKCAjwzIK1BhAuEiwAHQmU3iU1xH2bvbiFg83bqMv5ZS9CC_-b3PRKPOCRk8_KIES3gOWfYJa4ABoCgYsQAvD_BwE_k_&gad_source=1&gclid=CjwKCAjwzIK1BhAuEiwAHQmU3iU1xH2bvbiFg83bqMv5ZS9CC_-b3PRKPOCRk8_KIES3gOWfYJa4ABoCgYsQAvD_BwE."},{"key":"3101_CR40","unstructured":"365 M. Microsoft Copilot for Microsoft 365 overview Microsoft 2024. Available from: https:\/\/learn.microsoft.com\/en-us\/copilot\/microsoft-365\/microsoft-365-copilot-overview."},{"key":"3101_CR41","unstructured":"Microsoft. Microsoft Copilot for Microstf 365 - best pracrices with SharePoint Microsoft 2024. Available from: https:\/\/learn.microsoft.com\/en-us\/sharepoint\/sharepoint-copilot-best-practices."},{"key":"3101_CR42","unstructured":"D. R. INGO experiences adopting Microsoft Copilot 2024. Available from: https:\/\/merltech.org\/july-10-2024-nlp-cop-session\/."},{"key":"3101_CR43","unstructured":"Sightsavers. Cataract evidence gap map 2021. Available from: https:\/\/research.sightsavers.org\/evidence-gap-maps\/cataract-gap-map\/."},{"issue":"3","key":"3101_CR44","doi-asserted-by":"publisher","first-page":"817","DOI":"10.1016\/j.survophthal.2021.09.004","volume":"67","author":"D Tognetto","year":"2022","unstructured":"Tognetto D, Giglio R, Vinciguerra AL, Milan S, Rejdak R, Rejdak M, et al. Artificial intelligence applications and cataract management: a systematic review. Surv Ophthalmol. 2022;67(3):817\u201329.","journal-title":"Surv Ophthalmol"},{"issue":"4","key":"3101_CR45","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1167\/tvst.13.4.20","volume":"13","author":"S Muller","year":"2024","unstructured":"Muller S, Jain M, Sachdeva B, Shah PN, Holz FG, Finger RP, et al. Artificial intelligence in cataract surgery: a systematic review. Transl Vis Sci Technol. 2024;13(4):20.","journal-title":"Transl Vis Sci Technol"},{"key":"3101_CR46","doi-asserted-by":"crossref","unstructured":"Bola\u00f1os F, Salatino A, Osborne F, Motta E. Artificial intelligence for literature reviews: opportunities and challenges. Artif Intell Rev. 2024;57(10):259.","DOI":"10.1007\/s10462-024-10902-3"},{"issue":"1","key":"3101_CR47","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1186\/s40537-024-00943-4","volume":"11","author":"M Mujahid","year":"2024","unstructured":"Mujahid M, K\u0131na E, Rustam F, Villar MG, Alvarado ES, De La Torre Diez I, et al. Data oversampling and imbalanced datasets: an investigation of performance for machine learning and feature engineering. J Big Data. 2024;11(1):87.","journal-title":"J Big Data."},{"issue":"6","key":"3101_CR48","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1007\/s10462-024-10759-6","volume":"57","author":"W Chen","year":"2024","unstructured":"Chen W, Yang K, Yu Z, Shi Y, Chen CLP. A survey on imbalanced learning: latest research, applications and future directions. Artif Intell Rev. 2024;57(6):137.","journal-title":"Artif Intell Rev."},{"key":"3101_CR49","unstructured":"Schroeder NL, Jaldi CD, S. Z. Large language models with human-in-the-loop validation for systematic review data extraction. Pre-print. 2025."},{"key":"3101_CR50","doi-asserted-by":"publisher","unstructured":"Gartlehner G, Kahwati L, Nussbaumer-Streit B, Crotty K, Hilscher R, Kugley S, et al. From promise to practice: challenges and pitfalls in the evaluation of large language models for data extraction in evidence synthesis.\u00a0BMJ Evid Based Med. 2025;30(6):385\u20139. https:\/\/doi.org\/10.1136\/bmjebm-2024-113199.","DOI":"10.1136\/bmjebm-2024-113199"},{"issue":"1","key":"3101_CR51","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/2046-4053-4-1","volume":"4","author":"D Moher","year":"2015","unstructured":"Moher D, Liberati A, Tetzlaff J, Altman DG, Group TP. Preferred reporting items for systematic review and meta-analysis protocols (PRISMA-P) 2015 statement. Syst Rev. 2015;4(1):1.","journal-title":"Syst Rev"},{"issue":"1-2","key":"3101_CR52","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1504\/IJCBDD.2013.052198","volume":"6","author":"S Jonnalagadda","year":"2013","unstructured":"Jonnalagadda S, Petitti D. A new iterative method to reduce workload in systematic review process. Int J Comput Biol Drug Des. 2013;6(1\u20132):5\u201317.","journal-title":"Int J Comput Biol Drug Des"},{"issue":"3","key":"3101_CR53","doi-asserted-by":"publisher","first-page":"470","DOI":"10.1002\/jrsm.1311","volume":"9","author":"P Przybyla","year":"2018","unstructured":"Przybyla P, Brockmeier AJ, Kontonatsios G, Le Pogam MA, McNaught J, von Elm E, et al. Prioritising references for systematic reviews with RobotAnalyst: a user study. Res Synth Methods. 2018;9(3):470\u201388.","journal-title":"Res Synth Methods"},{"key":"3101_CR54","unstructured":"World Bank. World Bank Country and Lending Groups 2025. Available from: https:\/\/datahelpdesk.worldbank.org\/knowledgebase\/articles\/906519-world-bank-country-and-lending-group."},{"key":"3101_CR55","unstructured":"Cumpston M, Flemyng E, Thomas J, Higgins JPT, Deeks JJ, MJ C. Chapter I: Introduction. In: Higgins JPT TJ, Chandler J, Cumpston M, Li T, Page MJ, Welch VA, editor. Cochrane handbook for systematic reviews of interventions version 65: cochrane 2024."},{"issue":"1","key":"3101_CR56","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1186\/s12874-017-0468-4","volume":"18","author":"Z Munn","year":"2018","unstructured":"Munn Z, Stern C, Aromataris E, Lockwood C, Jordan Z. What kind of systematic review should I conduct? A proposed typology and guidance for systematic reviewers in the medical and health sciences. BMC Med Res Methodol. 2018;18(1):5.","journal-title":"BMC Med Res Methodol"},{"key":"3101_CR57","unstructured":"Gartlehner G, Hansen RA, Nissman D, al. e. Criteria for distinguishing effectiveness from efficacy trials in systematic reviews. Rockville (MD): Agency for Healthcare Research and Quality (US). 2006."},{"issue":"11","key":"3101_CR58","first-page":"e864","volume":"8","author":"N Jahan","year":"2016","unstructured":"Jahan N, Naveed S, Zeshan M, Tahir MA. How to conduct a systematic review: a narrative literature review. Cureus. 2016;8(11):e864.","journal-title":"Cureus"},{"key":"3101_CR59","unstructured":"Cobino G. Why language models give different answers to the very same question? 2024. Available from: https:\/\/www.linkedin.com\/pulse\/why-language-models-give-different-answers-very-same-question-cobino-jpqic\/."}],"container-title":["Systematic Reviews"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13643-026-03101-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13643-026-03101-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13643-026-03101-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T10:37:08Z","timestamp":1774435028000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s13643-026-03101-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,17]]},"references-count":59,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["3101"],"URL":"https:\/\/doi.org\/10.1186\/s13643-026-03101-4","relation":{},"ISSN":["2046-4053"],"issn-type":[{"value":"2046-4053","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,17]]},"assertion":[{"value":"31 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 February 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"95"}}