Leveraging artificial intelligence to enhance systematic reviews in health research: advanced tools and challenges
Open accessThe DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.
Abstract
Artificial Intelligence (AI) is transforming systematic reviews (SRs) in health research by automating processes such as study screening, data extraction, and quality assessment. This perspective highlights recent advancements in AI tools that enhance efficiency and accuracy in SRs. It discusses the benefits, challenges, and future directions of AI integration, emphasising the need for human oversight to ensure the reliability of AI outputs in evidence synthesis and decision-making in healthcare.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Other recent work has demonstrated promise for LLMs in data extraction 7,8”
From Automation of Systematic Reviews with Large Language Models (2025) · cites this paper as [7]
Experimental — accuracy not yet measuredThe check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“though these studies rely on self-defined reference standards and evaluate on small datasets.”
From Automation of Systematic Reviews with Large Language Models (2025) · cites this paper as [7]
Experimental — accuracy not yet measuredThe check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“This approach represented a methodological improvement over prior work that relied on self-created ground truths 7 .”
From Automation of Systematic Reviews with Large Language Models (2025) · cites this paper as [7]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
An open source machine learning framework for efficient and transparent systematic reviews
van de Schoot, R., de Bruin, J., Schram, R., Zahedi, P., de Boer, J., Weijdema, F., Kramer, B., Huijts, M., Hoogerwerf, M., Ferdinands, G., et al. (2021) · Nature Machine Intelligence · doi:10.1038/s42256-020-00287-7 · Cited by 1,157
Collins, G. S., Dhiman, P., Andaur Navarro, C. L., Ma, J., Hooft, L., Reitsma, J. B., Logullo, P., Beam, A. L., Peng, L., Van Calster, B., et al. (2021) · BMJ Open · doi:10.1136/bmjopen-2020-048008 · Cited by 852
Marshall, I. J., & Wallace, B. C. (2019) · Systematic Reviews · doi:10.1186/s13643-019-1074-9 · Cited by 638 · cited 2×
“Tools like RobotReviewer have high accuracy in extracting relevant details from randomised control trials (RCTs) [10].”
BackgroundMethodHarrison, H., Griffin, S. J., Kuhn, I., & Usher-Smith, J. A. (2020) · BMC Medical Research Methodology · doi:10.1186/s12874-020-0897-3 · Cited by 449 · cited 1×
“Several software tools support titles and abstract screening, with Abstrackr and Rayyan being the most validated [5, 6].”
MethodReducing Workload in Systematic Review Preparation Using Automated Citation Classification
Cohen, A. M., Hersh, W. R., Peterson, K., & Yen, P.-Y. (2006) · Journal of the American Medical Informatics Association · doi:10.1197/jamia.m1929 · Cited by 411 · cited 1×
“Since 2005, artificial intelligence (AI) tools have gained increasing attention [1] for their ability to automate these processes, offering increased efficiency and accuracy [2].”
BackgroundRobotReviewer: evaluation of a system for automatically assessing bias in clinical trials
Marshall, I. J., Kuiper, J., & Wallace, B. C. (2016) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocv044 · Cited by 317 · cited 1×
“For instance, RobotReviewer uses NLP to identify relevant text and assess the risk of bias in RCTs, achieving an accuracy rate of 71–78.3% [11], though it is less precise than Cochrane reviews.”
MethodInfluentialO’Connor, A. M., Tsafnat, G., Thomas, J., Glasziou, P., Gilbert, S. B., & Hutton, B. (2019) · Systematic Reviews · doi:10.1186/s13643-019-1062-0 · Cited by 167 · cited 1×
“The performance of these tools depends on the effectiveness of the underlying ML paradigms and algorithms, the quality and quantity of data used for training, and the degree of human involvement [9].”
MethodHamel, C., Kelly, S. E., Thavorn, K., Rice, D. B., Wells, G. A., & Hutton, B. (2020) · BMC Medical Research Methodology · doi:10.1186/s12874-020-01129-1 · Cited by 140 · cited 1×
“Several software tools support titles and abstract screening, with Abstrackr and Rayyan being the most validated [5, 6].”
MethodHow to optimize the systematic review process using AI tools
Fabiano, N., Gupta, A., Bhambra, N., Luu, B., Wong, S., Maaz, M., Fiedorowicz, J. G., Smith, A. L., & Solmi, M. (2024) · JCPP Advances · doi:10.1002/jcv2.12234 · Cited by 130 · cited 2×
“Since 2005, artificial intelligence (AI) tools have gained increasing attention [1] for their ability to automate these processes, offering increased efficiency and accuracy [2].”
BackgroundMethodEvaluating the effectiveness of large language models in abstract screening: a comparative analysis
Li, M., Sun, J., & Tan, X. (2024) · Systematic Reviews · doi:10.1186/s13643-024-02609-x · Cited by 125 · cited 1×
“0 API script achieved 96% screening specificity and 93% sensitivity when prompted with inclusion and exclusion criteria [13], showcasing the capability of base models without fine-tuning.”
Background
Cited by
Long-term air pollution exposure and incident dementia: a systematic review and meta-analysis
Rogowski, C. B. B., Bredell, C., Shi, Y., Tien-Smith, A. Z., Szybka, M., Fung, K. W., Hong, L., Phillips, V., Andersen, Z. J., Sharp, S. J., et al. (2025) · The Lancet Planetary Health · doi:10.1016/s2542-5196(25)00118-4 · Cited by 66
Leadership training in healthcare: a systematic umbrella review
Phillipson, J., Pinto, A. C., Kingsley‐Smith, H., Krachler, N., McGivern, G., & Lyons, O. (2025) · BMJ Leader · doi:10.1136/leader-2025-001269 · Cited by 51
“105 However, these tools currently lack the nuanced judgement and contextual understanding required for independent assessments.”
Andersen, T. H., Marcussen, T. M., Termannsen, A., Lawaetz, T. W. H., & Nørgaard, O. (2025) · Cochrane Evidence Synthesis and Methods · doi:10.1002/cesm.70036 · Cited by 63
Automation of Systematic Reviews with Large Language Models
Cao, C., Arora, R., Cento, P., Budak, A., Manta, K., Farahani, E., Cecere, M., Selemon, A., Sang, J., Gong, L. X., et al. (2025) · medRxiv · doi:10.1101/2025.06.13.25329541 · Cited by 33
Artificial Intelligence in Uveitis: Innovations in Diagnosis and Therapeutic Strategies
Murugan, S., Sanjay, S., Somanath, A., Mahendradas, P., Patil, A., Kaur, K., & Gurnani, B. (2024) · Clinical ophthalmology · doi:10.2147/opth.s495307 · Cited by 26
Chatbots for conducting systematic reviews in pediatric dentistry
Rokhshad, R., Mohammad, F. D., Nomani, M., Mohammad‐Rahimi, H., & Schwendicke, F. (2025) · Journal of Dentistry · doi:10.1016/j.jdent.2025.105733 · Cited by 23
Daraqel, B., Owayda, A., Khan, H., Koletsi, D., & Mheissen, S. (2025) · Journal of Dentistry · doi:10.1016/j.jdent.2025.105846 · Cited by 17
Kallmes, K. M., Thurnham, J., Sauca, M., Tarchand, R., Kallmes, K. R., & Holub, K. J. (2025) · Cochrane Evidence Synthesis and Methods · doi:10.1002/cesm.70059 · Cited by 17
RetractedOn the ethical and moral dimensions of using artificial intelligence for evidence synthesis
Bhaumik, S. (2025) · PLOS Global Public Health · doi:10.1371/journal.pgph.0004348 · Cited by 14
“[2 –10] While AI is being increasing used for evidence synthesis in health and medicine, [11, 12] there are no articles examining ethical and moral dimensions of AI use for conducting evidence synthesis.”
Hu, M., Koh, P. S., Soh, X. C., Hartanto, A., & Majeed, N. M. (2026) · Behavior Research Methods · doi:10.3758/s13428-026-02961-x · Cited by 11
“Overall, while AI tools offer promising ways to enhance the efficiency of the systematic review process, their outputs should be regarded as complementary to, rather than substitutes for, human expertise (Bernard et al., 2025; Ge et al., 2024).”
Pacheco, R. J. P., Caicedo–Quiroz, R., Caraballo, G. D. L. C. M., Monteses, J. J. B., Miranda, L. C. B., & Gabela, J. R. A. (2025) · Data & Metadata · doi:10.56294/dm20251103 · Cited by 9
Naylor, N. R., Hummel, N., de Moor, C., & Kadambi, A. (2025) · Clinical and Translational Science · doi:10.1111/cts.70206 · Cited by 6
“NLP algorithms can assist in the initial stages of SLRs by scanning large datasets of publications to identify relevant studies using a variety of schemes, including Generative Pre-Trained Transformer 4 (GPT-4) and other AI classifiers [3].”
InfluentialAI in Marketing Education: Capabilities required of Marketers today
Weege, M., & Zweigle, T. M. (2025) · IU Discussion Papers Marketing und Kommunikation · doi:10.56250/4049 · Cited by 9
Film Production Artificial Intelligence Use
Davaasambuu, T. (2025) · Art and Design Review · doi:10.4236/adr.2025.133016 · Cited by 7
Kwon, C. (2025) · Integrative Medicine Research · doi:10.1016/j.imr.2025.101217 · Cited by 6
“As Li et al. (2024) emphasized, the use of large language models allows researchers and clinicians to access the latest evidence more quickly 17 , which is especially important for clinical decision support in fields such as pharmacopuncture where research results are distributed and published in…”
Performance of AI Tools in Citing Retracted Literature : Content Analysis
Labenbacher, S., Niederer, M., Hammer, S., Bader, M., Schreiber, N., & Bornemann-Cimenti, H. (2026) · Journal of Medical Internet Research · doi:10.2196/88766 · Cited by 5
“Similarly, Jan et al [10] and Ge et al [6] have shown that GenAI tools frequently fabricate or misattribute citations during literature summarization tasks.”
Verdonschot, R. G., Dilles, T., Cahir, C., Graef, M. D., Holis, R. V., Frydenlund, J., Denig, P., Grimes, T., Karapinar‐Çarkit, F., & Schor, M. (2026) · Systematic Reviews · doi:10.1186/s13643-026-03185-y · Cited by 7
Chan, V. T. T., Mak, A. C. Y., Agrawal, R. V., Biswas, J., Bodaghi, B., Chan, C. K. M., Chee, S.-P., Chi, W., Cordero‐Coma, M., Gupta, V., et al. (2025) · Asia-Pacific Journal of Ophthalmology · doi:10.1016/j.apjo.2025.100261 · Cited by 5
Self-citationHunter, R. L., Booth, A., & Wood, L. (2026) · BMC Medical Research Methodology · doi:10.1186/s12874-026-02814-3 · Cited by 6
“Studies such as Ge et al. [30] and Gwon et al. [31] high-light similar dynamics in other evidence synthesis contexts, where AI accelerates routine tasks like screening but requires human oversight for rigour and contextual interpretation.”
Case Studies on the Use of AI in Literary Research and Academic Studies
Rani, J., Guru, R., & Santhanam, S. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-6330-1.ch001 · Cited by 4
From reviews to real-time: dynamic evidence in dentistry
Gavrilova, A. V., & Galli, C. (2026) · Evidence-Based Dentistry · doi:10.1038/s41432-026-01206-2 · Cited by 4
Implementation of artificial intelligence (AI) in ASD treatment
Chatzis, K. D., Tretiakov, P. S., & Passias, P. G. (2025) · North American Spine Society Journal (NASSJ) · doi:10.1016/j.xnsj.2025.100787 · Cited by 5
“Recent scoping reviews high-light that while LLMs can support up to 10 of 13 systematic review steps, fully validated and established applications that match the gold-standard human-led reviews do not yet exist [ 16–18 ].”
Shereefdeen, H., Thaivalappil, A., Young, I., & MacKay, M. (2025) · INQUIRY The Journal of Health Care Organization Provision and Financing · doi:10.1177/00469580251399374 · Cited by 3
“31 In particular, DistillerSR, a reference management software, integrates AI into their screening and data extraction capabilities, 32 with promise shown for screening efficiency.”
Gao, Y., Qi, L., & Tongwu, Y. U. (2026) · Frontiers in Public Health · doi:10.3389/fpubh.2026.1743075 · Cited by 4
“The study selection process followed a systematic two-stage approach using the EPPI-Reviewer version 6 web platform to ensure transparency and reproducibility (37, 38).”
Development of living evidence-informed guidelines, part 1
Martins-Pfeifer, C. C., Bhosale, A. S., Zhang, L., Urquhart, O., Verdugo‐Paiva, F., Glick, M., & Carrasco‐Labra, A. (2026) · The Journal of the American Dental Association · doi:10.1016/j.adaj.2025.09.014 · Cited by 11
Corrao, S., Tuccinardi, D., & Baratta, R. (2026) · Obesity Reviews · doi:10.1111/obr.70155 · Cited by 3
Artificial intelligence adoption by allied health professionals: a scoping review
Morris, M. E., Raghunathan, K., Peiris, C. L., Gilmartin‐Thomas, J., Heng, H. W. F., McKercher, J. P., Edvardsson, K., Ho, K. H. M., Johnston, J., Bourke, S., et al. (2026) · European Journal of Physiotherapy · doi:10.1080/21679169.2026.2665430 · Cited by 3
Uncovering the Mechanisms of Organisational Resilience: A Critical Realist Systematic Review
Mahmoud, M., Chan, K. C., & Ally, M. (2026) · Sustainability · doi:10.3390/su18105003 · Cited by 3
Amer, M. R., Møller, M. H., Granholm, A., Alotaibi, H. F., AlMuhaidib, S., Duhailib, Z. A., Arafat, A. A., Chew, M. S., Rehn, M., Sigurdsson, M. I., et al. (2025) · Acta Anaesthesiologica Scandinavica · doi:10.1111/aas.70036 · Cited by 3
Yao, X., Saha, A., Low, A., Ahmed, S., Ali, S., Misra, A., Abdelmalek, M., Saravanan, S., & SUSSMAN, J. S. (2025) · Intelligent Medicine · doi:10.1016/j.imed.2025.12.008 · Cited by 3
Encouraging Authors to Embrace AI in Research and Writing
Antel, R., & Ingelmo, P. M. (2025) · Pediatric Anesthesia · doi:10.1111/pan.15084 · Cited by 3
“AI-based tools can also improve the accuracy and comprehensiveness of literature searches, as well as streamline the identification and filtering of studies [5].”
Artificial Intelligence in Uveitis: A 360-Degree Perspective
Agrawal, R. V., See, A. U., Kiosia, A., & Gupta, V. (2026) · Ocular Immunology and Inflammation · doi:10.1080/09273948.2025.2612107 · Cited by 3
“17 Additionally, AI-enabled virtual case conferences can integrate multimodal data, including imaging, laboratory results, and systemic information, to create immersive discussion platforms that mirror real-world complexity.”
Self-citationSiegel, M., Fanninger, S., Riedel, J., & Zemp, M. (2025) · Frontiers in Psychology · doi:10.3389/fpsyg.2025.1535606 · Cited by 2
Assessing TDApp: An AI-based clinical decision support system for ADHD treatment recommendations
Baykova, E., Raya, Ò., Lombardía, C., Gonzalvo, B., Andreu, I., Losada, D., Falkenhain, T., Cunill, R., Serrano, D., Comas, D. R., et al. (2025) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2025.1582746 · Cited by 5
Watson, J. C., Leeth, C. K., Wong, K., & Schroeder, J. (2025) · Journal of Counselor Preparation and Supervision · doi:10.70013/pbsrlnat · Cited by 2
Lai, H., Ma, N., Zhao, W., Liu, J., Pan, B., Tian, J., Chen, Y., Ma, B., Shang, H., Liu, J., et al. (2025) · Chinese Science Bulletin (Chinese Version) · doi:10.1360/csb-2025-5395 · Cited by 2
Self-citationJay, M., Morgan, M., Straus, S. E., Wilson, E., Sutradhar, R., Yu, C., Conn, L. G., Dharma, C., Lipscombe, L. L., & Eskander, A. (2026) · JMIR Research Protocols · doi:10.2196/90588 · Cited by 3
“AI use in SRs is often poorly disclosed, with important details (tool identity, model version, stage of use, prompts, or oversight) frequently omitted, limiting reproducibility and bias appraisal [20].”
L-PRISMA: An Extension of PRISMA in the Era of Generative Artificial Intelligence (GenAI)
Shailendra, S., Kadel, R., Sharma, A., Islam, M. T., & Saxena, U. R. (2025) · International Conference on Modern Educational Technology (ICMET) · doi:10.1109/icmet67594.2025.11452106 · Cited by 2
“Purely AI-driven pipelines risk errors and lack robustness [25] Proposes combining statistical pre-screening with AI methods to balance efficiency with reproducibility, ensuring methodological soundness.”
“Can a chatbot be used in the full-text screening in a systematic review?”
Martins, A. M., Juan, L. F. V., Oliveira, A., Martins, J. P., & Santos, M. (2026) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2026.106422 · Cited by 3
Evaluating the performance of a custom GPT in full text screening of a systematic review
Davis, R. C., List, S. S., Chappell, K. G., Madar, A., Henjum, S., & Heen, E. (2026) · Scandinavian Journal of Public Health · doi:10.1177/14034948261423410 · Cited by 2
Revolutionizing Retail Operations through Generative AI: A Systematic Review
Chowdhury, A. G., Bandapati, G., & Chilakapati, P. (2025) · International Journal of Computer Applications · doi:10.5120/ijca2025924834 · Cited by 1
The meta-analysis and systematic review mirage: when data synthesis becomes data distortion
Sonis, S. T., & Villa, A. (2025) · Supportive Care in Cancer · doi:10.1007/s00520-025-09615-2 · Cited by 1
Ali, H., & Ali, U. (2025) · Cureus · doi:10.7759/cureus.93644 · Cited by 1
Anih, D. C., Okorocha, U. C., Tayo-Ladega, O. T., Onichabor, J. O., Njideka, U. H., Apata, C. O., & Tarshi, M. W. (2025) · International journal of research and scientific innovation · doi:10.51244/ijrsi.2025.1210000242 · Cited by 1
Halis, A., & Ibrahim, H. (2025) · Canadian Urological Association Journal · doi:10.5489/cuaj.9302 · Cited by 1
Arroqui, C., Berradre, M. N., Fernández‐Pan, I., Beriain, M. J., Ibáñez, F. C., & Vírseda, P. (2025) · Trends in Food Science & Technology · doi:10.1016/j.tifs.2025.105518 · Cited by 1
The Promise of Artificial Intelligence to Aid in Systematic Reviews: An Examination of Scopus AI
Madsen, L. T., John C. Carter, M., Sheeba Cantanelli, M., Christine Hong, P., & Bazzell, A. F. (2026) · Journal of the Advanced Practitioner in Oncology · doi:10.6004/jadpro.2026.17.7.10 · Cited by 1
D’Andrea, F., Bartels, S. L., Markaryan, M., Masterson‐Algar, P., Bernal, A. N., de Bruin, S. R., Chirico, I., Flynn, A., Garcia, L., Gebhard, D., et al. (2026) · BMJ Open · doi:10.1136/bmjopen-2025-114584 · Cited by 1
“41 42 Below, we provide detailed descriptions of the screening and selection process, as well as the specific roles of these AI tools and the check validation activity.”
How Can Large Language Models Improve Health Research Skills: A Perspective Study
Montazeri, M., Ahmadian, L., Dinari, F., & molaei, K. (2026) · Health Science Reports · doi:10.1002/hsr2.72261 · Cited by 1
Ye, Y., Colombo, M., Meessen, J. M. T. A., Hajizadeh, N., Vore, L. D., Sigarchian, H. G., Peters, C., Krovvidi, S., Meresh, S., Hasson, L., et al. (2026) · European Heart Journal - Digital Health · doi:10.1093/ehjdh/ztag070 · Cited by 1
“5,12 Besides, the rapid evolution of models requires evaluation frameworks that emphasize reproducibility, benchmarking procedures, and the ability to up-date assessments as models evolve.”
Aldalou, M., Brooks, W. S., Rush, E., Landry-Wegener, B., Bills, C. B., Cook, D. A., Swope, J., & Wilson, A. B. (2026) · AEM Education and Training · doi:10.1002/aet2.70189 · Cited by 1
“While early applications are encouraging, the use of GenAI for appraising research quality remains in its infancy and requires further validation [8, 9].”
Wang, X., Dadashipour, F., Basori, Maeda, Y., & Richardson, J. C. (2026) · Educational Technology Research and Development · doi:10.1007/s11423-026-10629-8 · Cited by 1
“While automation can reduce repetitive workload (Ge et al., 2024 ), its development and effec - tiveness are uneven across different stages of the review process (Tóth et al., 2024 ).”
Zou, Y., Kim, I., Gao, N., Li, M., Kim, M., & Ge, J. (2026) · npj gut and liver. · doi:10.1038/s44355-026-00068-w · Cited by 1
Lee, K. H., Kim, H., Yang, D. S., Yoon, W. S., & Rim, C. H. (2026) · Journal of Epidemiology · doi:10.2188/jea.je20260233 · Cited by 1
Kurian, N., Cherian, J. M., Reji, R. M., & Varghese, K. G. (2026) · Evidence-Based Dentistry · doi:10.1038/s41432-026-01238-8 · Cited by 1
Comparing artificial intelligence versus human screening in systematic reviews
Gorici, M., Espin, A. T., & Oremus, M. (2026) · Health and Quality of Life Outcomes · doi:10.1186/s12955-026-02642-5 · Cited by 1
Turki, H., Pasha, N. A., Altammami, A., & Alzahrani, A. (2025) · Research Square · doi:10.21203/rs.3.rs-7660197/v1 · Cited by 1
Trends in AI and Human-AI Interaction in Clinical Trials -- A Hybrid Human-AI ExplorationPreprint
Woolley, S. I., Collins, T., Khattak, K. A., Chernomorets, I., Arevalo, A., & Richardson, C. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.29096 · Cited by 1
“…to its use in healthcare and other domains, AI has been increasingly used to support the time-consuming processes of systematic reviews, from identification and screening prioritization [14,15], with more recent work moving towards human-overseen automation and AI-enhanced review workflows [16,17].”
VICTORIOUS: A Visual Analytics System for Scoping Review of Document Sets
Haghighati, A., Haghverdi, A. R., & Sedig, K. (2025) · Multimodal Technologies and Interaction · doi:10.3390/mti9050037
Carrillo, B., Rubinos-Cuadrado, M., Parellada-Martin, J., Palacios-López, A., Carrillo-Rubinos, B., Canillas, F., Cortés, J. J. B., & Gómez‐Pavón, J. (2025) · JMIR Formative Research · doi:10.2196/75215
“It also raises important questions about the continued necessity of highly complex search protocols, suggesting that AI-assis-ted models may offer comparable effectiveness in certain contexts [61-63].”
A 25-year retrospective of Canadian plastic surgery research and its influence: a bibliometric study
Ordaz, D. J. G., Tai, P., Lalonde, A., Cordoba, M., Delisle, É., Nguyen, S., Brañes, R., Mozafarinia, M., & Cordoba, C. (2025) · Canadian Journal of Surgery · doi:10.1503/cjs.012024
“31 Ethical considerations, such as algorithmic bias and accessibility disparities, must also be addressed to ensure equitable AI integration in academia.”
New Frontiers in Health Service Evaluation: Navigating Health, Agency, and Artificial Intelligence
Kaehne, A., & Feather, J. (2025) · Springer eBooks · doi:10.1007/978-3-031-87869-5_30
Evidence map of oesophageal surgery: protocol for a living systematic review and meta-analysis
Benignus, C., Schiedeck, T. H. K., Avramovska, I., Evers, L. M., Giulini, L., Heger, P., Diener, M. K., & Hüttner, F. J. (2025) · BMJ Open · doi:10.1136/bmjopen-2025-105457
“32 Additionally, natural language processing (NLP) algorithms could help identify trends, highlight inconsistencies in the literature and even predict emerging research gaps.”
Ng, J. Y. (2025) · Perspectives on Integrative Medicine · doi:10.56986/pim.2025.10.001
“By using structured prompts, researchers can train GenAI models to extract quantitative data from studies, thus, enabling more efficient meta-analytical assessments [9,10].”
Gacek, Z., & Limé, M. (2025) · DiVA (University of Gävle)
IA Generativa vs. PubMed ¿Qué herramienta es más efectiva para buscar información científica?
Coma-Campmany, I., Basagaña Farrés, M., Caro Benito, C., Zaborras, R., Montcusí Puig, C., & Carles Pomar, M. À. (2025) · Dipòsit Digital de Documents de la UAB (Universitat Autònoma de Barcelona)
What Does Positive Social Functioning Entail for Emerging Adults? A Scoping Review.
Kreider, C., Medina, S., Mburu, S. N., DiFino, S. M., Klumpp, A., Morgan-Daniel, J., & Chou, C.-C. (2025) · OTJR: Occupation, Participation and Health · doi:10.1177/15394492251403413
Bansal, A., Sletten, I. S. K., Le, T. T., Tollefsen, S., Shannon, J. P., Cox, R. J., Pathirana, R. D., UiB-CEPI Group, Beglerovic, M., Blomberg, B., et al. (2026) · Systematic Reviews · doi:10.1186/s13643-025-03051-3
“We will utilise tools such as Rayyan and Covidence; however, we are currently exploring additional platforms—includ-ing Scispace, SWIFT–Review, ASReview LAB, and similar AI-assisted tools—to support the systematic review process [16].”
Alili, M. E., van de Laar, C., de Greeff, J., Vromans, J. G. F., van Asten, F., & Bosmans, J. E. (2026) · Ophthalmology and Therapy · doi:10.1007/s40123-025-01301-0
“This ensured full human oversight and verification of all extracted data [27].”
Uysal, J., LaNasa, K. H., Kully, G., Pearson, E., McDougal, L., & Hay, K. (2026) · Research Square · doi:10.21203/rs.3.rs-8716367/v1
Akram, C. M. (2026) · International Journal of Integrative Studies (IJIS) · doi:10.63856/2y4hk640
“In addition to popular sentiment analysis tools, there are increasing efforts to adopt NLP-based and generative AI tools for automating literature review, summarization, and research synthesis [2,4,14,30] .”
InfluentialMethodological Quality of Umbrella Reviews in Paediatric Dentistry: A Cross-Sectional Study
Gopinath, V. K., Govindaraju, L., Pulikkotil, S. J., Narasimhan, S., Shetty, R. M., Faggion, C. M., Dummer, P. M. H., & Nagendrababu, V. (2026) · International Dental Journal · doi:10.1016/j.identj.2026.109502 · Cited by 1
Khadse, S., Sajitha, A., V, & Joshi, N. (2026) · International Journal of Integrative Studies (IJIS) · doi:10.63856/sk3jd948
Mukuna, K. R. (2026) · International Journal of Studies in Systematic Reviews · doi:10.66434/ijssr.v1i1.538 · Cited by 1
Ahn, S., Kim, S., & Valdes, J. (2026) · Springer international handbooks of education · doi:10.1007/978-3-031-88898-4_24-1
Uranbey, Ö., Özbey, F., & Kaygisiz, Ö. F. (2026) · Scientific Reports · doi:10.1038/s41598-026-50239-1
Validation of an AI‐Assisted Framework for Systematic Bias Assessment in Observational Studies
Etminan, M., Rezaeianzadeh, R., & Douros, A. (2026) · Journal of Evaluation in Clinical Practice · doi:10.1111/jep.70593
Manoharan, J., & Sehgal, Y. (2026) · Journal of Medico Informatics · doi:10.64659/jomi/215260 · Cited by 2
Akalin, B., Topal, C., & Canat, L. (2026) · Research Square · doi:10.21203/rs.3.rs-9941676/v1
Thomas, G., Alley, S., Browne, M., Baumann, H., Duncan, M. J., Vandelanotte, C., & Gilson, N. D. (2026) · Digital Health · doi:10.1177/20552076261455158
“Consistent with Ge et al., 10 we caution against over-reliance on AI as a decision-maker.”
Bonilla, H. A. M., & Tudela, J. M. O. (2026) · Contemporary Educational Technology · doi:10.30935/cedtech/18870
Zhai, J., & Aryadoust, V. (2026) · Innovation in Language Learning and Teaching · doi:10.1080/17501229.2026.2698703
Munguía‐Realpozo, P., Ramírez‐Lara, E., Pinto, C. M., Etchegaray‐Morales, I., Solís-Poblano, J. C., Trinidad-González, M. A., Ayón-Aguilar, J., García-Flores, M. A., & Montiel-Jarquín, Á. J. (2026) · Digital Health · doi:10.1177/20552076261467480
Can Artificial Intelligence Literature Review Tools Provide Reliable Overviews?
Allagui, B. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-32112-1_2
Artificial Intelligence in Medical Writing – Promise, Pitfalls, and the Need for Balance
Garg, R. K. (2026) · Neurology India · doi:10.4103/neurol-india.neurol-india-d-25-00793
dos Santos, A. A., & dos Santos, V. M. L. (2026) · Artefactum · doi:10.23900/artefactum.v25i5.3374
La IA y el acceso a la información médica. ¿Un nuevo método revolucionario o un complemento?
García, V. M. N. (2026) · Innova medica revista de innovación docente de la Facultad de Medicina de Sevilla · doi:10.12795/innovamedica.2026.i01.01
Parkington, K. B., Joseph, J. T., Musleh, K., Rouleau-Tang, M., Persaud, A., Rueda, A., Teferra, B. G., Al-Shamali, H. F., Mao, W., Nezhad, F. G., et al. (2026) · PLOS Digital Health · doi:10.1371/journal.pdig.0001666
“Signal detection theory [22,39,54] was applied as a standardized comparative benchmarking framework to evaluate GPT-5 mode variant outputs relative to the consensus-based human reference workflow; however, operationalization varied according to task structure and evaluability.”
Evaluating AI Performance in Systematic Literature Reviews for HEOR: A Case Study
Wang-Silvanto, J., Jajoo, M., Guo, H., Ohri, R., Nelissen, J., & Comabella, C. C. I. (2026) · Journal of health economics and outcomes research · doi:10.36469/001c.165173 · Cited by 1
Schiffman, J. E., Wislocki, K. E., Petti, E., Bridgwater, M. A., Hegwood, C. M., Sharif, S., Giljen, M., Boos, A. K., Coscolluela, S., Martin, E. A., et al. (2026) · Schizophrenia Bulletin · doi:10.1093/schbul/sbaf259
“25 , 26 In alignment with past recommendations, this review employed manual over-sight by the research team during the extraction process.”
Alenzuela, R., & Alenzuela, R. H. (2026) · Libri · doi:10.1515/libri-2025-0042
“The study revealed that by automating essential tasks such as study screening, data extraction, and quality assessment, these tools not only streamline the work fl ow but also enhance the overall e ffi ciency and accuracy of systematic reviews (Ge et al. 2024).”
Steijger, D. J. M., Thissen, S., Aarts, S., Verbeek, H., de Vugt, M. E., & Christie, H. L. (2026) · JMIR Formative Research · doi:10.2196/84989
“…is no solid overview of how well active learning-based screening tools perform in the title and abstract screening process [23], and previous evaluations show that performance varies across review topics, data-set size, model configurations, prior knowledge strategies, and stopping rules [7,19,37].”
Marco-Pérez, I., Pérez, B., & Rubio, Á. L. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-36587-3_13
Who else cares? A conceptualization of non-investor and non-workforce perspectives on downsizing
Veigel, M., & Kanbach, D. K. (2026) · Management Review Quarterly · doi:10.1007/s11301-026-00631-y
AI-agents in de onderzoekscyclus: een praktische handleiding voor het versnellen van scoping reviews
Witte, L. P. W., Ribbert, L., Frijns, F., & van Toorenburg, E. (2026) · Tijdschrift voor Urologie · doi:10.1007/s13629-026-00507-6
Kaza, L. V. C., R, P. S., Naffa', R., Patel, S., & Manickam, S. (2026) · Pediatric Radiology · doi:10.1007/s00247-026-06775-z
Rocca, M., Noviello, D., Amoroso, C., Vecchi, M., Caprioli, F., & Facciotti, F. (2026) · Research Square · doi:10.21203/rs.3.rs-10919084/v1
Evidence map of open abdomen treatment: protocol for a living systematic review and meta-analysis
Benignus, C., Marquardt, C., Schiedeck, T. H. K., Probst, P., Müller-Kühnle, J., Diener, M., Huettner, F. J., & Schaaf, S. (2026) · Innovative Surgical Sciences · doi:10.1515/iss-2026-0029
Shi, B., Zhang, H., & Zhang, L. (2026) · Artificial Intelligence in Applied Sciences · doi:10.69882/adba.ai.2026023
“…questions (“What was the mean shoot biomass for the treatment group in Figure 2?") and the model, powered by a GPT-based engine, will attempt to locate and extract the answer (Ge et al. 2024 zobacteria, plant growth, soil chemistry), which often features a mix of laboratory and field contexts.”
Metadata
- Authors
- Ge, L., Agrawal, R., Singer, M., Kannapiran, P., De Castro Molina, J. A., Teow, K. L., Yap, C. W., & Abisheganaden, J. A.
- Affiliations
- National Skin Centre (SG)
- Tan Tock Seng Hospital (SG)
- Yale University (US)
- Corresponding author
- Ge, Lixia
- Venue
- Systematic Reviews
- Published
- 2024-10-25
- Volume
- 13
- Issue
- 1
- Pages
- 269-269
- ISSN
- 2046-4053 (ISSN-L)
- PMC
- PMC11504244
- OpenAlex
- W4403778417
- Cited by
- 92
- References
- 13
- Citations by year
- 2026: 53 · 2025: 38 · 2024: 1
- FWCI
- 11.61
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by-nc-nd
- creativecommons.org/licenses/by-nc-nd/4.0 (tdm)
- creativecommons.org/licenses/by-nc-nd/4.0 (vor)
- Locations
- Systematic Reviews (publishedVersion, cc-by-nc-nd)
- PubMed Central (publishedVersion, cc-by-nc-nd)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- Topics
- Social Sciences › Decision Sciences › Statistics, Probability and Uncertainty › Meta-analysis and systematic reviews
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Social Sciences › General Social Sciences › Computational and Text Analysis Methods
- Keywords
- artificial intelligence, automated data extraction, quality assessment, evidence synthesis, human oversight, healthcare decision-making, AI tools
- MeSH terms
- Systematic Reviews as Topic, Artificial Intelligence, Humans, Reproducibility of Results, Biomedical Research
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.