Journal article · 2026 · Open access
Abstract No: 465 Assessment of Accuracy and Agreement of AI Tool in Risk of Bias Assessment: An Opportunity or Obstacle Towards AI-Assisted Systematic Reviews
Journal of Society of Indian Physiotherapists, 10(1), 89 · Published 1 January 2026 · DOI 10.4103/jsip.jsip_2026_vol_abstract_s9
In brief
“Abstract No: 465 Assessment of Accuracy and Agreement of AI Tool in Risk of Bias Assessment: An Opportunity or Obstacle Towards AI-Assisted Systematic Reviews” is a 2026 journal article by Josh Naga Vartha and 2 co-authors, published in Journal of Society of Indian Physiotherapists. OpenAlex counts 0 citations as of 18 November 2026. It is open access under a CC BY-NC-ND licence: the full text is free to read at Journal of Society of Indian Physiotherapists.
- Citations
- 0
- Authors
- 3
Abstract
Background: Systematic reviews (SRs) are foundational in evidence-based research. The assessment of risk of bias (ROB) in these reviews on randomized controlled trials (RCTs) is a critical yet labour-intensive step. With the advent of large language model like ChatGPT-5, there is increasing interest in automating aspects of this process to improve efficiency without compromising quality. Objective: To evaluate the accuracy and agreement of ChatGPT-5 in assessing ROB in RCTs with human experts in the ROB evaluation process. Methods: A total of 36 RCTs from three published systematic reviews were analyzed. Each RCT was assessed independently for ROB across multiple domains by both human experts and ChatGPT-5 using the RoB 2.0 tool. Cross-tabulation was used to study the level of association along with the likelihood ratio between the raters. Agreement was quantified using Cohen’s Kappa statistics and Systematic differences were evaluated via the McNemar-Bowker test. Results: The Pearson Chi-Square test was 3.920(P=0.417) and the likelihood ratio was 5.697(P=0.223). The overall observed agreement between human reviewers (O1) and ChatGPT-5 (O2) with a Cohen’s Kappa of 0.044 (p = 0.428). The McNemar-Bowker test confirmed a significant asymmetry in rating patterns (χ 2 = 24.33, df = 3, p < 0.001). Conclusion: ChatGPT-5 exhibits considerable variation in overall risk of bias (ROB) assessments compared to human reviewers, with a tendency to assign “moderate” ratings more liberally. Therefore, use of ChatGPT-5 as a standalone tool remains questionable. There is a need for further research to explore the influence of different prompts and Ai responses need to be standardized the prompts and reproducible a of ROB.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Vartha, J. N., M, J. S., & Raghumahanti, R. (2026). Abstract No: 465 Assessment of Accuracy and Agreement of AI Tool in Risk of Bias Assessment: An Opportunity or Obstacle Towards AI-Assisted Systematic Reviews. Journal of Society of Indian Physiotherapists, 10(1), 89. https://doi.org/10.4103/jsip.jsip_2026_vol_abstract_s9
MLA 9
Vartha, Josh Naga, et al. “Abstract No: 465 Assessment of Accuracy and Agreement of AI Tool in Risk of Bias Assessment: An Opportunity or Obstacle Towards AI-Assisted Systematic Reviews.” Journal of Society of Indian Physiotherapists, vol. 10, no. 1, 2026, p. 89. https://doi.org/10.4103/jsip.jsip_2026_vol_abstract_s9.
Chicago
Vartha, Josh Naga, John Solomon M, and Raghuveer Raghumahanti. 2026. “Abstract No: 465 Assessment of Accuracy and Agreement of AI Tool in Risk of Bias Assessment: An Opportunity or Obstacle Towards AI-Assisted Systematic Reviews.” Journal of Society of Indian Physiotherapists 10 (1): 89. https://doi.org/10.4103/jsip.jsip_2026_vol_abstract_s9.
Harvard
Vartha, J. N., M, J. S. and Raghumahanti, R. (2026) ‘Abstract No: 465 Assessment of Accuracy and Agreement of AI Tool in Risk of Bias Assessment: An Opportunity or Obstacle Towards AI-Assisted Systematic Reviews’, Journal of Society of Indian Physiotherapists, 10(1), p. 89. doi:10.4103/jsip.jsip_2026_vol_abstract_s9.
IEEE
J. N. Vartha, J. S. M, and R. Raghumahanti, “Abstract No: 465 Assessment of Accuracy and Agreement of AI Tool in Risk of Bias Assessment: An Opportunity or Obstacle Towards AI-Assisted Systematic Reviews,” Journal of Society of Indian Physiotherapists, vol. 10, no. 1, p. 89, 2026, doi: 10.4103/jsip.jsip_2026_vol_abstract_s9.
BibTeX
@article{vartha2026abstract,
title = {{Abstract No: 465 Assessment of Accuracy and Agreement of AI Tool in Risk of Bias Assessment: An Opportunity or Obstacle Towards AI-Assisted Systematic Reviews}},
author = {Vartha, Josh Naga and M, John Solomon and Raghumahanti, Raghuveer},
journal = {Journal of Society of Indian Physiotherapists},
year = {2026},
volume = {10},
number = {1},
pages = {89},
doi = {10.4103/jsip.jsip_2026_vol_abstract_s9},
url = {https://doi.org/10.4103/jsip.jsip_2026_vol_abstract_s9}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Social Sciences › Decision Sciences › Statistics, Probability and Uncertainty › Meta-analysis and systematic reviews
- risk of bias assessment
- ChatGPT-5
- large language models
- randomized controlled trials
- interobserver agreement
- human-AI comparison
Work with this paper
Most-cited papers in Decision Sciences
- The PRISMA 2020 statement: an updated guideline for reporting systematic reviewsMatthew James Page, Joanne E. McKenzie, Patrick M. Bossuyt and 23 more · BMJ · 2021 · 144,919 citations
- Evaluating Structural Equation Models with Unobservable Variables and Measurement ErrorClaes Fornell, David F. Larcker · Journal of Marketing Research · 1981 · 118,336 citations
- Cutoff criteria for fit indexes in covariance structure analysis: Conventional criteria versus new alternativesLi‐tze Hu, Peter M. Bentler · Structural Equation Modeling A Multidisciplinary Journal · 1999 · 117,461 citations
- Common method biases in behavioral research: A critical review of the literature and recommended remedies.Philip M. Podsakoff, SCOTT B. MACKENZIE, Jeong Yeon Lee and 1 more · Journal of Applied Psychology · 2003 · 89,248 citations
- Preferred reporting items for systematic reviews and meta-analyses: the PRISMA statementDavid Moher, Alessandro Liberati, Jennifer Tetzlaff and 2 more · BMJ · 2009 · 85,524 citations
Questions about this paper
How do I cite this paper in APA style?
Vartha, J. N., M, J. S., & Raghumahanti, R. (2026). Abstract No: 465 Assessment of Accuracy and Agreement of AI Tool in Risk of Bias Assessment: An Opportunity or Obstacle Towards AI-Assisted Systematic Reviews. Journal of Society of Indian Physiotherapists, 10(1), 89. https://doi.org/10.4103/jsip.jsip_2026_vol_abstract_s9
How many times has this paper been cited?
0 times, according to OpenAlex on 18 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at Journal of Society of Indian Physiotherapists: sign in and open the full text from this page.
Who wrote this paper?
Josh Naga Vartha, John Solomon M, Raghuveer Raghumahanti.
What is the DOI of this paper?
10.4103/jsip.jsip_2026_vol_abstract_s9, permanently at https://doi.org/10.4103/jsip.jsip_2026_vol_abstract_s9. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 18 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.