Jaswanth Gorla

Jaswanth Gorla

Auto-generated profile, based on publicly available information

Jaswanth Gorla

Temerty Faculty of Medicine, University of Toronto, Toronto, ON, Canada

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 June 2025 in medRxiv
Verified
Preprint
Open access
PDF file
CCChristian Cao
Christian Cao
RARohit Arora
Rohit Arora
PCPaul Cento
Paul Cento
ABAdil Budak
Adil Budak
KMKatherine Manta
Katherine Manta
IBIsabelle Boutron
Isabelle Boutron
Importance: Systematic reviews (SRs) inform evidence-based decision making. Yet, many take over a year to complete, are labor intensive, prone to human error, and face reproducibility challenges; thus limiting access to timely and reliable information. Objective: To validate a large language model (LLM)-based workflow (otto-SR) to automate three of the most labour intensive tasks in performing SR’s: article screening, data extraction, and risk of bias assessment; and to assess its feasibility in rapidly updating existing reviews. Design, setting, and participants: We conducted a validation study in four phases, with direct benchmarking against graduate-level human researchers in phases 1 and 2. Phase 1: article screening performance was measured across 32,357 citations from 5 systematic reviews. The reference standard consisted of the original reviews’ screening decisions after full-text screening. Phase 2: data extraction performance was measured across 4,495 data points from 495 studies in 7 reviews. Phase 3: risk of bias assessment (ROB2, Newcastle-Ottawa, QUADAS2) performance was measured across 345 studies from 12 reviews. Reference standards for Phase 2 and Phase 3 were created after blinded adjudication of the original review extraction and RoB assessments. Phase 4: otto-SR was used to reproduce and update the primary analysis from an issue of Cochrane reviews (n=12 reviews, 146,276 citations), with analytical comparisons to the original meta-analyzed findings. All discrepancies underwent dual human review. Results: otto-SR showed high performance in phase 1 article screening ( otto-SR : 96.7% sensitivity, 97.9% specificity; human: 81.7% sensitivity, 98.1% specificity) and phase 2 data extraction ( otto-SR : 93.1% accuracy; human: 79.7% accuracy). In phase 3, otto-SR demonstrated high interrater reliability for risk of bias judgements (ROB2 0.98, Newcastle-Ottawa 0.95, QUADAS2 0.74; Gwet AC2). In phase 4, otto-SR , reproduced and updated the primary analysis from an issue of Cochrane reviews. Across Cochrane reviews, otto-SR incorrectly excluded a median of 0 studies (IQR 0 to 0.25), and found nearly twice as many eligible studies compared to the original authors (n= 114 vs. 64). Meta-analyses based on otto-SR generated screening and extraction outputs, subsequently verified through dual human review, yielded newly statistically significant effect estimates in 2 reviews and negated significance in 1 review. Conclusions and relevance: LLMs have high performance in article screening, data extraction, and risk of bias assessments. They can rapidly reproduce and update existing systematic reviews, laying the foundation for automated, scalable, and reliable evidence synthesis.

3 June 2024 in medRxiv
Verified
Preprint
Open access
PDF file
CCChristian Cao
Christian Cao
JSJason Sang
Jason Sang
RARohit Arora
Rohit Arora
RKRobbie Kloosterman
Robbie Kloosterman
MCMatt Cecere
Matt Cecere
NBNiklas Bobrovitz
Niklas Bobrovitz
Systematic reviews (SRs) are the highest standard of evidence, shaping clinical practice guidelines, policy decisions, and research priorities. However, their labor-intensive nature, including an initial rigorous article screen by at least two investigators, delays access to reliable information synthesis. Here, we demonstrate that large language models (LLMs) with intentional prompting can match human screening performance. We introduce Framework Chain-of-Thought, a novel prompting approach that directs LLMs to systematically reason against predefined frameworks. We evaluated our prompts across ten SRs covering four common types of SR questions (i.e., prevalence, intervention benefits, diagnostic test accuracy, prognosis), achieving a mean accuracy of 93.6% (range: 83.3-99.6%) and sensitivity of 97.5% (89.7-100%) in full-text screening. Compared to experienced reviewers (mean accuracy 92.4% [76.8-97.8%], mean sensitivity 75.1% [44.1-100%]), our full-text prompt demonstrated significantly higher sensitivity in four reviews (p<0.05), significantly higher accuracy in one review (p0.05). While traditional human screening for an SR of 7000 articles required 530 hours and $10,000 USD, our approach completed screening in one day for $430 USD. Our results establish that LLMs can perform SR screening with performance matching human experts, setting the foundation for end-to-end automated SRs.

4 July 2024 in BMJ Open Quality
Verified
Journal Article
Open access
PDF file
RSRickinder Sethi
Rickinder Sethi
BLBrendan Lyver
Brendan Lyver
JGJaswanth Gorla
Jaswanth Gorla
BSBrendan Singh
Brendan Singh
THTrevor Hanagan
Trevor Hanagan
CSChristian Schulz-Quach
Christian Schulz-Quach
Background Workplace violence (WPV) is a complex global challenge in healthcare that can only be addressed through a quality improvement initiative composed of a complex intervention. However, multiple WPV-specific quality indicators are required to effectively monitor WPV and demonstrate an intervention’s impact. This study aims to determine a set of quality indicators capable of effectively monitoring WPV in healthcare. Methods This study used a modified Delphi process to systematically arrive at an expert consensus on relevant WPV quality indicators at a large, multisite academic health science centre in Toronto, Canada. The expert panel consisted of 30 stakeholders from the University Health Network (UHN) and its affiliates. Relevant literature-based quality indicators which had been identified through a rapid review were categorised according to the Donabedian model and presented to experts for two consecutive Delphi rounds. Results 87 distinct quality indicators identified through the rapid review process were assessed by our expert panel. The surveys received an average response rate of 83.1% in the first round and 96.7% in the second round. From the initial set of 87 quality indicators, our expert panel arrived at a consensus on 17 indicators including 7 structure, 6 process and 4 outcome indicators. A WPV dashboard was created to provide real-time data on each of these indicators. Conclusions Using a modified Delphi methodology, a set of quality indicators validated by expert opinion was identified measuring WPV specific to UHN. The indicators identified in this study were found to be operationalisable at UHN and will provide longitudinal quality monitoring. They will inform data visualisation and dissemination tools which will impact organisational decision-making in real time.