Systematic literature reviews (SLRs) are essential for synthesizing high-quality evidence in clinical research, health economics and outcomes research, and health technology assessments. However, the growing volume of published data has made SLRs time-consuming, labor-intensive, and costly. To address these challenges, we introduce A4SLR, an agentic artificial-intelligence-assisted SLR framework, which provides a flexible, extensible methodology for automating the entire SLR process-from initial query formulation to evidence synthesis-across various study fields.
A4SLR comprises 8 modules integrated with specialized artificial intelligence agents powered by large language models: search, I/E criteria deployment, abstract/full-text screening, text/table pre-processing, data extraction, assessment, risk of bias analysis, and report. We implemented and validated this framework using 2 use cases, non-small cell lung cancer and perinatal mood and anxiety disorders. Performance of the assessment was evaluated quantitatively and qualitatively.
Our implementation demonstrated high accuracy in article screening (F1 scores: 0.917-0.977), risk of bias assessment (Cohen’s k: 0.8442-0.9064), and data extraction (F-scores: 0.96-0.998), including patient characteristics, safety and efficacy outcomes, economic model parameters, and cost-effectiveness data. Notably, the text/table preprocessing agent yielded comprehensive coverage of data elements, particularly in the challenging tasks of accurately matching outcome values to their corresponding study arms.
Our findings highlight the potential of the A4SLR framework to transform the evidence synthesis process by addressing the limitations of manual SLRs, thereby enhancing health economics and outcomes research and health technology assessments. Designed as a scalable, user-centric, extensible approach, A4SLR provides a robust solution for generating comprehensive up-to-date evidence to support researchers and decision makers across diverse clinical and therapeutic areas.