Treffer: Accelerating systematic reviews: a novel 1-wk screening protocol using rule-based automation with AI-assisted Python coding.

The exponential growth in academic publishing—exceeding 2 million papers annually in 2023—has rendered traditional systematic review methods unsustainable. These conventional approaches typically require 6–24 mo for completion, creating critical delays between evidence availability and clinical implementation. Although existing automation tools demonstrate workload reductions of 30%–72.5%, their machine learning dependencies create barriers to immediate implementation. In addition, direct artificial intelligence (AI) screening methods involve substantial computational costs, lack real-time adaptability, suffer from inconsistent performance across different research domains, and provide no clear audit trail for regulatory compliance. We present a 1-wk systematic review acceleration protocol using rule-based automation where artificial intelligence (AI) assists with code generation. Researchers define screening criteria, then use AI language models (Claude and ChatGPT) as coding assistants. This protocol uses a two-phase screening process: 1) rule-based title/abstract screening and 2) rule-based full-text analysis, while adhering to established systematic review guidelines such as Cochrane methodology and Preferred Reporting Items for Systematic Reviews and Meta-Analyses reporting. The rule-based system provides immediate implementation with complete transparency, whereas validation framework guides researchers in systematically testing screening sensitivity to minimize false negatives and ensure comprehensive study capture; meta-analysis and statistical synthesis remain manual processes requiring human expertise. We demonstrate the protocol's application through a case study examining cardiac fatty acid oxidation in heart failure with preserved ejection fraction, and validated through a separate review examining e-cigarette versus traditional cigarette cardiopulmonary effects, which successfully processed 3,791 records. This protocol represents a substantial advancement in systematic review methodology, making high-quality evidence synthesis more accessible across a broad range of scientific disciplines. NEW & NOTEWORTHY Systematic reviews are essential to keep up with academic literature but typically require 6–24 mo to complete. Our novel 1-wk protocol integrates AI-assisted screening with Python-based automation-eliminating machine learning dependencies for immediate implementation. By streamlining article selection while adhering to Cochrane and PRISMA guidelines, this method accelerates evidence synthesis without compromising rigor. Applied in a cardiac metabolism case study, it offers a fast, accessible solution for researchers across disciplines. [ABSTRACT FROM AUTHOR]