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: <i>1</i>) rule-based title/abstract screening and <i>2</i>) 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.<b>NEW & NOTEWORTHY</b> 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.