Inclusion Criteria for a Scoping Review of LLMs in Medical Exams

A protocol for a scoping review synthesizing prior research on Large Language Model performance in standardized medical examinations. The 5.5 KB Excel file, authored by Weiqi Wang and last updated on April 22, 2026, outlines the methodology for a systematic literature search in PubMed and Web of Science. It details inclusion criteria and analytical frameworks for assessing LLM accuracy and reliability in clinical contexts.

Use Cases

• Designing a systematic literature search strategy based on the described inclusion/exclusion criteria.
• Replicating the scoping review methodology for other AI-in-medicine topics based on the JBI Manual-guided protocol.
• Analyzing trends and limitations in LLM medical exam evaluations based on the proposed synthesis framework.

Strengths

• Protocol follows the JBI Manual for Evidence Synthesis, indicating a structured methodological approach.
• File is openly licensed under CC-BY-4.0, permitting reuse and adaptation.
• Explicitly states no ethical approval is required, clarifying its literature-based nature.

Limitations

• Dataset is very small at 5.5 KB, containing only the review protocol, not the underlying literature data.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment for some analytical purposes.

Provenance

Source

figshare

Collection Method

Literature review protocol for systematic searches in PubMed and Web of Science.

Time Range

Covers literature up to the date of the protocol's creation.

Freshness

Last updated 2026-04-22 17:32:03; freshness should be verified.

Geography

null