# Evaluating Scopus AI Versus Traditional Searches for Literature Review About Prepectoral Breast Reconstruction: An Exploratory Study

## TL;DR

This study compares AI-powered Scopus AI with traditional PubMed searches for finding literature on prepectoral breast reconstruction, finding that AI can speed up the process but still needs human review.

## Contribution

The study introduces a direct comparison of AI-based and traditional literature search methods in a specific clinical context.

## Key findings

- Scopus AI retrieved 25 articles versus 4 from traditional PubMed searches.
- Only 17 articles were included after filtering for relevance and quality.
- No overlap was found between the results from the two search methods.

## Abstract

Background: Artificial intelligence tools are increasingly being used to assist literature reviews, but their effectiveness compared to traditional methods is not well established. This study compares Scopus AI with PubMed keyword searches on the topic of primary prepectoral breast reconstruction after radical mastectomy. Methods: On 28 May 2025, two literature searches were conducted on the topic of primary prepectoral breast reconstruction after radical mastectomy—one using Scopus AI and the other using manual keyword searches in PubMed. Both searches were limited to peer-reviewed clinical studies in English, excluding case reports and studies with fewer than 10 patients. Data extracted included study design, sample size, outcomes, and key findings. Results: The Scopus AI search retrieved 25 articles, while the traditional method identified 4. After removing duplicates, non-English texts, and non-relevant sources, 17 articles were included in the final analysis. Scopus AI provided automatic summaries, while manual review was required for the traditional method. No overlap was found between the two methods. Conclusions: AI tools like Scopus AI can enhance the speed and breadth of literature reviews, but human oversight remains essential to ensure relevance and quality. Combining AI with traditional methods may offer a more balanced and effective approach for clinical research.