Liu HY, Alessandri Bonetti M, De Lorenzi F, Gimbel ML, Nguyen VT, Egro FM. Consulting the Digital Doctor: Google Versus ChatGPT as Sources of Information on Breast Implant-Associated Anaplastic Large Cell Lymphoma and Breast Implant Illness.
Aesthetic Plast Surg 2024;
48:590-607. [PMID:
37903939 DOI:
10.1007/s00266-023-03713-4]
[Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/19/2023] [Accepted: 10/10/2023] [Indexed: 11/01/2023]
Abstract
BACKGROUND
Breast implant-associated anaplastic large cell lymphoma (BIA-ALCL) is a rare complication associated with the use of breast implants. Breast implant illness (BII) is another potentially concerning issue related to breast implants. This study aims to assess the quality of ChatGPT as a potential source of patient education by comparing the answers to frequently asked questions on BIA-ALCL and BII provided by ChatGPT and Google.
METHODS
The Google and ChatGPT answers to the 10 most frequently asked questions on the search terms "breast implant associated anaplastic large cell lymphoma" and "breast implant illness" were recorded. Five blinded breast plastic surgeons were then asked to grade the quality of the answers according to the Global Quality Score (GQS). A Wilcoxon paired t-test was performed to evaluate the difference in GQS ratings for Google and ChatGPT answers. The sources provided by Google and ChatGPT were also categorized and assessed.
RESULTS
In a comparison of answers provided by Google and ChatGPT on BIA-ALCL and BII, ChatGPT significantly outperformed Google. For BIA-ALCL, Google's average score was 2.72 ± 1.44, whereas ChatGPT scored an average of 4.18 ± 1.04 (p < 0.01). For BII, Google's average score was 2.66 ± 1.24, while ChatGPT scored an average of 4.28 ± 0.97 (p < 0.01). The superiority of ChatGPT's responses was attributed to their comprehensive nature and recognition of existing knowledge gaps. However, some of ChatGPT's answers had inaccessible sources.
CONCLUSION
ChatGPT outperforms Google in providing high-quality answers to commonly asked questions on BIA-ALCL and BII, highlighting the potential of AI technologies in patient education.
LEVEL OF EVIDENCE
Level III, comparative study LEVEL OF EVIDENCE III: This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266 .
Collapse