Background: The increasing popularity of Large Language Models (LLMs) in various healthcare settings has raised questions about their ability to provide accurate and reliable information. This study aimed to evaluate the informational value of Large Language Models responses in aesthetic plastic surgery by comparing them with the opinions of experienced surgeons.
Methods: Thirty patients undergoing three common aesthetic procedures-dermal fillers, botulinum toxin injections, and aesthetic blepharoplasty-were selected. The most frequently asked questions by these patients were recorded and submitted to ChatGpt 3.5 and Google Bard v.1.53. The answers provided by the Large Language Models were then evaluated by 13 experienced aesthetic plastic surgeons on a Likert scale for accessibility, accuracy, and overall usefulness.
Results: The overall ratings of the chatbot responses were moderate, with surgeons generally finding them to be accurate and clear. However, the lack of transparency regarding the sources of the information provided by the LLMs made it impossible to fully evaluate their credibility.
Conclusions: While chatbots have the potential to provide patients with convenient access to information about aesthetic plastic surgery, their current limitations in terms of transparency and comprehensiveness warrant caution in their use as a primary source of information. Further research is needed to develop more robust and reliable LLMs for healthcare applications.
Level Of Evidence I: 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 .
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1007/s00266-024-04613-x | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Large Language Model-Based Critical Care Big Data Deployment and Extraction: Descriptive Analysis.
JMIR Med Inform
March 2025
Department of Critical Care Medicine, Beijing Tiantan Hospital, Capital Medical University, No.119 Nansihuanxi Road, Fengtai District, Beijing, 100070, China, 86 17611757717.
Background: Publicly accessible critical care-related databases contain enormous clinical data, but their utilization often requires advanced programming skills. The growing complexity of large databases and unstructured data presents challenges for clinicians who need programming or data analysis expertise to utilize these systems directly.
Objective: This study aims to simplify critical care-related database deployment and extraction via large language models.
Data Note: Alternative Name Encodings - Using Jyutping or Pinyin as tonal representations of Chinese names for data linkage.
Int J Popul Data Sci
March 2025
Great Ormond Street Institute of Child Health, University College London, London, UK.
Accurate data linkage across large administrative databases is crucial for addressing complex research and policy questions, yet linkage errors-stemming from inconsistent name representations-can introduce biases, predominantly for names not given in English. This data note examines the impact of romanisation on linkage accuracy, focusing on Chinese names and comparing standardised systems (Jyutping and Pinyin) with the non-standardised Hong Kong Government Cantonese Romanisation (HKG-romanisation). We identify three primary issues: language-specific variations in romanisation, the loss of tonal information inherent to tonal languages, and discrepancies in name order conventions.
View Article and Find Full Text PDFExamining the Accuracy and Reproducibility of Responses to Nutrition Questions Related to Inflammatory Bowel Disease by Generative Pre-trained Transformer-4.
Crohns Colitis 360
January 2025
Department of Medicine, Karsh Division of Digestive and Liver Diseases, Inflammatory Bowel and Immunobiology Research Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA.
Background: Generative pre-trained transformer-4 (GPT-4) is a large language model (LLM) trained on a vast corpus of data, including the medical literature. Nutrition plays an important role in managing inflammatory bowel disease (IBD), with an unmet need for nutrition-related patient education resources. This study examines the accuracy, comprehensiveness, and reproducibility of responses by GPT-4 to patient nutrition questions related to IBD.
View Article and Find Full Text PDFIndividual variation in the functional lateralization of human ventral temporal cortex: Local competition and long-range coupling.
Imaging Neurosci (Camb)
March 2025
Neuroscience Institute, Carnegie Mellon University, Pittsburgh, PA, United States.
The ventral temporal cortex (VTC) of the human cerebrum is critically engaged in high-level vision. One intriguing aspect of this region is its functional lateralization, with neural responses to words being stronger in the left hemisphere, and neural responses to faces being stronger in the right hemisphere; such patterns can be summarized with a signed laterality index (LI), positive for leftward laterality. Converging evidence has suggested that word laterality emerges to couple efficiently with left-lateralized frontotemporal language regions, but evidence is more mixed regarding the sources of the right lateralization for face perception.
View Article and Find Full Text PDFFoundation models in bioinformatics.
Natl Sci Rev
April 2025
Hunan Provincial Key Lab on Bioinformatics, School of Computer Science and Engineering, Central South University, Changsha 410083, China.
With the adoption of foundation models (FMs), artificial intelligence (AI) has become increasingly significant in bioinformatics and has successfully addressed many historical challenges, such as pre-training frameworks, model evaluation and interpretability. FMs demonstrate notable proficiency in managing large-scale, unlabeled datasets, because experimental procedures are costly and labor intensive. In various downstream tasks, FMs have consistently achieved noteworthy results, demonstrating high levels of accuracy in representing biological entities.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!