Comparing large language models and search engine responses to common orthodontic questions

by Yuanyuan Ren, Jing Sun

Background

Large Language Models (LLMs) highlight their potential in supporting patient education and self-management. Their performance in responses to orthodontic questions has yet to be explored.

Objectives

This study aims to compare the quality, empathy, readability, and satisfaction of responses from LLMs and search engines on common orthodontic questions.

Methods

Forty-five common orthodontic questions (six categories) and a prompt were developed, and a self-designed multidimensional evaluation questionnaire was constructed. Questions were presented to 5 LLMs and 3 search engines on December,22,2024. The primary outcomes were the median expert-rated scores of LLMs versus search engine responses on quality, empathy, readability, and satisfaction, using 5- or 10-point Likert scales.

Results

LLMs scored significantly higher than search engines in quality (4.00 vs. 3.50, p  Conclusions

In this cross-sectional study, the LLMs, particularly GPT-4o, outperformed search engines. These results indicate the potential of LLMs as supplementary tools for orthodontic patient education and self-management.

Effects of multicomponent exercise on quality of life, depression and anxiety among stroke survivors: A systematic review and meta‐analysis

Abstract

Background

Current guidelines stress the importance of exercise, especially multicomponent exercise to older adults with chronic conditions.

Aim

To critically synthesise evidence that evaluates the effects of multicomponent exercise on quality of life, depression and anxiety after stroke.

Design

Systematic review and meta-analysis followed the PRISMA 2020 statement.

Methods

A systematic search of PubMed, Embase, Web of Science, Cochrane Library, CINAHL and PsycINFO from inception to 12 June 2023 was performed. Risk of bias was assessed using the Revised Cochrane risk-of-bias tool for randomised trials (RoB 2). Meta-analyses were conducted using Review Manager 5.4 and narrative syntheses were adopted whenever meta-analysis was inappropriate. The overall certainty of the evidence was rated using the Grading of Recommendations, Assessment, Development and Evaluation (GRADE) approach.

Results

Of 15,351 records identified, nine were eligible and data were available for seven randomised controlled trials, three of which were identified as having a high risk of bias, one as low risk, and five as having some concerns. Subgroup pooled analyses indicated that multicomponent exercise engaged in longer exercise sessions (>60 min) was effective in improving quality of life immediately post-intervention and through 3–6 months post-intervention. However, multicomponent exercise did not significantly affect depression and anxiety.

Conclusions

Multicomponent exercise with longer duration of exercise sessions has promising effects on both short- to medium-term quality of life among stroke survivors.

Patient or Public Contribution

This does not apply to our work as it is a review paper.

Relevance to Clinical Practice

Healthcare providers could consider encouraging the patients to participate in multicomponent exercise sessions for more than 60 min. It is important to note that stroke survivors should be supervised by trained personnel at the beginning of the training.

Registration

The protocol was registered on PROSPERO.