Category Ranking

98%

Total Visits

921

Avg Visit Duration

2 minutes

Citations

20

Article Abstract

Purpose: ChatGPT is a large language model trained on a large dataset covering a broad range of topics, including the medical literature. We aim to examine its accuracy and reproducibility in answering patient questions regarding bariatric surgery.

Materials And Methods: Questions were gathered from nationally regarded professional societies and health institutions as well as Facebook support groups. Board-certified bariatric surgeons graded the accuracy and reproducibility of responses. The grading scale included the following: (1) comprehensive, (2) correct but inadequate, (3) some correct and some incorrect, and (4) completely incorrect. Reproducibility was determined by asking the model each question twice and examining difference in grading category between the two responses.

Results: In total, 151 questions related to bariatric surgery were included. The model provided "comprehensive" responses to 131/151 (86.8%) of questions. When examined by category, the model provided "comprehensive" responses to 93.8% of questions related to "efficacy, eligibility and procedure options"; 93.3% related to "preoperative preparation"; 85.3% related to "recovery, risks, and complications"; 88.2% related to "lifestyle changes"; and 66.7% related to "other". The model provided reproducible answers to 137 (90.7%) of questions.

Conclusion: The large language model ChatGPT often provided accurate and reproducible responses to common questions related to bariatric surgery. ChatGPT may serve as a helpful adjunct information resource for patients regarding bariatric surgery in addition to standard of care provided by licensed healthcare professionals. We encourage future studies to examine how to leverage this disruptive technology to improve patient outcomes and quality of life.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10234918PMC
http://dx.doi.org/10.1007/s11695-023-06603-5DOI Listing

Publication Analysis

Top Keywords

questions bariatric
16
bariatric surgery
16
model provided
12
model chatgpt
8
large language model
8
accuracy reproducibility
8
provided "comprehensive"
8
"comprehensive" responses
8
model
7
questions
7

Similar Publications

Purpose: Primary ventral hernia repair is a common elective procedure; however, mesh placement practices vary widely, and there is limited evidence to guide optimal placement. This international study examined surgeons' preferences and considerations regarding mesh placement in elective primary ventral hernia repair.

Methods: We conducted an international cross-sectional survey targeting surgeons experienced in primary ventral hernia repair.

View Article and Find Full Text PDF

Background: There is a notable increase in metabolic and bariatric surgery (MBS) procedures, the numbers of patients treated, and volume of scientific articles published. However, it is not clear whether there is a parallel diversification in the analytic approaches employed in published MBS research. The current study appraised this point.

View Article and Find Full Text PDF

Background Obesity is a growing public health crisis in Pakistan, with increasing numbers of individuals experiencing obesity related complications such as diabetes and cardiovascular disease. Metabolic and bariatric surgery (MBS) is a well-established, evidence-based intervention for managing severe obesity. However, its utilization remains suboptimal in many low- and middle-income countries, including Pakistan.

View Article and Find Full Text PDF

Background: The study aims to determine adults' interest in weight loss methods and their predictors such as anthropometric parameters, physical activity, and sociodemographic factors.

Methods: A two-step procedure was adopted. First, anthropometric parameters of 1130 Polish adults were taken, and the body mass index (BMI), the waist-to-hip ratio (WHR), and the body fat (BF) percentage were calculated.

View Article and Find Full Text PDF

Background: Large language models (LLMs) can generate human-like, empathetic responses within seconds. Their potential in terms of comprehensibility, empathy, and completeness to support physician-patient communication in bariatric surgery care needs to be evaluated.

Methods: We collected 200 real-world questions from patient support groups, initial consultations, and follow-up visits, which were answered by GPT-4o and two human bariatric experts.

View Article and Find Full Text PDF