98%
921
2 minutes
20
Introduction: Artificial intelligence (such as Chat Generative Pretrained Transformer [ChatGPT]) augments patient education on medical topics, including reconstructive surgery. In this study, we assess the information, misinformation, and readability of ChatGPT responses to reconstructive urology questions. We also evaluate prompt engineering to optimize responses.
Methods: One hundred twenty-five questions were presented to ChatGPT (version 4 omni [ChatGPT-4o], OpenAI) and were divided into 6 domains: stress urinary continence, neurogenic bladder, urethral stricture, ureteral stricture, impotence, and Peyronie disease. Quality of health information was assessed using DISCERN (1 [low] to 5 [high]). Understandability and actionability were assessed using Patient Education Materials Assessment Tool for Printable Materials (PEMAT-P; 0% [low] to 100% [high]). Misinformation was scored from 1 (no misinformation) to 5 (high misinformation). Grade and reading level were calculated using the Flesch-Kincaid scale (5 [easy] to 16 [difficult] and 100-90 [fifth grade level] to 10-0 [professional level], respectively).
Results: Mean and median DISCERN scores were 3.63 and 5. PEMAT-P understandability was 85.3% but only 37.2% on actionability. There was little misinformation (mean, range: 1.23, 1-4). Responses were at a college graduate reading level. Using prompt engineering in the incontinence domain, scores for DISCERN (3.57-4.75, = .007), PEMAT-P understandability (89.6% to 96.2%, < .001), actionability (38.3% to 93.5%, < .001), and reading level (grade 12.4-5.4, < .01) all improved significantly while misinformation and word count did not change significantly.
Conclusions: ChatGPT-4o's responses are of high quality and understandability with little misinformation. Limitations include actionability and advanced reading level. Using prompt engineering, these deficiencies were addressed without increasing misinformation. ChatGPT-4o can help augment reconstructive urology.
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.1097/UPJ.0000000000000792 | DOI Listing |
J Craniofac Surg
September 2025
Department of Breast Plastic Surgery, Plastic Surgery Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Shijingshan, Beijing, China.
Background: With the development of artificial intelligence, obtaining patient-centered medical information through large language models (LLMs) is crucial for patient education. However, existing digital resources in online health care have heterogeneous quality, and the reliability and readability of content generated by various AI models need to be evaluated to meet the needs of patients with different levels of cultural literacy.
Objective: This study aims to compare the accuracy and readability of different LLMs in providing medical information related to gynecomastia, and explore the most promising science education tools in practical clinical applications.
Biomed Environ Sci
August 2025
Gastrointestinal Disease Centre, Hebei Key Laboratory of Colorectal Cancer Precision Diagnosis and Treatment, The First Hospital of Hebei Medical University, Shijiazhuang 050031, Hebei, China.
Objective: To explore the correlation between chromosome 8 open reading frame 76 (C8orf76) and cyclin-dependent kinase 4 (CDK4) and the potential predictive effect of C8orf76 and CDK4 on the prognosis of colorectal cancer (CRC).
Methods: We constructed a protein-protein interaction network of C8orf76-related genes and analyzed the prognostic signatures of C8orf76 and CDK4. Clinicopathological features of C8orf76 and CDK4 were visualized using a nomogram.
Stroke
September 2025
Brain Language Laboratory, Freie Universität Berlin, Germany (A.-T.P.J., M.R.O., A.S., F.P.).
Background: Intensive language-action therapy treats language deficits and depressive symptoms in chronic poststroke aphasia, yet the underlying neural mechanisms remain underexplored. Long-range temporal correlations (LRTCs) in blood oxygenation level-dependent signals indicate persistence in brain activity patterns and may relate to learning and levels of depression. This observational study investigates blood oxygenation level-dependent LRTC changes alongside therapy-induced language and mood improvements in perisylvian and domain-general brain areas.
View Article and Find Full Text PDFFront Nutr
August 2025
Nutrition Unit, National Agency for Food and Drug Administration and Control, Lagos, Nigeria.
Background: Food labelling policy has become increasingly important in public health due to the rising burden of diet-related diseases. This study examines the compliance of pre-packaged foods sold in Nigerian markets with national food labelling guidelines.
Methods: A total of 883 pre-packaged foods from broad categories were purposively enlisted from selected Nigerian stores and supermarkets.
Front Psychol
August 2025
Department of Educational Psychology and Pedagogy, Faculty of Psychology, Lomonosov Moscow State University, Moscow, Russia.
Family socioeconomic status is broadly acknowledged to be associated with child development and wellbeing. However, the extent of this association across various dimensions of child development remains a topic of ongoing debate. This study aims to investigate the relationship between parental education and child cognitive and socioemotional skills, as well as the mediating role of children's leisure time activities, including screen time and shared book reading.
View Article and Find Full Text PDF