Awareness and Use of ChatGPT and Large Language Models: A Prospective Cross-sectional Global Survey in Urology

Artificial Intelligence Modeling and Priapism

PURPOSE OF REVIEW

This narrative review aims to outline the current available evidence, challenges, and future perspectives of Artificial Intelligence (AI) in the diagnosis and management of priapism, a condition marked by prolonged and often painful erections that presents unique diagnostic and therapeutic challenges.

RECENT FINDINGS

Recent advancements in AI offer promising solutions to face the challenges in diagnosing and treating priapism. AI models have demonstrated the potential to predict the need for surgical intervention and improve diagnostic accuracy. The integration of AI models into medical decision-making for priapism can also predict long-term consequences. AI is currently being implemented in urology to enhance diagnostics and treatment work-up for various conditions, including priapism. Traditional diagnostic approaches rely heavily on assessments based on history, leading to potential delays in treatment with possible long-term sequelae. To date, the role of AI in the management of priapism is understudied, yet to achieve dependable and effective models that can reliably assist physicians in making decisions regarding both diagnostic and treatment strategies.

Can ChatGPT provide high-quality patient information on male lower urinary tract symptoms suggestive of benign prostate enlargement?

BACKGROUND

ChatGPT has recently emerged as a novel resource for patients' disease-specific inquiries. There is, however, limited evidence assessing the quality of the information. We evaluated the accuracy and quality of the ChatGPT's responses on male lower urinary tract symptoms (LUTS) suggestive of benign prostate enlargement (BPE) when compared to two reference resources.

METHODS

Using patient information websites from the European Association of Urology and the American Urological Association as reference material, we formulated 88 BPE-centric questions for ChatGPT 4.0+. Independently and in duplicate, we compared the ChatGPT's responses and the reference material, calculating accuracy through F1 score, precision, and recall metrics. We used a 5-point Likert scale for quality rating. We evaluated examiner agreement using the interclass correlation coefficient and assessed the difference in the quality scores with the Wilcoxon signed-rank test.

RESULTS

ChatGPT addressed all (88/88) LUTS/BPE-related questions. For the 88 questions, the recorded F1 score was 0.79 (range: 0-1), precision 0.66 (range: 0-1), recall 0.97 (range: 0-1), and the quality score had a median of 4 (range = 1-5). Examiners had a good level of agreement (ICC = 0.86). We found no statistically significant difference between the scores given by the examiners and the overall quality of the responses (p = 0.72).

DISCUSSION

ChatGPT demostrated a potential utility in educating patients about BPE/LUTS, its prognosis, and treatment that helps in the decision-making process. One must exercise prudence when recommending this as the sole information outlet. Additional studies are needed to completely understand the full extent of AI's efficacy in delivering patient education in urology.

ChatGPT prompts for generating multiple-choice questions in medical education and evidence on their validity: a literature review

ChatGPT's role in creating multiple-choice questions (MCQs) is growing but the validity of these artificial-intelligence-generated questions is unclear. This literature review was conducted to address the urgent need for understanding the application of ChatGPT in generating MCQs for medical education. Following the database search and screening of 1920 studies, we found 23 relevant studies. We extracted the prompts for MCQ generation and assessed the validity evidence of MCQs. The findings showed that prompts varied, including referencing specific exam styles and adopting specific personas, which align with recommended prompt engineering tactics. The validity evidence covered various domains, showing mixed accuracy rates, with some studies indicating comparable quality to human-written questions, and others highlighting differences in difficulty and discrimination levels, alongside a significant reduction in question creation time. Despite its efficiency, we highlight the necessity of careful review and suggest a need for further research to optimize the use of ChatGPT in question generation. Main messages  Ensure high-quality outputs by utilizing well-designed prompts; medical educators should prioritize the use of detailed, clear ChatGPT prompts when generating MCQs. Avoid using ChatGPT-generated MCQs directly in examinations without thorough review to prevent inaccuracies and ensure relevance. Leverage ChatGPT's potential to streamline the test development process, enhancing efficiency without compromising quality.

Accuracy, readability, and understandability of large language models for prostate cancer information to the public

BACKGROUND

Generative Pretrained Model (GPT) chatbots have gained popularity since the public release of ChatGPT. Studies have evaluated the ability of different GPT models to provide information about medical conditions. To date, no study has assessed the quality of ChatGPT outputs to prostate cancer related questions from both the physician and public perspective while optimizing outputs for patient consumption.

METHODS

Nine prostate cancer-related questions, identified through Google Trends (Global), were categorized into diagnosis, treatment, and postoperative follow-up. These questions were processed using ChatGPT 3.5, and the responses were recorded. Subsequently, these responses were re-inputted into ChatGPT to create simplified summaries understandable at a sixth-grade level. Readability of both the original ChatGPT responses and the layperson summaries was evaluated using validated readability tools. A survey was conducted among urology providers (urologists and urologists in training) to rate the original ChatGPT responses for accuracy, completeness, and clarity using a 5-point Likert scale. Furthermore, two independent reviewers evaluated the layperson summaries on correctness trifecta: accuracy, completeness, and decision-making sufficiency. Public assessment of the simplified summaries' clarity and understandability was carried out through Amazon Mechanical Turk (MTurk). Participants rated the clarity and demonstrated their understanding through a multiple-choice question.

RESULTS

GPT-generated output was deemed correct by 71.7% to 94.3% of raters (36 urologists, 17 urology residents) across 9 scenarios. GPT-generated simplified layperson summaries of this output was rated as accurate in 8 of 9 (88.9%) scenarios and sufficient for a patient to make a decision in 8 of 9 (88.9%) scenarios. Mean readability of layperson summaries was higher than original GPT outputs ([original ChatGPT v. simplified ChatGPT, mean (SD), p-value] Flesch Reading Ease: 36.5(9.1) v. 70.2(11.2), <0.0001; Gunning Fog: 15.8(1.7) v. 9.5(2.0), p < 0.0001; Flesch Grade Level: 12.8(1.2) v. 7.4(1.7), p < 0.0001; Coleman Liau: 13.7(2.1) v. 8.6(2.4), 0.0002; Smog index: 11.8(1.2) v. 6.7(1.8), <0.0001; Automated Readability Index: 13.1(1.4) v. 7.5(2.1), p < 0.0001). MTurk workers (n = 514) rated the layperson summaries as correct (89.5-95.7%) and correctly understood the content (63.0-87.4%).

CONCLUSION

GPT shows promise for correct patient education for prostate cancer-related contents, but the technology is not designed for delivering patients information. Prompting the model to respond with accuracy, completeness, clarity and readability may enhance its utility when used for GPT-powered medical chatbots.

Performance of ChatGPT on the Taiwan urology board examination: insights into current strengths and shortcomings

PURPOSE

To compare ChatGPT-4 and ChatGPT-3.5's performance on Taiwan urology board examination (TUBE), focusing on answer accuracy, explanation consistency, and uncertainty management tactics to minimize score penalties from incorrect responses across 12 urology domains.

METHODS

450 multiple-choice questions from TUBE(2020-2022) were presented to two models. Three urologists assessed correctness and consistency of each response. Accuracy quantifies correct answers; consistency assesses logic and coherence in explanations out of total responses, alongside a penalty reduction experiment with prompt variations. Univariate logistic regression was applied for subgroup comparison.

RESULTS

ChatGPT-4 showed strengths in urology, achieved an overall accuracy of 57.8%, with annual accuracies of 64.7% (2020), 58.0% (2021), and 50.7% (2022), significantly surpassing ChatGPT-3.5 (33.8%, OR = 2.68, 95% CI [2.05-3.52]). It could have passed the TUBE written exams if solely based on accuracy but failed in the final score due to penalties. ChatGPT-4 displayed a declining accuracy trend over time. Variability in accuracy across 12 urological domains was noted, with more frequently updated knowledge domains showing lower accuracy (53.2% vs. 62.2%, OR = 0.69, p = 0.05). A high consistency rate of 91.6% in explanations across all domains indicates reliable delivery of coherent and logical information. The simple prompt outperformed strategy-based prompts in accuracy (60% vs. 40%, p = 0.016), highlighting ChatGPT's limitations in its inability to accurately self-assess uncertainty and a tendency towards overconfidence, which may hinder medical decision-making.

CONCLUSIONS

ChatGPT-4's high accuracy and consistent explanations in urology board examination demonstrate its potential in medical information processing. However, its limitations in self-assessment and overconfidence necessitate caution in its application, especially for inexperienced users. These insights call for ongoing advancements of urology-specific AI tools.

Embracing the future: Integrating ChatGPT into China's nursing education system

This article delves into the role of ChatGPT within the rapidly evolving field of artificial intelligence, especially highlighting its significant potential in nursing education. Initially, the paper presents the notable advancements ChatGPT has achieved in facilitating interactive learning and providing real-time feedback, along with the academic community's growing interest in this technology. Subsequently, summarizing the research outcomes of ChatGPT's applications in nursing education, including various clinical disciplines and scenarios, showcases the enormous potential for multidisciplinary education and addressing clinical issues. Comparing the performance of several Large Language Models (LLMs) on China's National Nursing Licensure Examination, we observed that ChatGPT demonstrated a higher accuracy rate than its counterparts, providing a solid theoretical foundation for its application in Chinese nursing education and clinical settings. Educational institutions should establish a targeted and effective regulatory framework to leverage ChatGPT in localized nursing education while assuming corresponding responsibilities. Through standardized training for users and adjustments to existing educational assessment methods aimed at preventing potential misuse and abuse, the full potential of ChatGPT as an innovative auxiliary tool in China's nursing education system can be realized, aligning with the developmental needs of modern teaching methodologies.

Conformity of ChatGPT recommendations with the AUA/SUFU guideline on postprostatectomy urinary incontinence

INTRODUCTION

Artificial intelligence (AI) shows immense potential in medicine and Chat generative pretrained transformer (ChatGPT) has been used for different purposes in the field. However, it may not match the complexity and nuance of certain medical scenarios. This study evaluates the accuracy of ChatGPT 3.5 and 4 in providing recommendations regarding the management of postprostatectomy urinary incontinence (PPUI), considering The Incontinence After Prostate Treatment: AUA/SUFU Guideline as the best practice benchmark.

MATERIALS AND METHODS

A set of questions based on the AUA/SUFU Guideline was prepared. Queries included 10 conceptual questions and 10 case-based questions. All questions were open and entered into the ChatGPT with a recommendation to limit the answer to 200 words, for greater objectivity. Responses were graded as correct (1 point); partially correct (0.5 point), or incorrect (0 point). Performances of versions 3.5 and 4 of ChatGPT were analyzed overall and separately for the conceptual and the case-based questions.

RESULTS

ChatGPT 3.5 scored 11.5 out of 20 points (57.5% accuracy), while ChatGPT 4 scored 18 (90.0%; p = 0.031). In the conceptual questions, ChatGPT 3.5 provided accurate answers to six questions along with one partially correct response and three incorrect answers, with a final score of 6.5. In contrast, ChatGPT 4 provided correct answers to eight questions and partially correct answers to two questions, scoring 9.0. In the case-based questions, ChatGPT 3.5 scored 5.0, while ChatGPT 4 scored 9.0. The domains where ChatGPT performed worst were evaluation, treatment options, surgical complications, and special situations.

CONCLUSION

ChatGPT 4 demonstrated superior performance compared to ChatGPT 3.5 in providing recommendations for the management of PPUI, using the AUA/SUFU Guideline as a benchmark. Continuous monitoring is essential for evaluating the development and precision of AI-generated medical information.

Evaluating ChatGPT-4.0's data analytic proficiency in epidemiological studies: A comparative analysis with SAS, SPSS, and R

Background

OpenAI's Chat Generative Pre-trained Transformer 4.0 (ChatGPT-4), an emerging artificial intelligence (AI)-based large language model (LLM), has been receiving increasing attention from the medical research community for its innovative 'Data Analyst' feature. We aimed to compare the capabilities of ChatGPT-4 against traditional biostatistical software (i.e. SAS, SPSS, R) in statistically analysing epidemiological research data.

Methods

We used a data set from the China Health and Nutrition Survey, comprising 9317 participants and 29 variables (e.g. gender, age, educational level, marital status, income, occupation, weekly working hours, survival status). Two researchers independently evaluated the data analysis capabilities of GPT-4's 'Data Analyst' feature against SAS, SPSS, and R across three commonly used epidemiological analysis methods: Descriptive statistics, intergroup analysis, and correlation analysis. We used an internally developed evaluation scale to assess and compare the consistency of results, analytical efficiency of coding or operations, user-friendliness, and overall performance between ChatGPT-4, SAS, SPSS, and R.

Results

In descriptive statistics, ChatGPT-4 showed high consistency of results, greater analytical efficiency of code or operations, and more intuitive user-friendliness compared to SAS, SPSS, and R. In intergroup comparisons and correlational analyses, despite minor discrepancies in statistical outcomes for certain analysis tasks with SAS, SPSS, and R, ChatGPT-4 maintained high analytical efficiency and exceptional user-friendliness. Thus, employing ChatGPT-4 can significantly lower the operational threshold for conducting epidemiological data analysis while maintaining consistency with traditional biostatistical software's outcome, requiring only specific, clear analysis instructions without any additional operations or code writing.

Conclusions

We found ChatGPT-4 to be a powerful auxiliary tool for statistical analysis in epidemiological research. However, it showed limitations in result consistency and in applying more advanced statistical methods. Therefore, we advocate for the use of ChatGPT-4 in supporting researchers with intermediate experience in data analysis. With AI technologies like LLMs advancing rapidly, their integration with data analysis platforms promises to lower operational barriers, thereby enabling researchers to dedicate greater focus to the nuanced interpretation of analysis results. This development is likely to significantly advance epidemiological and medical research.

Ethical Dilemmas in Using AI for Academic Writing and an Example Framework for Peer Review in Nephrology Academia: A Narrative Review

The emergence of artificial intelligence (AI) has greatly propelled progress across various sectors including the field of nephrology academia. However, this advancement has also given rise to ethical challenges, notably in scholarly writing. AI's capacity to automate labor-intensive tasks like literature reviews and data analysis has created opportunities for unethical practices, with scholars incorporating AI-generated text into their manuscripts, potentially undermining academic integrity. This situation gives rise to a range of ethical dilemmas that not only question the authenticity of contemporary academic endeavors but also challenge the credibility of the peer-review process and the integrity of editorial oversight. Instances of this misconduct are highlighted, spanning from lesser-known journals to reputable ones, and even infiltrating graduate theses and grant applications. This subtle AI intrusion hints at a systemic vulnerability within the academic publishing domain, exacerbated by the publish-or-perish mentality. The solutions aimed at mitigating the unethical employment of AI in academia include the adoption of sophisticated AI-driven plagiarism detection systems, a robust augmentation of the peer-review process with an "AI scrutiny" phase, comprehensive training for academics on ethical AI usage, and the promotion of a culture of transparency that acknowledges AI's role in research. This review underscores the pressing need for collaborative efforts among academic nephrology institutions to foster an environment of ethical AI application, thus preserving the esteemed academic integrity in the face of rapid technological advancements. It also makes a plea for rigorous research to assess the extent of AI's involvement in the academic literature, evaluate the effectiveness of AI-enhanced plagiarism detection tools, and understand the long-term consequences of AI utilization on academic integrity. An example framework has been proposed to outline a comprehensive approach to integrating AI into Nephrology academic writing and peer review. Using proactive initiatives and rigorous evaluations, a harmonious environment that harnesses AI's capabilities while upholding stringent academic standards can be envisioned.