Background: A large language model is a type of artificial intelligence (AI) model that opens up great possibilities for health care practice, research, and education, although scholars have emphasized the need to proactively address the issue of unvalidated and inaccurate information regarding its use. One of the best-known large language models is ChatGPT (OpenAI). It is believed to be of great help to medical research, as it facilitates more efficient data set analysis, code generation, and literature review, allowing researchers to focus on experimental design as well as drug discovery and development. Objective: This study aims to explore the potential of ChatGPT as a real-time literature search tool for systematic reviews and clinical decision support systems, to enhance their efficiency and accuracy in health care settings. Methods: The search results of a published systematic review by human experts on the treatment of Peyronie disease were selected as a benchmark, and the literature search formula of the study was applied to ChatGPT and Microsoft Bing AI as a comparison to human researchers. Peyronie disease typically presents with discomfort, curvature, or deformity of the penis in association with palpable plaques and erectile dysfunction. To evaluate the quality of individual studies derived from AI answers, we created a structured rating system based on bibliographic information related to the publications. We classified its answers into 4 grades if the title existed: A, B, C, and F. No grade was given for a fake title or no answer. Results: From ChatGPT, 7 (0.5%) out of 1287 identified studies were directly relevant, whereas Bing AI resulted in 19 (40%) relevant studies out of 48, compared to the human benchmark of 24 studies. In the qualitative evaluation, ChatGPT had 7 grade A, 18 grade B, 167 grade C, and 211 grade F studies, and Bing AI had 19 grade A and 28 grade C studies. Conclusions: This is the first study to compare AI and conventional human systematic review methods as a real-time literature collection tool for evidence-based medicine. The results suggest that the use of ChatGPT as a tool for real-time evidence generation is not yet accurate and feasible. Therefore, researchers should be cautious about using such AI. The limitations of this study using the generative pre-trained transformer model are that the search for research topics was not diverse and that it did not prevent the hallucination of generative AI. However, this study will serve as a standard for future studies by providing an index to verify the reliability and consistency of generative AI from a user’s point of view. If the reliability and consistency of AI literature search services are verified, then the use of these technologies will help medical research greatly.

Although many studies on bladder cancer and the microbiome have been conducted so far, useful strains at the species level have not yet been identified. In addition, in the case of urine studies, methodological heterogeneity is too great, and in tissue studies, the species level through shotgun analysis has not been revealed, and studies using stool samples have provided only limited information. In this review, we will review all the microbiome studies related to bladder cancer so far through a systematic review.

Background: Ureteral stents, such as double-J stents, have become indispensable in urologic procedures but are associated with complications like hematuria and pain. While the advancement of artificial intelligence (AI) technology has led to its increasing application in the health sector, AI has not been used to provide information on potential complications and to facilitate subsequent measures in the event of such complications. Objective: This study aimed to assess the effectiveness of an AI-based prediction tool in providing patients with information about potential complications from ureteroscopy and ureteric stent placement and indicating the need for early additional therapy. Methods: Overall, 28 patients (aged 20-70 years) who underwent ureteral stent insertion for the first time without a history of psychological illness were consecutively included. A “reassurance-call” service was set up to equip patients with details about the procedure and postprocedure care, to monitor for complications and their severity. Patients were randomly allocated into 2 groups, reassurance-call by AI (group 1) and reassurance-call by humans (group 2). The primary outcome was the level of satisfaction with the reassurance-call service itself, measured using a Likert scale. Secondary outcomes included satisfaction with the AI-assisted reassurance-call service, also measured using a Likert scale, and the level of satisfaction (Likert scale and Visual Analogue Scale [VAS]) and anxiety (State-Trait Anxiety Inventory and VAS) related to managing complications for both groups. Results: Of the 28 recruited patients (14 in each group), 1 patient in group 2 dropped out. Baseline characteristics of patients showed no significant differences (all P>.05). Satisfaction with reassurance-call averaged 4.14 (SD 0.66; group 1) and 4.54 (SD 0.52; group 2), with no significant difference between AI and humans (P=.11). AI-assisted reassurance-call satisfaction averaged 3.43 (SD 0.94). Satisfaction about the management of complications using the Likert scale averaged 3.79 (SD 0.70) and 4.23 (SD 0.83), respectively, showing no significant difference (P=.14), but a significant difference was observed when using the VAS (P=.01), with 6.64 (SD 2.13) in group 1 and 8.69 (SD 1.80) in group 2. Anxiety about complications using the State-Trait Anxiety Inventory averaged 36.43 (SD 9.17) and 39.23 (SD 8.51; P=.33), while anxiety assessed with VAS averaged 4.86 (SD 2.28) and 3.46 (SD 3.38; P=.18), respectively, showing no significant differences. Multiple regression analysis was performed on all outcomes, and humans showed superior satisfaction than AI in the management of complications. Otherwise, most of the other variables showed no significant differences (P.>05). Conclusions: This is the first study to use AI for patient reassurance regarding complications after ureteric stent placement. The study found that patients were similarly satisfied for reassurance calls conducted by AI or humans. Further research in larger populations is warranted to confirm these findings. Trial Registration: Clinical Research Information System KCT0008062; https://tinyurl.com/4s8725w2

BACKGROUND Ureteral stents, such as double-J stents, have become indispensable in urologic procedures but are associated with complications like hematuria and pain. While the advancement of artificial intelligence (AI) technology has led to its increasing application in the health sector, AI has not been used to provide information on potential complications and to facilitate subsequent measures in the event of such complications. OBJECTIVE This study aimed to assess the effectiveness of an AI-based prediction tool in providing patients with information about potential complications from ureteroscopy and ureteric stent placement and indicating the need for early additional therapy. METHODS Overall, 28 patients (aged 20-70 years) who underwent ureteral stent insertion for the first time without a history of psychological illness were consecutively included. A “reassurance-call” service was set up to equip patients with details about the procedure and postprocedure care, to monitor for complications and their severity. Patients were randomly allocated into 2 groups, reassurance-call by AI (group 1) and reassurance-call by humans (group 2). The primary outcome was the level of satisfaction with the reassurance-call service itself, measured using a Likert scale. Secondary outcomes included satisfaction with the AI-assisted reassurance-call service, also measured using a Likert scale, and the level of satisfaction (Likert scale and Visual Analogue Scale [VAS]) and anxiety (State-Trait Anxiety Inventory and VAS) related to managing complications for both groups. RESULTS Of the 28 recruited patients (14 in each group), 1 patient in group 2 dropped out. Baseline characteristics of patients showed no significant differences (all P>.05). Satisfaction with reassurance-call averaged 4.14 (SD 0.66; group 1) and 4.54 (SD 0.52; group 2), with no significant difference between AI and humans (P=.11). AI-assisted reassurance-call satisfaction averaged 3.43 (SD 0.94). Satisfaction about the management of complications using the Likert scale averaged 3.79 (SD 0.70) and 4.23 (SD 0.83), respectively, showing no significant difference (P=.14), but a significant difference was observed when using the VAS (P=.01), with 6.64 (SD 2.13) in group 1 and 8.69 (SD 1.80) in group 2. Anxiety about complications using the State-Trait Anxiety Inventory averaged 36.43 (SD 9.17) and 39.23 (SD 8.51; P=.33), while anxiety assessed with VAS averaged 4.86 (SD 2.28) and 3.46 (SD 3.38; P=.18), respectively, showing no significant differences. Multiple regression analysis was performed on all outcomes, and humans showed superior satisfaction than AI in the management of complications. Otherwise, most of the other variables showed no significant differences (P.>05). CONCLUSIONS This is the first study to use AI for patient reassurance regarding complications after ureteric stent placement. The study found that patients were similarly satisfied for reassurance calls conducted by AI or humans. Further research in larger populations is warranted to confirm these findings. CLINICALTRIAL Clinical Research Information System KCT0008062; https://tinyurl.com/4s8725w2

Gwon YN, et al. World J Mens Health. 2024 Nov;42:e101. https://doi.org/10.5534/wjmh.240191