Background: Artificial intelligence (AI) chatbots, such as ChatGPT, have made significant progress. These chatbots, particularly popular among health care professionals and patients, are transforming patient education and disease experience with personalized information. Accurate, timely patient education is crucial for informed decision-making, especially regarding prostate-specific antigen screening and treatment options. However, the accuracy and reliability of AI chatbots’ medical information must be rigorously evaluated. Studies testing ChatGPT’s knowledge of prostate cancer are emerging, but there is a need for ongoing evaluation to ensure the quality and safety of information provided to patients. Objective: This study aims to evaluate the quality, accuracy, and readability of ChatGPT-4’s responses to common prostate cancer questions posed by patients. Methods: Overall, 8 questions were formulated with an inductive approach based on information topics in peer-reviewed literature and Google Trends data. Adapted versions of the Patient Education Materials Assessment Tool for AI (PEMAT-AI), Global Quality Score, and DISCERN-AI tools were used by 4 independent reviewers to assess the quality of the AI responses. The 8 AI outputs were judged by 7 expert urologists, using an assessment framework developed to assess accuracy, safety, appropriateness, actionability, and effectiveness. The AI responses’ readability was assessed using established algorithms (Flesch Reading Ease score, Gunning Fog Index, Flesch-Kincaid Grade Level, The Coleman-Liau Index, and Simple Measure of Gobbledygook [SMOG] Index). A brief tool (Reference Assessment AI [REF-AI]) was developed to analyze the references provided by AI outputs, assessing for reference hallucination, relevance, and quality of references. Results: The PEMAT-AI understandability score was very good (mean 79.44%, SD 10.44%), the DISCERN-AI rating was scored as “good” quality (mean 13.88, SD 0.93), and the Global Quality Score was high (mean 4.46/5, SD 0.50). Natural Language Assessment Tool for AI had pooled mean accuracy of 3.96 (SD 0.91), safety of 4.32 (SD 0.86), appropriateness of 4.45 (SD 0.81), actionability of 4.05 (SD 1.15), and effectiveness of 4.09 (SD 0.98). The readability algorithm consensus was “difficult to read” (Flesch Reading Ease score mean 45.97, SD 8.69; Gunning Fog Index mean 14.55, SD 4.79), averaging an 11th-grade reading level, equivalent to 15- to 17-year-olds (Flesch-Kincaid Grade Level mean 12.12, SD 4.34; The Coleman-Liau Index mean 12.75, SD 1.98; SMOG Index mean 11.06, SD 3.20). REF-AI identified 2 reference hallucinations, while the majority (28/30, 93%) of references appropriately supplemented the text. Most references (26/30, 86%) were from reputable government organizations, while a handful were direct citations from scientific literature. Conclusions: Our analysis found that ChatGPT-4 provides generally good responses to common prostate cancer queries, making it a potentially valuable tool for patient education in prostate cancer care. Objective quality assessment tools indicated that the natural language processing outputs were generally reliable and appropriate, but there is room for improvement.

Purpose: To assess baseline clinical and urodynamic profiles of a contemporary cohort of men undergoing radical prostatectomy (RP) as part of the ROSE (Robotic and Open Surgery for Prostate Cancer: A Prospective, Multi-centre, Comparative Study of Functional and Oncological Outcomes) study.Methods: Men with localized prostate cancer undergoing RP were prospectively recruited to undergo clinical assessment and urodynamic testing prior to surgery as part of a clinical trial. The International Prostate Symptoms Score (IPSS) was used to determine participants’ degree of lower urinary tract symptoms (LUTS).Results: Eighty-five men with a median age of 64.5 years and a median prostate-specific antigen level of 6.3 ng/mL were prospectively recruited. Of patients with complete baseline data, 36 (50.7%), 28 (39.4%), and 7 (9.9%) had mild (IPSS20) LUTS, respectively. Obstruction was identified in 18 men (29.5%), and 9 (14.8%) showed detrusor underactivity. Of the 15 patients with detrusor overactivity, 12 (80%) reported overactive bladder (OAB). Of men with urodynamic obstruction, 5 (31.3%), 10 (62.5%), and 1 (6.3%) reported mild, moderate, and severe LUTS, respectively. Of men without OAB, 4 (11.8%, P=0.002) showed filling phase abnormalities, 13 (46.4%, P=0.611) had flow rates of <15 mL/sec, and 7 (30.4%, P=0.767) showed obstruction. Of men with mild or no LUTS, 5 (20%, P=0.072) showed obstruction and 4 (16%, P=0.524) showed poor contractility.Conclusion: LUTS and OAB were common in men with localized prostate cancer undergoing RP. Detrusor overactivity and urodynamic filling phase abnormalities were strongly correlated with OAB. IPSS did not show a strong correlation with bladder outflow obstruction or detrusor underactivity. Urodynamic filling abnormalities were found in 11.8% of men without OAB. Symptomatic and functional assessment may therefore have a role in the preoperative counselling of patients and possibly guide postoperative management of LUTS, especially if OAB is present.

Background: Prostate cancer (PCa) is a prevalent malignancy in men, with increasing incidence and longer wait times for curative surgery, particularly in public health systems. While the impact of surgical wait time (SWT) on oncological outcomes in PCa remains controversial, its influence on patient‐reported outcomes has not been thoroughly evaluated. Objective: To assess the impact of SWT on both oncological and psychological outcomes in patients undergoing robot‐assisted radical prostatectomy (RARP) for preoperative ISUP grade 2 and 3 PCa. Methods: This retrospective single‐center study included patients who underwent RARP for intermediate risk localized PCa between April 2016 and August 2024. Patients were stratified into two groups based on SWT: < 6 months vs. ≥ 6 months. The primary outcome was recurrence‐free survival (RFS) for all patients. Secondary outcomes included RFS in a high‐risk subgroup defined by pathological features (pT3 stage, seminal vesicle invasion, extracapsular extension, and positive surgical margins), as well as a comparison of functional outcomes between the two groups. Patient‐reported outcomes were evaluated using SF‐36 (mental and physical components) and the Decision Regret Scale (DRS) at 6 weeks, 3 months, 6 months, and 1 year. Statistical analyses included Kaplan–Meier survival estimates, Cox proportional hazard models, and comparative tests with p < 0.05 considered significant. Results: 218 patients have been included. RFS did not significantly differ between groups ( p = 0.98), including among high‐risk patients ( p = 1.00). No significant differences were found in extraprostatic extension, seminal vesicle invasion, positive surgical margins, or ISUP upgrading between groups. Similarly, changes in both SF‐36 physical and mental and DRS scores showed no statistically significant differences at all time points. Conclusion: In this cohort of patients with intermediate‐risk PCa, SWT beyond 6 months did not adversely affect oncological or health‐related quality of life outcomes.

BACKGROUND Artificial intelligence (AI) chatbots, such as ChatGPT, have made significant progress. These chatbots, particularly popular among health care professionals and patients, are transforming patient education and disease experience with personalized information. Accurate, timely patient education is crucial for informed decision-making, especially regarding prostate-specific antigen screening and treatment options. However, the accuracy and reliability of AI chatbots’ medical information must be rigorously evaluated. Studies testing ChatGPT’s knowledge of prostate cancer are emerging, but there is a need for ongoing evaluation to ensure the quality and safety of information provided to patients. OBJECTIVE This study aims to evaluate the quality, accuracy, and readability of ChatGPT-4’s responses to common prostate cancer questions posed by patients. METHODS Overall, 8 questions were formulated with an inductive approach based on information topics in peer-reviewed literature and Google Trends data. Adapted versions of the Patient Education Materials Assessment Tool for AI (PEMAT-AI), Global Quality Score, and DISCERN-AI tools were used by 4 independent reviewers to assess the quality of the AI responses. The 8 AI outputs were judged by 7 expert urologists, using an assessment framework developed to assess accuracy, safety, appropriateness, actionability, and effectiveness. The AI responses’ readability was assessed using established algorithms (Flesch Reading Ease score, Gunning Fog Index, Flesch-Kincaid Grade Level, The Coleman-Liau Index, and Simple Measure of Gobbledygook [SMOG] Index). A brief tool (Reference Assessment AI [REF-AI]) was developed to analyze the references provided by AI outputs, assessing for reference hallucination, relevance, and quality of references. RESULTS The PEMAT-AI understandability score was very good (mean 79.44%, SD 10.44%), the DISCERN-AI rating was scored as “good” quality (mean 13.88, SD 0.93), and the Global Quality Score was high (mean 4.46/5, SD 0.50). Natural Language Assessment Tool for AI had pooled mean accuracy of 3.96 (SD 0.91), safety of 4.32 (SD 0.86), appropriateness of 4.45 (SD 0.81), actionability of 4.05 (SD 1.15), and effectiveness of 4.09 (SD 0.98). The readability algorithm consensus was “difficult to read” (Flesch Reading Ease score mean 45.97, SD 8.69; Gunning Fog Index mean 14.55, SD 4.79), averaging an 11th-grade reading level, equivalent to 15- to 17-year-olds (Flesch-Kincaid Grade Level mean 12.12, SD 4.34; The Coleman-Liau Index mean 12.75, SD 1.98; SMOG Index mean 11.06, SD 3.20). REF-AI identified 2 reference hallucinations, while the majority (28/30, 93%) of references appropriately supplemented the text. Most references (26/30, 86%) were from reputable government organizations, while a handful were direct citations from scientific literature. CONCLUSIONS Our analysis found that ChatGPT-4 provides generally good responses to common prostate cancer queries, making it a potentially valuable tool for patient education in prostate cancer care. Objective quality assessment tools indicated that the natural language processing outputs were generally reliable and appropriate, but there is room for improvement.