Hellstrom, Wayne J.G.

Abstract Introduction An iteration of artificial intelligence (AI), large language models (LLMs), such as ChatGPT, have recently gained popularity as a potential educational resource for patients, students, and researchers. LLMs utilize deep learning algorithms to predict the next word in a sequence based on a data library of 300 billion words. Recent studies have shown that while LLMs provide useful information, they are limited due to producing false and nonsensical information. A focus of studies has been on the utility of ChatGPT as an educational resource to patients and learners; however, no study has investigated the utilization of ChatGPT to write a scientific review. AI- generated systematic reviews would be valuable to the dynamic field of urology, especially in terms of research and innovation. Objective Considering the limitations of ChatGPT in performing data analysis, the aim of this project was to assess the utility of AI in constructing introductions of a systematic review on urologic issues and to compare these AI-generated introductions to published introductions written by humans. Methods ChatGPT (4.0), available at www.chat.openai.com, was used to construct three introductions to three different systematic reviews on the following topics: testosterone therapy and cardiovascular events, safety and efficacy of noninvasive therapies for Peyronie’s disease, and erectile dysfunction after radical prostatectomy. Introductions from published systematic reviews in each of the above topics were also obtained. Five different experts in these topics, who were blinded to which introductions were AI generated, reviewed then assessed the introductions for the following parameters: completeness, engagement, accuracy, logic, and clarity of objective. Introductions were assessed for baseline literary differences as well. Results There were no significant differences in the words, characters, number of sentences, and length of sentences between AI-generated introductions compared to those written by humans. There was a statistically significant difference in word length, with AI having a lower average of word length. AI scored significantly higher on average in the categories of completeness and engagement. We did not observe a significant difference between the two groups in the other categories. These observed findings demonstrate that AI can synthesize urologic literature (sexual medicine/men’s health) and generate introductions of a systematic review that are minimally noninferior and possibly superior regarding engagement and completeness. The limitations from this study include a small sample size (5) and the exclusive focus on AI-generated introductions rather than other AI-generated sections of a systematic review. Conclusions Our study reveals that ChatGPT, as an LLM, can provide a noninferior, possibly superior, introduction to a systematic review on topics of urologic sexual medicine and men’s health. As more facets of AI are developed, such as data integration and analysis, AI could be used to generate entire systematic reviews noninferior to those written by humans. Ethical principles of using AI in scientific literature should be examined and discussed prior to the development of more enhanced LLMs. Disclosure No.

Abstract Introduction Climacturia has been reported in up to 64% of patients following radical prostatectomy (RP). In 2017, a prospective multicenter, multinational, investigational pilot study was conducted examining outcomes using a novel surgical technique, the Mini-Jupette sling, for the management of men with post-RP erectile dysfunction (ED) and climacturia and/or minimal stress urinary incontinence (SUI). We sought to report the 5-year outcomes from this original cohort. Objective To assess long-term safety and efficacy of the mini-jupette sling in the treatment of ED and concomitant mild SUI and/or climacturia Methods We identified patients who were enrolled in the previous multicenter study with post-RP ED and climacturia and/or mild SUI (2 ppd) and underwent IPP insertion with simultaneous placement of a Mini-Jupette sling. Data including current ppd, improvement in climacturia, complications, need for revision of IPP or additional urinary incontinence surgery, and date of most recent follow-up were collected. Results Of the original 38 patients, 5 have since died and 10 were lost to follow-up with 23/38 (61%) patients available for evaluation of long-term outcomes. The average follow-up time was 59 months (SD= 8.8) with a mean age of 69 years (SD= 6.8). Most patients (n=21, 91%) had subjective improvement of SUI and climacturia. One patient with persistent bothersome incontinence underwent artificial urinary sphincter (AUS) placement in 2018 with no complications, while the other is still considering a repeat procedure due to minor but persistent SUI. The mean ppd decreased from 1.4 preoperatively to 0.3 at a mean 5 years of follow-up. Most patients reported satisfaction in their urinary symptoms with 91% and 73% reporting improvement in SUI and climacturia respectively, compared to 86% and 93% respectively in the original series. One (4.3%) patient had an IPP revision for pump malfunction. There were no device infections reported. Conclusions The Mini-Jupette sling appears to be a safe and effective procedure with durable improvements in SUI and climacturia at 5 years of follow-up. Disclosure Any of the authors act as a consultant, employee or shareholder of an industry for: Coloplast, Clarus Therapeutics, Antares Pharma, Acerus, Intuitive Surgical, Fidalis, Hims & Hers Health Inc

Abstract Background Erectile dysfunction (ED) is a common condition that may affect men of all ages; in 1999, a Process of Care Model was developed to provide clinicians with recommendations regarding the evaluation and management of ED. Aim To reflect the evolution of the study of ED since 1999, this update to the process of care model presents health care providers with a tool kit to facilitate patient interactions, comprehensive evaluation, and counseling for ED. Methods A cross-disciplinary panel of international experts met to propose updates to the 1999 process of care model from a global perspective. The updated model was designed to be evidence-based, data-driven, and accessible to a wide range of health care providers. Outcomes This article summarizes the resulting discussion of the expert meeting and focuses on ED evaluation. The management of ED is discussed in an article by Muhall et al (J Sex Med 2018;15:1280-1292). Results A comprehensive approach to the evaluation of ED is warranted because ED may involve both psychological and organic components. The updated process of care model for evaluation was divided into core and optional components and now focuses on the combination of first-line pharmacotherapy and counseling in consideration of patient sexual dynamics. Clinical Implications Patient evaluation for ED should encompass a variety of aspects, including medical history, sexual history, physical examination, psychological evaluation, laboratory testing, and possibly adjunctive testing. Strengths & Limitations This update draws on author expertise and experience to provide multi-faceted guidance for the evaluation of ED in a modern context. Although a limited number of contributors provided input on the update, these experts represent diverse fields that encounter patients with ED. Additionally, no meta-analyses were performed to further support the ED evaluation guidelines presented. Conclusion Comprehensive evaluation of ED affords health care providers an opportunity to address medical, psychological/psycho-social, and sexual issues associated with ED, with the ultimate goal being effective management and possibly resolution of ED. While some or all techniques described in the updated model may be needed for each patient, evaluation should in all cases be thorough.