Faculty Bibliography

BACKGROUND:The Chatbot Assessment Reporting Tool (CHART) is a reporting guideline developed to provide reporting recommendations for studies evaluating the performance of generative artificial intelligence (AI)-driven chatbots when summarizing clinical evidence and providing health advice, referred to as Chatbot Health Advice (CHA) studies. METHODS:CHART was developed in several phases after performing a comprehensive systematic review to identify variation in the conduct, reporting, and methodology in CHA studies. Findings from the review were used to develop a draft checklist that was revised through an international, multidisciplinary modified asynchronous Delphi consensus process of 531 stakeholders, three synchronous panel consensus meetings of 48 stakeholders, and subsequent pilot testing of the checklist. RESULTS:CHART includes 12 items and 39 subitems to promote transparent and comprehensive reporting of CHA studies. These include Title (subitem 1a), Abstract/Summary (subitem 1b), Background (subitems 2ab), Model Identifiers (subitems 3ab), Model Details (subitems 4abc), Prompt Engineering (subitems 5ab), Query Strategy (subitems 6abcd), Performance Evaluation (subitems 7ab), Sample Size (subitem 8), Data Analysis (subitem 9a), Results (subitems 10abc), Discussion (subitems 11abc), Disclosures (subitem 12a), Funding (subitem 12b), Ethics (subitem 12c), Protocol (subitem 12d), and Data Availability (subitem 12e). CONCLUSION/CONCLUSIONS:The CHART checklist and corresponding methodological diagram were designed to support key stakeholders including clinicians, researchers, editors, peer reviewers, and readers in reporting, understanding, and interpreting the findings of CHA studies.

BACKGROUND AND OBJECTIVE/OBJECTIVE:The health care sector is a significant contributor to greenhouse gas (GHG) emissions, and assessments of the environmental impacts of health services are essential. We aimed to evaluate the environmental impact of a highly common but controversial urology-specific blood test: the prostate-specific antigen (PSA) test. METHODS:e). The secondary outcome was the health impact attributed to the environmental harm of the test. KEY FINDINGS AND LIMITATIONS/UNASSIGNED:e, equivalent to driving 14.5 million miles, with a resulting human health impact of 6.6 disability-adjusted life years annually. This study focused on the PSA test itself, and not on emissions from staff, patient, or sample transportation; building infrastructure; or cleaning. CONCLUSIONS AND CLINICAL IMPLICATIONS/CONCLUSIONS:Although the carbon footprint of a single PSA test is small, the cumulative impact of the estimated total of 30 million PSA tests performed annually in the USA is substantial, especially when considering that a notable proportion of these tests may be performed on men who are unlikely to benefit.

The Chatbot Assessment Reporting Tool (CHART) is a reporting guideline developed to provide reporting recommendations for studies evaluating the performance of generative artificial intelligence (AI)-driven chatbots when summarizing clinical evidence and providing health advice, referred to as Chatbot Health Advice (CHA) studies. CHART was developed in several phases after performing a comprehensive systematic review to identify variation in the conduct, reporting and methodology in CHA studies. Findings from the review were used to develop a draft checklist that was revised through an international, multidisciplinary modified asynchronous Delphi consensus process of 531 stakeholders, three synchronous panel consensus meetings of 48 stakeholders, and subsequent pilot testing of the checklist. CHART includes 12 items and 39 subitems to promote transparent and comprehensive reporting of CHA studies. These include Title (subitem 1a), Abstract/Summary (subitem 1b), Background (subitems 2ab), Model Identifiers (subitem 3ab), Model Details (subitems 4abc), Prompt Engineering (subitems 5ab), Query Strategy (subitems 6abcd), Performance Evaluation (subitems 7ab), Sample Size (subitem 8), Data Analysis (subitem 9a), Results (subitems 10abc), Discussion (subitems 11abc), Disclosures (subitem 12a), Funding (subitem 12b), Ethics (subitem 12c), Protocol (subitem 12d), and Data Availability (subitem 12e). The CHART checklist and corresponding methodological diagram were designed to support key stakeholders including clinicians, researchers, editors, peer reviewers, and readers in reporting, understanding, and interpreting the findings of CHA studies.

BACKGROUND:Potential rural-urban differences in prostate cancer care are understudied, particularly regarding the utilization of advanced diagnostic tests. Herein we examined variations in Positron Emission Tomography (PET) utilization for prostate cancer care, including diagnosis, staging and treatment planning, across residential regions in the United States. METHODS:Patients newly diagnosed with prostate cancer between 2019 and 2021 and post-diagnostic PETs were identified using full Medicare claims data. PET use was assessed in all newly diagnosed patients, though indications vary by risk. Patients' counties were categorized as metro, urban, or rural, from most to least urbanized. Regional PET utilization was further examined at the level of hospital referral regions. A multivariable logistic regression model was performed to assess the impact of rurality on PET imaging. A secondary analysis included an interaction term for race to explore the effect of residence on PET imaging by racial group. RESULTS:Overall, 495 865 patients were included in the analysis: 393 861 (79.4%) lived in metro, 56 698 (11.4%) in urban and 39 707 (8.0%) in rural counties. Patients in metro counties underwent PET imaging more often (8.4%) than patients in urban (7.3%) or rural counties (7.2%), p < 0.0001. At a level of hospital referral region, PET utilization rates ranged from 2.2 to 20.8%. PET imaging was more commonly performed in White compared to Black or Hispanic patients. Rural patients were less likely to undergo PET imaging compared to metro patients (odds ratio [OR] 0.87, 95% Confidence interval [CI]: 0.82-0.92 p < 0.0001). Rural Black (OR 0.69, 95%CI 0.57-0.83, p < 0.0001) and rural White patients (OR 0.89, 95%CI 0.83-0.94 p < 0.0001) were less likely to obtain PET imaging compared to their metro counterparts, p-interaction < 0.0001. CONCLUSION/CONCLUSIONS:Rural patients were less likely to undergo PET imaging than metro patients. The effect of rurality was most pronounced among Black patients. Our findings underscore the need for strategies to support equitable use of PET imaging.

BACKGROUND:Personalized therapeutic approaches for localized prostate cancer have evolved significantly, with tissue-based biomarker tests supplementing traditional risk stratification tools. However, national testing patterns and geographic variability remain limited a decade after coverage implementation. We aimed to assess current nationwide utilization and urban-rural differences in tissue-based biomarker testing. METHODS:Using full Medicare claims data, we retrospectively identified patients with newly diagnosed prostate cancer and tissue-based biomarker testing claims from 2019 to 2023. Patients' county of residence was categorized as metro, urban, or rural. Regional testing rates were further assessed across hospital referral regions. A multivariable logistic regression model was performed to assess the effect of residence on test receipt. RESULTS:Our final cohort included 749,202 patients, of whom 79.5% lived in metro, 11.4% in urban and 8.00% in rural counties. Overall, 86,908 (11.6%) patients underwent tissue-based biomarker tests. Hospital referral region-level testing rates ranged from 2.4% to 42.7%. Rural patients were 18% less likely to undergo testing compared to metro patients (Odds Ratio [OR] 0.82 95% Confidence Interval [CI] 0.73-0.91). Independently, the odds of undergoing testing were lower among Black (OR 0.82, 95% CI 0.77-0.88) and Hispanic patients (OR 0.80, 95% CI 0.73-0.88) compared to White patients. CONCLUSION/CONCLUSIONS:This study reveals high geographic variability in tissue-based biomarker testing for prostate cancer. Further, Black and Hispanic patients were less likely to receive testing. Our findings highlight regional practice variation in the use of advanced, not routinely recommended tests and underscore the need to minimize disparities in diagnostic access.

BACKGROUND/OBJECTIVES/OBJECTIVE:Patients often face uncertainty about what they should know after prostate cancer diagnosis. Web-based information is common but is at risk of being of poor quality or readability. SUBJECTS/METHODS/METHODS:We used ChatGPT, a freely available Artificial intelligence (AI) platform, to generate enquiries about prostate cancer that a newly diagnosed patient might ask and compared to Google search trends. Then, we evaluated ChatGPT responses to these questions for clinical appropriateness and quality using standardised tools. RESULTS:ChatGPT generates broad and representative questions, and provides understandable, clinically sound advice. CONCLUSIONS:AI can guide and empower patients after prostate cancer diagnosis through education. However, the limitations of the ChatGPT language-model must not be ignored and require further evaluation and optimisation in the healthcare field.

Germline Testing (GT) for prostate cancer (PCA) is now central to PCA care and hereditary cancer assessment, with a rising role in PCA screening approaches. Guidelines have significantly expanded to include testing patients with metastatic PCA, advanced PCA or with high-risk features, and for males with or without PCA with a strong family cancer history to identify hereditary cancer syndromes for patients and their families. However, the expansion of GT has overwhelmed genetic counselling programs, necessitating the development and evaluation of alternate genetic delivery models. Furthermore, disparities in engagement in PCA GT are of major concern for impacting PCA-related and overall cancer-related outcomes for patients and their families. This review focuses on integrating PCA GT guidelines with implementation strategies and addressing PCA GT disparities to help inform current and future strategies to enhance the benefits of GT across populations.

Despite several randomized controlled trials demonstrating the benefits of combination therapies for metastatic hormone-sensitive prostate cancer (mHSPC), a significant treatment gap persists. This initiative by the Prostate Cancer Foundation (PCF) convened stakeholders from academia, community practices, industry, and patient advocacy groups to address critical challenges in mHSPC care. Expert discussions and a review of real-world evidence and meta-analyses informed the development of strategies to improve care delivery. Evaluation of the data from global registries, such as IRONMAN, and large community databases was used to assess treatment utilization patterns and disparities. Combination therapies with two agents-androgen deprivation therapy (ADT) plus an androgen receptor pathway inhibitor (ARPI)-or three agents-ADT + ARPI + docetaxel-demonstrate significant survival improvements while preserving quality of life for patients with mHSPC, yet adoption remains inconsistent. Of the eligible patients, 20%-60% remain undertreated, with geographic, financial, and systemic barriers contributing to inconsistencies in care. Younger, White, urban-dwelling patients with fewer comorbidities are more likely to receive combination treatment, highlighting disparities across populations. Meta-analyses identified a lack of standardization due to varying inclusion criteria and comparators across trials. Real-world evidence underscored disparities influenced by geographic location, practice type, and access to specialty care. Initiatives such as the PANTHER study highlight improved outcomes in Black patients treated with combination therapies, emphasizing the importance of including diverse populations in clinical trials. To bridge gaps in care, this initiative prioritizes awareness, standardization, and equitable access to evidence-based therapies. Proposed solutions include targeted knowledge dissemination strategies, development of educational resources, and advocacy for policy changes to promote guideline-concordant care. By leveraging collaborative efforts, organizations, including PCF, can contribute to enhancing survival outcomes and quality of life for all patients with mHSPC.

PURPOSE OF REVIEW/OBJECTIVE:Artificial intelligence (AI) chatbots are increasingly used as a source of information. Our objective was to review the literature on their use for patient education in urology. RECENT FINDINGS/RESULTS:There are many published studies examining the quality of AI chatbots, most commonly ChatGPT. In many studies, responses from chatbots had acceptable accuracy but were written at a difficult reading level without specific prompts to enhance readability. A few studies have examined AI chatbots for other types of patient education, such as creating lay summaries of research publications or generating handouts. SUMMARY/CONCLUSIONS:Artificial intelligence chatbots may provide an adjunctive source of patient education in the future, particularly if prompted to provide results with better readability. In addition, they may be used to rapidly generate lay research summaries, leaflets or other patient education materials for final review by experts.