Background: Accurate and efficient triage is crucial for prioritizing care and managing resources in emergency rooms. This study investigates the effectiveness of ChatGPT, an advanced artificial intelligence system, in assisting health providers with decision-making for patients presenting with metastatic prostate cancer, focusing on the potential to improve both patient outcomes and resource allocation. Methods: Clinical data from patients with metastatic prostate cancer who presented to the emergency room between 1 May 2022 and 30 April 2023 were retrospectively collected. The primary outcome was the sensitivity and specificity of ChatGPT in determining whether a patient required admission or discharge. The secondary outcomes included the agreement between ChatGPT and emergency medicine physicians, the comprehensiveness of diagnoses, the accuracy of treatment plans proposed by both parties, and the length of medical decision making. Results: Of the 147 patients screened, 56 met the inclusion criteria. ChatGPT had a sensitivity of 95.7% in determining admission and a specificity of 18.2% in discharging patients. In 87.5% of cases, ChatGPT made the same primary diagnoses as physicians, with more accurate terminology use (42.9% vs. 21.4%, p = 0.02) and more comprehensive diagnostic lists (median number of diagnoses: 3 vs. 2, p < 0.001). Emergency Severity Index scores calculated by ChatGPT were not associated with admission (p = 0.12), hospital stay length (p = 0.91) or ICU admission (p = 0.54). Despite shorter mean word count (169 ± 66 vs. 272 ± 105, p < 0.001), ChatGPT was more likely to give additional treatment recommendations than physicians (94.3% vs. 73.5%, p < 0.001). Conclusions: Our hypothesis-generating data demonstrated that ChatGPT is associated with a high sensitivity in determining the admission of patients with metastatic prostate cancer in the emergency room. It also provides accurate and comprehensive diagnoses. These findings suggest that ChatGPT has the potential to assist health providers in improving patient triage in emergency settings, and may enhance both efficiency and quality of care provided by the physicians.

Penile squamous cell carcinoma (PSCC) is a rare malignancy, and first-line therapy typically involves cisplatin-based chemotherapy. However, these regimens are often unsuitable for patients with poor performance status or advanced age due to their toxicity. This retrospective, multicenter study evaluated patients with metastatic PSCC who received immune checkpoint inhibitor (ICI) therapy between 2017 and 2024. A total of 10 patients met the inclusion criteria. The median age was 75 years, and 50% had an ECOG performance status of 2 or higher. The objective response rate (ORR) was 30%, and the disease control rate (DCR) was 40%. The duration of response and disease control was over 12 months and 8 months respectively in all patients with response or disease control. The median progression-free survival (PFS) was 2.82 months, and the median overall survival (OS) was 4.32 months. PD-L1 and HPV-positive patients had a 67% response rate (n = 2/3). No patients experienced severe immune-related adverse events (irAEs). This multicenter retrospective analysis suggests that ICI monotherapy may be a promising treatment option for patients with advanced PSCC who are either ineligible for first-line platinum-based chemotherapy or who have progressed after platinum-based chemotherapy, including those with poor performance status. Further studies are needed to confirm these findings and identify baseline patient characteristics that may optimize selection criteria.

The recent rise in telemedicine, notably during the COVID-19 pandemic, highlights the potential of integrating artificial intelligence tools in healthcare. This study assessed the effectiveness of ChatGPT versus medical oncologists in the telemedicine-based management of metastatic prostate cancer. In this retrospective study, 102 patients who met inclusion criteria were analyzed to compare the competencies of ChatGPT and oncologists in telemedicine consultations. ChatGPT’s role in pre-charting and determining the need for in-person consultations was evaluated. The primary outcome was the concordance between ChatGPT and oncologists in treatment decisions. Results showed a moderate concordance (Cohen’s Kappa = 0.43, p < 0.001). The number of diagnoses made by both parties was not significantly different (median number of diagnoses: 5 vs. 5, p = 0.12). In conclusion, ChatGPT exhibited moderate agreement with oncologists in management via telemedicine, indicating the need for further research to explore its healthcare applications.

Compared to the urban population, patients in rural areas face healthcare disparities and experience inferior healthcare-related outcomes. To compare the healthcare quality metrics and outcomes between patients with advanced genitourinary cancers from rural versus urban areas treated at a tertiary cancer hospital, in this retrospective study, eligible patients with advanced genitourinary cancers were treated at Huntsman Cancer Institute, an NCI-Designated Comprehensive Cancer Center in Utah. Rural–urban commuting area codes were used to classify the patients’ residences as being in urban (1–3) or rural (4–10) areas. The straight line distances of the patients’ residences from the cancer center were also calculated and included in the analysis. The median household income data were obtained and calculated from “The Michigan Population Studies Center”, based on individual zip codes. In this study, 2312 patients were screened, and 1025 eligible patients were included for further analysis (metastatic prostate cancer (n = 679), metastatic bladder cancer (n = 184), and metastatic renal cell carcinoma (n = 162). Most patients (83.9%) came from urban areas, while the remainder were from rural areas. Both groups had comparable demographic profiles and tumor characteristics at baseline. The annual median household income of urban patients was $8604 higher than that of rural patients (p < 0.001). There were fewer urban patients with Medicare (44.9% vs. 50.9%) and more urban patients with private insurance (40.4% vs. 35.1%). There was no difference between the urban and rural patients regarding receiving systemic therapies, enrollment in clinical trials, or tumor genomic profiling. The overall survival rate was not significantly different between the two populations in metastatic prostate, bladder, and kidney cancer, respectively. As available in a tertiary cancer hospital, access to care can mitigate the difference in the quality of healthcare and clinical outcomes in urban versus rural patients.

BACKGROUND: Clear cell renal cell carcinoma (ccRCC) with pancreatic metastases (PM) is paradoxically associated with prolonged overall survival (OS), but the biological basis for this observation remains unclear. METHODS: We analyzed matched primary and metastatic samples from an international consortium of patients with PM ( n = 108) and compared them with a previously characterized ccRCC cohort without PM ( n = 273). RESULTS: Primary ccRCC tumors associated with PM were dominated by indolent, angiogenic phenotypes, characterized by low-grade histology and reduced mTORC1 activation (all P < 0.001). Tumors of patients with PM were often PBRM1-deficient (80.4% vs. 54.8%, P < 0.001) and rarely harbored BAP1 loss (3.7% vs. 20.7%, P < 0.001). After metastasis diagnosis, patients with PM had significantly longer median OS compared with those without PM (110 vs. 33 months, HR 0.28 [95% CI, 0.19–0.39], P < 0.001). Survival was further prolonged among patients with PBRM1 loss (143 vs. 64 months, HR 0.41 [95% CI, 0.22–0.81], P = 0.008). Notably, PM lesions were typically low-grade and PBRM1-deficient even when more aggressive and evolved clones were present in primary tumors. Finally, PBRM1 loss was associated with preferential response to angiogenesis inhibitors over immune-oncology therapy, reflected by longer time on treatment (32.1 vs. 9.1 months, HR 0.16 [95% CI, 0.06–0.39], P < 0.001). CONCLUSION: These findings illustrate selective tropism of indolent, less-evolved, PBRM1-deficient ccRCC clones for pancreatic dissemination. This biological bias likely underlies therapeutic sensitivity and favorable survival, supporting the consideration of PBRM1 status and metastatic tropism in risk stratification and treatment selection. FUNDING: NIH Kidney Cancer SPORE grant (P50CA196516); The Cancer Prevention and Research Institute of Texas (RP220294); Endowment from Jan and Bob Pickens Distinguished Professorship in Medical Science and Brock Fund for Medical Science Chair in Pathology.

Thromboembolic events (TE) are a common complication in patients with metastatic renal cell carcinoma (mRCC) and are associated with poorer clinical outcomes. However, the incidence of TE and clinical and genomic characteristics of patients with mRCC who develop this complication are poorly understood. Herein, we describe the incidence and clinical features of patients with mRCC with or without TE at our institution, and examine their association with the underlying genomic and transcriptomic characteristics of the tumor. This retrospective study included all consecutive cases of mRCC seen at our institution. A CLIA-certified lab performed tumor genomics and transcriptomics. Patients were classified based on the presence of a TE within the first year of diagnosis. Three hundred and seventy patients with mRCC were included in the study. TE was seen in 11% (42) of the patients. Patients with favorable International mRCC Database Consortium (IMDC) risk were less likely to develop a TE. In contrast, patients receiving combination treatment with a tyrosine kinase inhibitor (TKI) and an immune checkpoint inhibitor were more likely to develop a TE. No difference in overall survival among patients with or without TE was observed (52 vs. 55 months; HR 0.85, 95% CI 0.5574–1.293, p = 0.24). The most upregulated pathways in mRCC with TEs versus those without were the xenobiotic metabolism and mTORC1 signaling pathways. Our findings suggest potential biomarkers that, after external validation, could be used to better select patients who would benefit from prophylactic anticoagulation.