Adequacy of prostate cancer prevention and screening recommendations provided by an artificial intelligence-powered large language model.

PURPOSE: We aimed to assess the appropriateness of ChatGPT in providing answers related to prostate cancer (PCa) screening, comparing GPT-3.5 and GPT-4. METHODS: A committee of five reviewers designed 30 questions related to PCa screening, categorized into three difficulty levels. The questions were formulated identically for both GPTs three times, varying the prompts. Each reviewer assigned a score for accuracy, clarity, and conciseness. The readability was assessed by the Flesch Kincaid Grade (FKG) and Flesch Reading Ease (FRE). The mean scores were extracted and compared using the Wilcoxon test. We compared the readability across the three different prompts by ANOVA. RESULTS: In GPT-3.5 the mean score (SD) for accuracy, clarity, and conciseness was 1.5 (0.59), 1.7 (0.45), 1.7 (0.49), respectively for easy questions; 1.3 (0.67), 1.6 (0.69), 1.3 (0.65) for medium; 1.3 (0.62), 1.6 (0.56), 1.4 (0.56) for hard. In GPT-4 was 2.0 (0), 2.0 (0), 2.0 (0.14), respectively for easy questions; 1.7 (0.66), 1.8 (0.61), 1.7 (0.64) for medium; 2.0 (0.24), 1.8 (0.37), 1.9 (0.27) for hard. GPT-4 performed better for all three qualities and difficulty levels than GPT-3.5. The FKG mean for GPT-3.5 and GPT-4 answers were 12.8 (1.75) and 10.8 (1.72), respectively; the FRE for GPT-3.5 and GPT-4 was 37.3 (9.65) and 47.6 (9.88), respectively. The 2nd prompt has achieved better results in terms of clarity (all p < 0.05). CONCLUSIONS: GPT-4 displayed superior accuracy, clarity, conciseness, and readability than GPT-3.5. Though prompts influenced the quality response in both GPTs, their impact was significant only for clarity.

A Comparative Evaluation of Multiparametric Magnetic Resonance Imaging and Micro-Ultrasound for the Detection of Clinically Significant Prostate Cancer in Patients with Prior Negative Biopsies.

BACKGROUND: The diagnostic process for prostate cancer after a negative biopsy is challenging. This study compares the diagnostic accuracy of micro-ultrasound (mUS) with multiparametric magnetic resonance imaging (mpMRI) for such cases. METHODS: A retrospective cohort study was performed, targeting men with previous negative biopsies and using mUS and mpMRI to detect prostate cancer and clinically significant prostate cancer (csPCa). RESULTS: In our cohort of 1397 men, 304 had a history of negative biopsies. mUS was more sensitive than mpMRI, with better predictive value for negative results. Importantly, mUS was significantly associated with csPCa detection (adjusted odds ratio [aOR]: 6.58; 95% confidence interval [CI]: 1.15-37.8; p = 0.035). CONCLUSIONS: mUS may be preferable for diagnosing prostate cancer in previously biopsy-negative patients. However, the retrospective design of this study at a single institution suggests that further research across multiple centers is warranted.

Testing the external validity of the POUT III trial (adjuvant platnium-based chemotherapy in upper tract urothelial carcinoma) in a North American cohort.

OBJECTIVE: The European POUT III randomized controlled trial provided level-one evidence that adjuvant platinum-based chemotherapy is the standard of care following nephroureterectomy (RNU) for locally invasive or node-positive upper tract urothelial carcinoma. We aim to assess this European randomized controlled trial's generalizability (external validity) to a North American cohort, using a nationwide database. MATERIALS AND METHODS: To compare trial patients with those seen in real-world practice, we simulated the trial inclusion criteria using data from the National Cancer Database (NCDB). We identified patients with histologically confirmed transitional cell carcinoma who underwent RNU. The available demographic characteristics of the NCDB cohort were compared with the POUT III trial cohort using Chi-squared test. RESULTS: The NCDB cohort (n = 3,380) had a significantly higher proportion of older patients (age ≥ 80: 23.5% vs. 5%), and more males (68% vs. 56.2%) than the POUT cohort (Table 1, both p < 0.001). Additionally, the rate of advanced nodal disease was higher in the NCDB (N1 9.6%, N2 9.3%) than in the POUT (N1 6%, N2 3%) cohort (p < 0.001). A more extensive lymph node dissection was performed in NCDB vs. POUT patients (node≥10 10.9% vs. 3%, p < 0.001). Sensitivity analysis removing all subjects with a Charlson Comorbidity Index > 0 did not change the significance of any results. CONCLUSIONS: While the primary disease stage was similar, the rate of advanced nodal disease was significantly higher in NCDB, which might be explained partially by the more extensive lymph node dissection performed in the latter. These differences warrant caution when applying the POUT III findings to North American patients.

Comparison of patient background between a real-world North American cohort and the Göteborg-2 trial.

OBJECTIVES: To analyze the generalizability of the Göteborg-2 findings to a North American cohort. METHODS: We replicated the Göteborg-2 inclusion criteria in our Henry Ford Health (HFH) cohort, by identifying all patients 50-60 years old who had a PSA test from 2013 to 2018. The first PSA within the study period was considered PSA at entry, and included in the analysis. Chi-square test was used to compare categorical variables between the Göteborg-2 and HFH cohort, with a particular focus on Black men, who were also analyzed separately. RESULTS: The HFH patients included in the cohort were 49 456, of which 8562 were Black. In patients within the entire HFH cohort, HFH Black cohort, Göteborg Reference cohort, and Göteborg Experimental cohort, the rate of PSA ≥3 ng/mL was, respectively, 6.8%, 10.2%, 6.8%, and 6.6%. The rate of biopsy performed was, respectively, 1.8%, 4.1%, 5.8%, and 2.5%. PCa was found in, respectively, 1.4%, 3.0%, 2.3%, and 1.5%; Gleason score 3 + 3 in, respectively, 0.5%, 0.8%, 1.2%, and 0.6%; Gleason score > 3 + 3 in, respectively, 0.9%, 2.2%, 1.1%, and 0.9%. CONCLUSIONS: Our cohort had a lower biopsy rate and a lower incidence of non-csPCa diagnosis than both Göteborg cohorts, while still maintaining the same incidence of csPCa. This implies that the benefits of reducing non-csPCa diagnosis, as observed in the Experimental Göteborg cohort, are not necessarily replicable in U.S. "real-world practice" patients. Also noteworthy, we had a significantly higher percentage of Black men, who showed more aggressive disease.

Impact of lymphovascular invasion on survival in surgically treated upper tract urothelial carcinoma: a nationwide analysis.

OBJECTIVES: To assess the prognostic ability of lymphovascular invasion (LVI) in upper tract urothelial carcinoma (UTUC) as a predictor of overall survival (OS) using a large North American cohort. PATIENTS AND METHODS: Our cohort included 5940 patients with clinical M0 UTUC who underwent a radical nephroureterectomy (RNU), between 2010 and 2016, within the National Cancer Database. The main variable of interest was LVI status, and its interaction with pathological nodal (pN) status. Kaplan-Meier curves were used to depict the OS also stratifying patients on LVI status. Cox regression analysis tested the impact of LVI status on OS after accounting for the available covariates. RESULTS: The median (interquartile range [IQR]) age at diagnosis was 71 (63-78) years and most patients had pathological T1 stage disease (48.6%). Nodal status was pN0, pN1 and pNx in 45.8%, 6.3% and 47.9%, respectively. Overall, 22.1% had LVI. The median (IQR) follow-up time was 32.6 (16.0-53.3) months. At the 5-year postoperative follow-up, the estimated OS rate was 28% in patients with LVI vs 66% in those without LVI (P < 0.001). When patients were stratified based on nodal status those rates were 32% vs 68% in pN0 patients (P < 0.001), 23% vs 30% in pN1 patients (P = 0.8), and 28% vs 65% in pNx patients (P < 0.001). On multivariable analysis, the presence of LVI was associated with less favourable OS (hazard ratio 1.79, 95% confidence interval 1.60-1.99; P < 0.001). CONCLUSION: Our study assessed the impact of LVI on OS in patients with UTUC in a large North American nationwide cohort. Our series, as the largest to date, indicate that LVI is associated with less favourable survival outcomes in patients with UTUC after RNU, and this variable could be used in counselling patients about their prognosis and might be a useful tool for future trials to risk-stratify patients.

Admission Rates, Healthcare Utilization, and Inpatient Cost of Radiation Cystitis in the United States.

OBJECTIVE: To assess the incidence, cumulative healthcare burden, and financial impact of inpatient admissions for radiation cystitis (RC), while exploring practice differences in RC management between teaching and nonteaching hospitals. METHODS: We focused on 19,613 patients with a diagnosis of RC within the National Inpatient Sample (NIS) from 2008 to 2014. ICD-9 diagnosis and procedure codes were used. Complex-survey procedures were used to study the descriptive characteristics of RC patients and the procedures received during admission, stratified by hospital teaching status. Inflation-adjusted cost and cumulative annual cost were calculated for the study period. Multivariable logistic regression was used to study the impact of teaching status on the high total cost of admission. RESULTS: Median age was 76 (interquartile range 67-82) years. Most of the patients were males (73%; P < .001). 59,571 (61%) patients received at least one procedure, of which, 24,816 (25.5%) received more than one procedure. Median length of stay was 5days (interquartile range 2-9). Female patients and patients with a higher comorbidity score were more frequently treated at teaching hospitals. A higher proportion of patients received a procedure at a teaching hospital (64% vs 59%; P < .001). The inflation-adjusted cost was 9207 USD and was higher in teaching hospitals. The cumulative cost of inpatient treatment of RC was 63.5 million USD per year and 952.2 million USD over the study period. CONCLUSION: The incidence of RC-associated admissions is rising in the US. This disease is a major burden to US healthcare. The awareness of the inpatient economic burden and healthcare utilization associated with RC may have funding implications.

Male awareness of prostate cancer risk remains poor in relatives of women with germline variants in DNA-repair genes.

Abstract. Objective: The aim of this study is to evaluate male awareness of developing prostate cancer (PCa) in families with germline DNA-repair genes (DRG) variants. Materials and methods: Data were collected from a prospective, monocentric cohort study. The study was conducted in a university hospital with a multidisciplinary approach to the patient (collaboration of the Departments of Oncology, Urology, Pathology, Radiology, and Medical Genetics Laboratory). We recruited healthy males, relatives of families of women with breast or ovarian cancer who tested positive for pathogenic variants (PVs) or likely pathogenic variants (LPVs) in DRGs. A dedicated PCa screening was designed and offered to men aged 35 to 69 years, based on early visits with digital rectal examination (DRE), prostate health index (PHI) measurement, multiparametric magnetic resonance imaging (mpMRI) and, if necessary, targeted/systematic prostate biopsies. The primary endpoint was to evaluate the willingness of healthy men from families with a DRG variants detected in female relatives affected with breast and/or ovarian cancer to be tested for the presence of familial PVs. The secondary endpoints were the acceptance to participate if resulted positive and compliance with the screening programme. Results: Over 1256 families, of which 139 resulted positive for PVs in DRGs, we identified 378 'healthy' men aged between 35 and 69 years old. Two hundred sixty-one (69.0%) refused to be tested for DRG variants, 66 (17.5%) declared to have been previously tested, and 51 (13.5%) males were interested to be tested. Between those previously tested and those who accepted to be tested, 62 (53.0%) were positive for a DRG variant, and all of them accepted to participate in the subsequent surveillance steps. The main limitation is that is a single-centre study and a short follow-up. Conclusions: All men tested positive for a DRG variants agreed to go under the surveillance scheme. However, only 31% of 'men at risk' (i.e., relative of a DRG variant carrier) expressed their willingness to be tested for the familial DRG variant. This observation strongly supports the urgent need to implement awareness of genetic risk for PCa within the male population.