Citations

Abstract Background: Many patients use artificial intelligence (AI) chatbots as a rapid source of health information. This raises important questions about the reliability and effectiveness of AI chatbots in delivering accurate and understandable information. Purpose: To evaluate and compare the accuracy, conciseness, and readability of responses from OpenAI ChatGPT-4 and Google Bard to patient inquiries concerning the novel 177Lu-PSMA-617 therapy for prostate cancer. Materials and Methods: Two experts listed the 12 most commonly asked questions by patients on 177Lu-PSMA-617 therapy. These twelve questions were prompted to OpenAI ChatGPT-4 and Google Bard. AI-generated responses were distributed using an online survey platform (Qualtrics) and blindly rated by eight experts. The performances of the AI chatbots were evaluated and compared across three domains: accuracy, conciseness, and readability. Additionally, potential safety concerns associated with AI-generated answers were also examined. The Mann-Whitney U and chi-square tests were utilized to compare the performances of AI chatbots. Results: Eight experts participated in the survey, evaluating 12 AI-generated responses across the three domains of accuracy, conciseness, and readability, resulting in 96 assessments (12 responses x 8 experts) for each domain per chatbot. ChatGPT-4 provided more accurate answers than Bard (2.95 ± 0.671 vs 2.73 ± 0.732, p=0.027). Bard's responses had better readability than ChatGPT-4 (2.79 ± 0.408 vs 2.94 ± 0.243, p=0.003). Both ChatGPT-4 and Bard achieved comparable conciseness scores (3.14 ± 0.659 vs 3.11 ± 0.679, p=0.798). Experts categorized the AI-generated responses as incorrect or partially correct at a rate of 16.6% for ChatGPT-4 and 29.1% for Bard. Bard's answers contained significantly more misleading information than those of ChatGPT-4 (p = 0.039). Conclusion: AI chatbots have gained significant attention, and their performance is continuously improving. Nonetheless, these technologies still need further improvements to be considered reliable and credible sources for patients seeking medical information on 177Lu-PSMA-617 therapy.

AbstractBackgroundFor men with prostate cancer, radiographic progression may occur without a concordant rise in prostate‐specific antigen (PSA). Our study aimed to assess the prevalence of radiographic progression using C‐11 choline positron emission tomography (PET) imaging in patients achieving ultra‐low PSA values and to evaluate clinical outcomes in this patient population.MethodsIn a single institution study, we reviewed the prospectively maintained Mayo Clinic C‐11 Choline PET metastatic prostate cancer registry to identify patients experiencing radiographic disease progression (rDP) on C‐11 choline PET scan while the PSA value was less than 0.5 ng/mL. Disease progression was confirmed by tissue biopsy or response to subsequent therapy. Clinicopathologic variables were abstracted by trained research personnel. Overall survival was estimated using the Kaplan–Meier method. Intergroup differences were assessed using the log‐rank test. A univariate and multivariate Cox regression model was performed to investigate variables associated with poor survival after rDP.ResultsA total of 1323 patients within the registry experienced rDP between 2011 and 2021, including 220 (16.6%) men with rDP occurring at low PSA level. A median (interquartile range [IQR]) of 54.7 (19.7–106.9) months elapsed between the time of prostate cancer diagnosis and low PSA rDP, during which 173 patients (78%) developed castration‐resistant prostate cancer (CRPC). Sites of low PSA rDP included local recurrence (n = 17, 8%), lymph node (n = 90, 41%), bone (n = 94, 43%) and visceral metastases (n = 19, 9%). Biopsy at the time of rDP demonstrated small‐cell or neuroendocrine features in 21% of patients with available tissue. Over a median (IQR) follow‐up of 49.4 (21.3–95.1) months from the time of low PSA rDP, 46% (n = 102) of patients died. Factors associated with poorer survival outcomes include advanced age at rDP, CRPC status, bone and visceral metastasis (p value <0.05). Visceral metastases were associated with decreased overall survival (p = 0.009 by log‐rank) as compared with other sites of rDP.ConclusionsMen with prostate cancer commonly experience metastatic progression at very low or even undetectable PSA levels. Periodic imaging, even at low absolute PSA values, may result in more timely identification of disease progression.

7543 Background: Total metabolic tumor volume (TMTV) and maximum standardized uptake value (SUVmax) may improve upon standard 18F-fluorodeoxyglucose positron emission tomography/computed tomography (PET-CT)-based assessment of advanced DLBCL during treatment. We report the association of TMTV and SUVmax changes at interim PET-CT (PET2) on survival outcomes in patients with primary refractory DLBCL (prDLBCL) and early relapsing DLBCL (erDLBCL). Methods: Adult patients with prDLBCL (less than a complete response (CR) or progression by the end of treatment (EOT)) or erDLBCL (CR at EOT with relapse within 12 months) between 2005 and 2019 at Mayo Clinic Rochester were included. The % change (Δ) from baseline to PET2 (after 2 cycles of 1L therapy) of TMTV and SUVmax were measured. A PET segmentation threshold of 1.5 liver mean SUV + two standard deviations with a minimum volume constraint of 0.5 mL was utilized (MIM Software, Inc., Cleveland OH, USA) with manual input as needed. Functional splines analysis determined SUVmax and TMTV threshold for analysis. Results: 131 patients had complete PET-CT data (N=79 prDLBCL, N=52 erDLBCL). Baseline median TMTV and SUVmax were 767.4 cm3 (range 0.9-6840.4) and 20.5 (2.0-52.6), respectively. At a median follow up of 77.6 months, 81 patients had died. 2-year OS rate was 53% (95% CI: 42-67) for patients with a PET2 ΔSUVmax decline ≥65% compared to 15% (95% CI: 7-29) for patients with a PET2 ΔSUVmax decline <65%(p<0.001). PrDLBCL had a 2-year OS rate of 48% (95% CI: 31-74) for a ΔSUVmax ≥65% compared to 7% (95% CI: 2-21) for a ΔSUVmax <65%(p<0.001), which captured 58% of prDLBCL patients (N=46). Two-year OS rate was 43% (95% CI: 34-54) for patients with a ΔTMTV ≥75% compared to 5% (95% CI: 1-35) for patients with ΔTMTV <75% (p<0.001). All patients with a ΔTMTV <75% had prDLBCL. PrDLBCL had a 2-year OS rate of 28% (95% CI: 18-44) for a ΔTMTV ≥75%. The outcomes for ΔSUVmax <65% and ΔTMTV <75% at PET2 remained significant in a cox regression model adjusted for IPI and bulky disease (>10cm)(Table). Conclusions: A ΔTMTV decline <75% or a ΔSUVmax decline <65% at PET2 identified an ultra-high-risk subgroup of DLBCL with particularly poor outcomes, that captured a high percentage of prDLBCL patients, and was significant after adjusting for IPI and bulky baseline disease. These patients may benefit from clinical trials evaluating alternative PET-adapted treatment strategies, but further evaluation among all patients with DLBCL is needed. [Table: see text]

e17057 Background: Results from the VISION trial (NCT03511664) led to the approval of lutetium-177 (177Lu)–PSMA-617 for the treatment of metastatic castration-resistant prostate cancer (mCRPC). This trial excluded patients with baseline cytopenias, thus safety in this frequently encountered patient population is unknown. We aimed to use real-world data to describe the tolerability of radioligand therapy in those with poorer bone marrow reserve. Methods: We retrospectively reviewed the records of all patients, who received a first dose of 177Lu–PSMA-617 at Mayo Clinic in the interval of April 26, 2022, to December 1, 2022. Patients were categorized as having poor marrow reserve on the basis of pre-treatment hematologic parameters, including: (1) an anemia cohort with hemoglobin (Hg) less than 9 g/dL, (2) a thrombocytopenia cohort with platelets (Plt) less than 100 x 109/L, (3) a leukopenia cohort with white blood cell count (WBC) less than 2.5 x 109/L, and (4) a multiple cytopenia cohort. These were exclusionary parameters from the VISION trial. Longitudinal laboratory data and clinical outcomes were collected and analyzed using descriptive statistics. Results: At data cutoff, 185 patients had received one or more doses of 177Lu, including 26 (14%) with at least one baseline cytopenia prior to their first cycle of treatment. In total, there were 19 (73%) patients with anemia, 3 (12%) with thrombocytopenia, 2 (8%) with leukopenia, and 2 (8%) with multiple cytopenias at baseline. The median number of cycles received thus far is 3, including 14 (54%) who are still receiving therapy and 12 (46%) who have permanently discontinued treatment. Median longitudinal changes in blood counts for the anemia cohort are presented in Table 1. Reasons for treatment discontinuation include: toxicity (n = 2), disease progression (n = 5), death (n = 4), or other (n = 1). Dose reductions or treatment delays for worsening myelosuppression were utilized in 3 (12%) and 5 (19%) patients, respectively. Transfusions of packed red blood cells or platelets were required for 16 (62%) patients. A total of 6 (23%) received care in the emergency department or were hospitalized. Conclusions: Treatment discontinuation for toxicity was rare among men with mCRPC and baseline cytopenias, while receiving 177Lu; however, these patients have an overall poor prognosis. [Table: see text]

Background: Peptide receptor radionuclide therapy with 177 Lu-dotatate is a novel therapy for metastatic neuroendocrine cancers. It undergoes reabsorption at the proximal tubule; after the breakdown of the peptide fragment, 177 Lu is retained and continues its decay process exposing the nephron to continuous low dose radiation. Pivotal NETTER-1 trial did not include patients with eGFR <50 and so its effects in CKD patients is not known. Methods: We performed a retrospective chart review of all consecutive adult patients that received 177 Lu-dotatate over 1 year at Mayo Clinic, Rochester. We analyzed renal and hematological laboratory data obtained prior to each of four treatment cycles and at 3- and 6-month post completion of all treatment. We defined CKD as eGFR <60 ml/min and AKI as creatinine increase of ⩾0.3 from baseline by AKIN criteria. Results: Overall 86 patients were included in the study with 39 (45%) with known CKD. About three patients had CKD, four with eGFR of 20–30 ml/min. About 4 (4.6%) patients had AKI and the predominant cause being hypotension. Among the CKD patients the average eGFR improved after the first cycle of PRRT therapy from baseline of 49 (13) to 53.5 (17) ml/min ( p = 0.01) with no significant decline of renal function noted at 3- and 6-months post treatment follow up. Rate of thrombocytopenia and leukopenia were significantly more in the CKD patients starting even after single treatment. No drug dose correlation was noted. Conclusion: Patients with CKD are at a higher risk of hematological toxicity especially with thrombocytopenia and require close monitoring and ongoing dose adjustment. Ongoing safety studies to assess the long-term impact of 177 Lu-dotatate on the kidney are needed.

Abstract Objectives Implicit bias is common and is thought to drive discriminatory behaviour. Having previously demonstrated discrimination against specific applicant demographics by academic radiology departments in a simulated resident selection process, the authors sought to better understand the relationship between implicit bias and discrimination, as well as the potential and mechanisms for their mitigation. Methods A total of 51 faculty reviewers at three academic radiology departments, who had participated in a 2017 audit study in which they were shown to treat applicants differently based on race or ethnicity and physical appearance, were invited to complete testing for implicit racial and weight bias using the Implicit Association Test in 2019. Respondents were also surveyed regarding awareness of their own personal racial and weight biases, as well as any prior participation in formal diversity training. Comparisons were made between implicit bias scores and applicant ratings, as well as between diversity training and self‐awareness of bias. Results A total of 31 out of 51 faculty reviewers (61%) completed and submitted results of race and weight Implicit Association Tests. A total of 74% (23/31) reported implicit anti‐obese bias, concordant with discrimination demonstrated in the resident selection simulation, in which obese applicants were rated 0.40 standard deviations (SDs) lower than non‐obese applicants ( P < .001). A total of 71% (22/31) reported implicit anti‐Black bias, discordant with application ratings, which were 0.47 SDs higher for Black than for White applicants ( P < .001). A total of 84% (26/31) of participants reported feeling self‐aware of potential racial bias at the time of application review, significantly higher than the 23% (7/31) reporting self‐awareness of potential anti‐obese bias ( P < .001). Participation in formal diversity training was not associated with implicit anti‐Black or anti‐fat bias, nor with self‐reported awareness of potential racial or weight‐based bias (all P > .2). Conclusions These findings suggest that implicit bias, as measured by the Implicit Association Test, does not inevitably lead to discrimination, and that personal awareness of implicit biases may allow their mitigation.