Validating racial and ethnic non-bias of artificial intelligence decision support for diagnostic breast ultrasound evaluation.

Purpose: Breast ultrasound suffers from low positive predictive value and specificity. Artificial intelligence (AI) proposes to improve accuracy, reduce false negatives, reduce inter- and intra-observer variability and decrease the rate of benign biopsies. Perpetuating racial/ethnic disparities in healthcare and patient outcome is a potential risk when incorporating AI-based models into clinical practice; therefore, it is necessary to validate its non-bias before clinical use. Approach: Our retrospective review assesses whether our AI decision support (DS) system demonstrates racial/ethnic bias by evaluating its performance on 1810 biopsy proven cases from nine breast imaging facilities within our health system from January 1, 2018 to October 28, 2021. Patient age, gender, race/ethnicity, AI DS output, and pathology results were obtained. Results: Significant differences in breast pathology incidence were seen across different racial and ethnic groups. Stratified analysis showed that the difference in output by our AI DS system was due to underlying differences in pathology incidence for our specific cohort and did not demonstrate statistically significant bias in output among race/ethnic groups, suggesting similar effectiveness of our AI DS system among different races (p>0.05 for all). Conclusions: Our study shows promise that an AI DS system may serve as a valuable second opinion in the detection of breast cancer on diagnostic ultrasound without significant racial or ethnic bias. AI tools are not meant to replace the radiologist, but rather to aid in screening and diagnosis without perpetuating racial/ethnic disparities.

Focal Ablative Therapy for Renal Cell Carcinoma in Transplant Allograft Kidneys.

OBJECTIVE: To evaluate outcomes after focal ablative therapy for renal cell carcinoma (RCC) in transplant allograft kidneys. METHODS: After institutional review board approval, patients with a history of RCC in a transplanted allograft kidney who underwent focal ablative therapy were identified. Complete chart reviews were performed and the relevant data were extracted for cumulative analysis. RESULTS: Six patients were treated with focal ablative therapy for RCC in a transplanted allograft kidney at our institutional between 2010 and 2017. Masses were diagnosed at a median of 8 years (range 1 month-8 years) after transplantation. Median mass size was 3 cm. Three patients were treated with microwave ablation, 1 with percutaneous irreversible electroporation, 1 with laparoscopic cryoablation, and 1 with open cryoablation. Median follow-up was 45 months (range 8-61 months). The median creatinine level was 1.65 before ablation and 1.58 1 year after ablation. No patients required dialysis after ablation. No patients developed local recurrence during the follow-up period. However, 1 patient developed lymph node metastases 4 years after ablation. Two patients died during follow-up of other causes. At the time of death both patients had functioning grafts. CONCLUSION: Focal ablative therapies are a feasible, renal-sparing intervention for the management of RCC in renal allografts at intermediate-term follow-up.

Patient Radiation Exposure in Transradial versus Transfemoral Yttrium-90 Radioembolization: A Retrospective Propensity Score-Matched Analysis.

PURPOSE: To compare differences in patient radiation exposure (PRE) during transarterial yttrium-90 (90Y) radioembolization (TARE) between transradial access (TRA) and transfemoral access (TFA). MATERIALS AND METHODS: A total of 810 consecutive first-time TARE procedures in patients from 2013 to 2017 were retrospectively reviewed. A propensity score-matching (PSM) analysis matched TRA and TFA groups on the basis of patient age, sex, weight, height, cancer type, 90Y microsphere type, and number of previous procedures from the same and opposite approaches. Matched groups were then compared by PRE measures fluoroscopy time (FT), dose-area product (DAP), and cumulative air kerma (AK). Effect size for each PRE measure was calculated. RESULTS: Before PSM, TRA and TFA groups differed significantly in mean age, weight, and number of previous procedures from the same and opposite approach (all P < .05). After PSM, each group consisted of 302 procedures (overall, n = 604) and no longer differed in any procedure performed before surgery measure. TRA did not differ from the matched TFA group regarding median FT (9.50 vs 9.40 minutes, P = .095), median DAP (67,066 vs 67,219 mGy·cm2; P = .19), or median AK (323.63 vs 248.46 mGy; P = .16). Effect sizes were 0.068, 0.054, and 0.110 for FT, DAP, and AK, respectively. CONCLUSIONS: No statistical differences were found for PRE measures between the matched TRA and TFA approach groups. Furthermore, practical effect sizes were considered to be small for AK and less than small for FT and DAP, and therefore, any differences in PRE between the radial and femoral approaches for TARE are minor and unlikely to be noticeable in everyday clinical practice.