RESUMO
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.
RESUMO
OBJECTIVES: Understanding the drivers of delays from diagnosis to treatment can elucidate how to reduce the time to treatment (TTT) in patients with prostate cancer. In addition, the available treatments depending on the stage of cancer can vary widely for many reasons. This study investigated the relationship of TTT and treatment choice with sociodemographic factors in patients with prostate cancer who underwent external beam radiation therapy (RT), radical prostatectomy (RP), androgen deprivation therapy (ADT), or active surveillance (AS) at a safety-net academic medical center. METHODS AND MATERIALS: A retrospective review was performed on 1088 patients who were diagnosed with nonmetastatic prostate cancer between January 2005 and December 2013. Demographic data as well as data on TTT, initial treatment choice, American Joint Committee on Cancer stage, and National Comprehensive Cancer Network risk categories were collected. Analyses of variance and multivariable logistic regression models were performed to analyze the relationship of these factors with treatment choice and TTT. RESULTS: Age, race, and marital status were significantly related to treatment choice. Patients who were nonwhite and older than 60 years were less likely to undergo RP. Black patients were 3.8 times more likely to undergo RT compared with white patients. The median TTT was 75 days. Longer time delays were significant in patients of older age, nonwhite race/ethnicity, non-English speakers, those with noncommercial insurance, and those with non-married status. The average TTT of high-risk patients was 25 days longer than that of low-risk patients. Patients who underwent RT had an average TTT that was 34 days longer than that of RP patients. CONCLUSIONS: The treatment choice and TTT of patients with prostate cancer are affected by demographic factors such as age, race, marital status, and insurance, as well as clinical factors including stage and risk category of disease.
