Search

Background Although several clinical breast cancer risk models are used to guide screening and prevention, they have only moderate discrimination. Purpose To compare selected existing mammography artificial intelligence (AI) algorithms and the Breast Cancer Surveillance Consortium (BCSC) risk model for prediction of 5-year risk. Materials and Methods This retrospective case-cohort study included data in women with a negative screening mammographic examination (no visible evidence of cancer) in 2016, who were followed until 2021 at Kaiser Permanente Northern California. Women with prior breast cancer or a highly penetrant gene mutation were excluded. Of the 324 009 eligible women, a random subcohort was selected, regardless of cancer status, to which all additional patients with breast cancer were added. The index screening mammographic examination was used as input for five AI algorithms to generate continuous scores that were compared with the BCSC clinical risk score. Risk estimates for incident breast cancer 0 to 5 years after the initial mammographic examination were calculated using a time-dependent area under the receiver operating characteristic curve (AUC). Results The subcohort included 13 628 patients, of whom 193 had incident cancer. Incident cancers in eligible patients (additional 4391 of 324 009) were also included. For incident cancers at 0 to 5 years, the time-dependent AUC for BCSC was 0.61 (95% CI: 0.60, 0.62). AI algorithms had higher time-dependent AUCs than did BCSC, ranging from 0.63 to 0.67 (Bonferroni-adjusted P < .0016). Time-dependent AUCs for combined BCSC and AI models were slightly higher than AI alone (AI with BCSC time-dependent AUC range, 0.66-0.68; Bonferroni-adjusted P < .0016). Conclusion When using a negative screening examination, AI algorithms performed better than the BCSC risk model for predicting breast cancer risk at 0 to 5 years. Combined AI and BCSC models further improved prediction. © RSNA, 2023 Supplemental material is available for this article.

Purpose: To examine whether overall survival (OS) differs for male and female patients with advanced soft-tissue sarcoma (STS)., Experimental Design: The study included patients from Kaiser Permanente Northern California and Stanford Cancer Center with grade 2 and 3 locally advanced or metastatic STS whose tumor underwent next-generation sequencing. We used Cox regression modeling to examine association of sex and OS adjusting for other important factors., Results: Among 388 eligible patients, 174 had leiomyosarcoma (LMS), 136 had undifferentiated pleomorphic sarcoma (UPS), and 78 had liposarcoma. OS for male versus female patients appeared to be slightly better among the full cohort [HR = 0.89; 95% confidence interval (CI), 0.66-1.20]; this association appeared to be stronger among the subsets of patients with LMS (HR = 0.76; 95% CI, 0.39-1.49) or liposarcoma (HR = 0.74; 95% CI, 0.32-1.70). Better OS for male versus female patients was also observed among all molecular subgroups except mutRB1 and mutATRX, especially among patients whose tumor retained wtTP53 (HR = 0.73; 95% CI, 0.44-1.18), wtCDKN2A (HR = 0.85; 95% CI, 0.59-1.23), wtRB1 (HR = 0.73; 95% CI, 0.51-1.04), and among patients whose tumor had mutPTEN (HR = 0.37; 95% CI, 0.09-1.62). OS also appeared to be better for males in the MSK-IMPACT and TCGA datasets., Conclusions: A fairly consistent pattern of apparent better OS for males across histologic and molecular subgroups of STS was observed. If confirmed, our results could have implications for clinical practice for prognostic stratification and possibly treatment tailoring as well as for future clinical trials design., (©2023 The Authors; Published by the American Association for Cancer Research.)