A Clinical Risk Model for Personalized Screening and Prevention of Breast Cancer

Abstract

Background: Image-derived artificial intelligence (AI) risk models have shown promise in identifying high-risk women in the short term. The long-term performance of image-derived risk models expanded with clinical factors has not been investigated. Methods: We performed a case–cohort study of 8110 women aged 40–74 randomly selected from a Swedish mammography screening cohort initiated in 2010 together with 1661 incident BCs diagnosed before January 2022. The imaging-only AI risk model extracted mammographic features and age at screening. Additional lifestyle/familial risk factors were incorporated into the lifestyle/familial-expanded AI model. Absolute risks were calculated using the two models and the clinical Tyrer–Cuzick v8 model. Age-adjusted model performances were compared across the 10-year follow-up. Results: The AUCs of the lifestyle/familial-expanded AI risk model ranged from 0.75 (95%CI: 0.70–0.80) to 0.68 (95%CI: 0.66–0.69) 1–10 years after study entry. Corresponding AUCs were 0.72 (95%CI: 0.66–0.78) to 0.65 (95%CI: 0.63–0.66) for the imaging-only model and 0.62 (95%CI: 0.55–0.68) to 0.60 (95%CI: 0.58–0.61) for Tyrer–Cuzick v8. The increased performances were observed in multiple risk subgroups and cancer subtypes. Among the 5% of women at highest risk, the PPV was 5.8% using the lifestyle/familial-expanded model compared with 5.3% using the imaging-only model, p < 0.01, and 4.6% for Tyrer–Cuzick, p < 0.01. Conclusions: The lifestyle/familial-expanded AI risk model showed higher performance for both long-term and short-term risk assessment compared with imaging-only and Tyrer–Cuzick models.

European validation of an image-derived AI-based short-term risk model for individualized breast cancer screening—a nested case-control study

“…42 A recent study indicated that an image-based model not only showed an overall higher discriminative performance compared to a clinical lifestyle/familial-based risk tool, but also higher discriminatory performances across subgroups of women by established risk factors of breast cancer and by breast cancer subtypes. 29 Considering the reporting from several research groups on the performance of image-based risk models, such newer approaches for identifying women in need to supplemental screening and a shorter screening interval may be considered in updated screening guidelines. 39 , 43 , 44 , 45 However, the risk-benefit balance of these models at an individual and societal level needs to be assessed before their clinical implementation for an individualized screening approach.…”

Predicting long term breast cancer risk using longitudinal mammographic screening history

“…The mean age is 53.77 (11.79) and 56.18 (11.68) for subcohort and case groups, respectively 26,33 . The table also reports the family history of breast cancer and ovarian cancer for both groups.…”

Modeling correlated pairs of mammogram images

“…Our work, along with other studies, has demonstrated that incorporating the image alongside mammographic density can enhance long-term breast cancer risk prediction. [4][5][6] However, in our previous work, we relied on averaging between the pair of images after proper image registration. 4,5 As a result, there has been a lack of investigation into studying the correlated pair of images as a whole.…”