Long-Term Performance of an Image-Based Short-Term Risk Model for Breast Cancer

Abstract

PURPOSE Image-derived artificial intelligence–based short-term risk models for breast cancer have shown high discriminatory performance compared with traditional lifestyle/familial-based risk models. The long-term performance of image-derived risk models has not been investigated. METHODS We performed a case-cohort study of 8,604 randomly selected women within a mammography screening cohort initiated in 2010 in Sweden for women age 40-74 years. Mammograms, age, lifestyle, and familial risk factors were collected at study entry. In all, 2,028 incident breast cancers were identified through register matching in May 2022 (206 incident breast cancers were found in the subcohort). The image-based model extracted mammographic features (density, microcalcifications, masses, and left-right breast asymmetries of these features) and age from study entry mammograms. The Tyrer-Cuzick v8 risk model incorporates self-reported lifestyle and familial risk factors and mammographic density to estimate risk. Absolute risks were estimated, and age-adjusted AUC model performances (aAUCs) were compared across the 10-year period. RESULTS The aAUCs of the image-based risk model ranged from 0.74 (95% CI, 0.70 to 0.78) to 0.65 (95% CI, 0.63 to 0.66) for breast cancers developed 1-10 years after study entry; the corresponding Tyrer-Cuzick aAUCs were 0.62 (95% CI, 0.56 to 0.67) to 0.60 (95% CI, 0.58 to 0.61). For symptomatic cancers, the aAUCs for the image-based model were ≥0.75 during the first 3 years. Women with high and low mammographic density showed similar aAUCs. Throughout the 10-year follow-up, 20% of all women with breast cancers were deemed high-risk at study entry by the image-based risk model compared with 7.1% using the lifestyle familial-based model ( P < .01). CONCLUSION The image-based risk model outperformed the Tyrer-Cuzick v8 model for both short-term and long-term risk assessment and could be used to identify women who may benefit from supplemental screening and risk reduction strategies.

Breast cancer risk prediction using machine learning: a systematic review

“…A study conducted by Eriksson et al. ( 62 ) compared AI-based short-term breast cancer risk methods using mammograms with traditional lifestyle/familial-based risk methods. Analyzing data from 8,604 women aged 40 to 74 years, the image-based model, which utilized mammographic characteristics and age, outperformed the lifestyle/familial-based model.…”

“…Eriksson et al. ( 62 ) compared AI-based risk models with traditional ones, highlighting AI’s potential for long-term risk analysis. Kayikci et al.…”

Artificial Intelligence Applications in Breast Imaging: Current Status and Future Directions

“…New developments in AI image-based risk models demonstrate promising results in cancer risk assessment, in some instances outperforming traditional cancer risk assessment models. A case-cohort study of an AI image-based mammography risk model assessed the short-term and long-term performance of its model compared to the Tyrer-Cuzick version 8 model over a period of 10 years [47]. The image-based AI model outperformed the Tyrer-Cuzick model in both short-term and long-term assessment when evaluating approximately 8600 women, with age-adjusted AUC AI model performances ranging from 0.74 to 0.65 for breast cancers developed in 1 to 10 years, significantly exceeding the Tyrer-Cuzick age-adjusted AUCs of 0.62 to 0.60 in this time period [47].…”

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

“…For this reason, we performed an external validation of a previously developed image-derived artificial intelligence (AI)E-based risk model, which was designed to predict risk of breast cancer in the short-term, for its ability to predict women who return with a breast cancer before or at the next scheduled screen in two years after a negative screen. We used the ProFound AI Risk (iCAD Inc., Nashua, NH) model 15 , 16 in a European setting including four screening populations in Italy, Spain, and Germany. The model is available for clinical use in the U.S. and Europe.…”