Search

PURPOSE Accurate risk assessment is essential for the success of population screening programs in breast cancer. Models with high sensitivity and specificity would enable programs to target more elaborate screening efforts to high-risk populations, while minimizing overtreatment for the rest. Artificial intelligence (AI)-based risk models have demonstrated a significant advance over risk models used today in clinical practice. However, the responsible deployment of novel AI requires careful validation across diverse populations. To this end, we validate our AI-based model, Mirai, across globally diverse screening populations. METHODS We collected screening mammograms and pathology-confirmed breast cancer outcomes from Massachusetts General Hospital, USA; Novant, USA; Emory, USA; Maccabi-Assuta, Israel; Karolinska, Sweden; Chang Gung Memorial Hospital, Taiwan; and Barretos, Brazil. We evaluated Uno's concordance index for Mirai in predicting risk of breast cancer at one to five years from the mammogram. RESULTS A total of 128,793 mammograms from 62,185 patients were collected across the seven sites, of which 3,815 were followed by a cancer diagnosis within 5 years. Mirai obtained concordance indices of 0.75 (95% CI, 0.72 to 0.78), 0.75 (95% CI, 0.70 to 0.80), 0.77 (95% CI, 0.75 to 0.79), 0.77 (95% CI, 0.73 to 0.81), 0.81 (95% CI, 0.79 to 0.82), 0.79 (95% CI, 0.76 to 0.83), and 0.84 (95% CI, 0.81 to 0.88) at Massachusetts General Hospital, Novant, Emory, Maccabi-Assuta, Karolinska, Chang Gung Memorial Hospital, and Barretos, respectively. CONCLUSION Mirai, a mammography-based risk model, maintained its accuracy across globally diverse test sets from seven hospitals across five countries. This is the broadest validation to date of an AI-based breast cancer model and suggests that the technology can offer broad and equitable improvements in care.

Screening programs must balance the benefits of early detection against the costs of over screening. Achieving this goal relies on two complementary technologies: (1) the ability to assess patient risk, (2) the ability to develop personalized screening programs given that risk. While methodologies for assessing patient risk have significantly improved with new advances in deep learning applied to imaging and genetics, our ability to personalize screening policies still lags behind. Here, we introduce a novel reinforcement learning-based framework for personalized screening, Tempo, and demonstrate its efficacy in the context of breast cancer. We trained our risk-based screening policies on a large screening mammography dataset from Massachusetts General Hospital (MGH) USA and validated them on held-out patients from MGH, and on external datasets from Emory USA, Karolinska Sweden and Chang Gung Memorial Hospital (CGMH) Taiwan. Across all test sets, we found that a Tempo policy combined with an image-based AI risk model was significantly more efficient than current regimes used in clinical practice in terms of simulated early detection per screen frequency. Moreover, we showed that the same Tempo policy can be easily adapted to a wide range of possible screening preferences, allowing clinicians to select their desired early detection to screening cost trade-off without training a new policy. Finally, we demonstrated Tempo policies based on AI-based risk models out performed Tempo policies based on less accurate clinical risk models. Altogether, our results show that pairing AI-based risk models with agile AI-designed screening policies has the potential to improve screening programs, advancing early detection while reducing over-screening.