Common origins and shared opportunities for breast cancer and cardiovascular disease prevention

Iron deficiency and supplementation in heart failure

Non-anaemic iron deficiency (NAID) is a strategic target in cardiovascular medicine because of its association with a range of adverse effects in various conditions. Endeavours to tackle NAID in heart failure have yielded mixed results, exposing knowledge gaps in how best to define 'iron deficiency' and the handling of iron therapies by the body. To address these gaps, we harness the latest understanding of the mechanisms of iron homeostasis outside the erythron and integrate clinical and preclinical lines of evidence. The emerging picture is that current definitions of iron deficiency do not assimilate the multiple influences at play in patients with heart failure and, consequently, fail to identify those with a truly unmet need for iron. Additionally, current iron supplementation therapies benefit only certain patients with heart failure, reflecting differences in the nature of the unmet need for iron and the modifying effects of anaemia and inflammation on the handling of iron therapies by the body. Building on these insights, we identify untapped opportunities in the management of NAID, including the refinement of current approaches and the development of novel strategies. Lessons learned from NAID in cardiovascular disease could ultimately translate into benefits for patients with other chronic conditions such as chronic kidney disease, chronic obstructive pulmonary disease and cancer.

Mammography-based deep learning model for coronary artery calcification

AIMS

Mammography, commonly used for breast cancer screening in women, can also predict cardiovascular disease. We developed mammography-based deep learning models for predicting coronary artery calcium (CAC) scores, an established predictor of coronary events.

METHODS AND RESULTS

We evaluated a subset of Korean adults who underwent image mammography and CAC computed tomography and randomly selected approximately 80% of the participants as the training dataset, used to develop a convolutional neural network (CNN) to predict detectable CAC. The sensitivity, specificity, area under the receiver operating characteristic curve (AUROC), and overall accuracy of the model's performance were evaluated. The training and validation datasets included 5235 and 1208 women, respectively [mean age, 52.6 (±10.2) years], including non-zero cases (46.8%). The CNN-based deep learning prediction model based on the Resnet18 model showed the best performance. The model was further improved using contrastive learning strategies based on positive and negative samples: sensitivity, 0.764 (95% CI, 0.667-0.830); specificity, 0.652 (95% CI, 0.614-0.710); AUROC, 0.761 (95% CI, 0.742-0.780); and accuracy, 70.8% (95% CI, 68.8-72.4). Moreover, including age and menopausal status in the model further improved its performance (AUROC, 0.776; 95% CI, 0.762-0.790). The Framingham risk score yielded an AUROC of 0.736 (95% CI, 0.712-0.761).

CONCLUSION

Mammography-based deep learning models showed promising results for predicting CAC, performing comparably to conventional risk models. This indicates mammography's potential for dual-risk assessment in breast cancer and cardiovascular disease. Further research is necessary to validate these findings in diverse populations, with a particular focus on representation from national breast screening programmes.