The present study by Sardanelli et al. explores a review with foresight of how artificial intelligence (AI) could transform the current processes of breast cancer prevention, with comparison between currently used techniques and future ones. Multiple cancer risk prediction models which integrate imaging data with clinical, genetic, and lifestyle information were examined by their ability to accurately predict an individual’s breast cancer likelihood. This process is heavily assisted and made simple by AI due to its ability to sort and read through large datasets at almost impossible speeds. In imaging, deep learning and radiomics approaches are applied to processes governing early lesion detection, breast density quantification, and the assessment of microcalcification in breast tissue. Sardanelli et al. further discusses many AI systems designed to triage screening exams by keenly qualifying cases as high-risk and requiring human attention while knowing which cases could be deprioritized without concern. Results from testing and quality review with oncologists conclude that the tested AI models increased cancer detection rates by 25% and reduced provider workload by 40%. Further results speak for the analysis technology’s ability to refine sensitivity and specificity, and stratify determined data with a higher precision than that of traditional models of identification. However, limitations for the technology include accessibility to technology, bias against non-human opinion, and the overall difficulty that comes with implementation into healthcare workflows. Thus, further research and innovation must be performed to assure that the addition of such technology is a benefit, and not a detriment in disguise.