Artificial intelligence shows potential in breast cancer detection and prenatal risk assessment

Recent research highlights the potential for artificial intelligence to improve diagnostic accuracy in two critical areas of healthcare: breast cancer screening and prenatal risk assessment.

A review led by investigators at the UCLA Health Jonsson Comprehensive Cancer Center suggests that AI may assist radiologists in identifying subtle signs of breast cancers that are often missed during routine mammograms. Specifically, AI could help detect interval cancers—those diagnosed after a negative screening but before the next scheduled appointment. While AI shows promise in identifying patterns associated with increased risk, researchers note that the clinical benefit remains uncertain and emphasize the need to ensure these tools are safe and effective.

In a separate multicenter study involving over 500,000 pregnancies across Sweden, Chile, and Singapore, machine learning models were found to outperform current early risk assessment methods for identifying at-risk pregnancies within the first 14 weeks. The study, published in the Journal of Medical Internet Research, indicates that AI could support more personalized prenatal care by incorporating social and demographic factors. However, researchers cautioned that models may need to be tailored to specific populations, as performance varied across the different regions studied.