Prognosis articles from across Nature Portfolio

Nderitu et al. present deep learning systems developed to predict emergent referable diabetic retinopathy and maculopathy over 1, 2 and 3 years. Using validated tabular, image and multimodal systems they aim to individualise risk-based screening.

Analysis of data related to the Ukraine famine of 1932–1933 shows that in utero exposure to famine increases the risk of adult type 2 diabetes by more than twofold.

Researchers developed an AI-enabled, battery-operated tool that can be operated by clinicians with no sonography experience — and that measures gestational age as accurately as high-specification ultrasound.

For women with kidney disease of childbearing age, kidney care should feature discussions of pregnancy, including informed counseling and support. Health disparities between regions with different levels of income are undeniable, but special care programs aimed at the early identification and management of patients at risk can greatly decrease the magnitude of the problem.