Noninvasive early prediction of preeclampsia in pregnancy using retinal vascular features

• DOI: 10.1038/s41746-025-01582-6
• Publication Date: 2025-04-05T09:29:26Z
• Authors: Yuxuan Wu; Lixia Shen; Lanqin Zhao; Xiaohong Lin; Miaohong Xu; Zhenjun Tu; Yihong Huang; Lingyi Kong; Zhenzhe Lin; Duoru Lin; Lixue Liu; Xun Wang; Zizheng Cao; Xi Chen; Shengmei Zhou; Weiling Hu; Yunjian Huang; Shiyuan Chen; Meimei Dongye; Xulin Zhang; Dongni Wang; Danli Shi; Zilian Wang; Xiaohang Wu; Dongyu Wang; Haotian Lin

Preeclampsia (PE), a severe hypertensive disorder during pregnancy, significantly contributes to maternal and neonatal mortality. Existing prediction biomarkers are often invasive expensive, hindering their widespread application. This study introduces PROMPT (Preeclampsia Risk factor + Ophthalmic data Mean arterial pressure Prediction Test), an AI-driven model leveraging retinal photography for PE prediction, registered at ChiCTR (ChiCTR2100049850) in August 2021. Analyzing 1812 pregnancies before 14 gestational weeks, we extracted parameters using deep learning system. The achieved AUC of 0.87 (0.83-0.90) 0.91 (0.85-0.97) preterm machine learning, outperforming the baseline (p < 0.001). It also improved detection adverse pregnancy outcomes from 35% 41%. Economically, was estimated avert 1809 cases saved over $50 million per 100,000 screenings. These results position as non-invasive cost-effective tool prenatal care, especially valuable low- middle-income countries.