NIH-funded research NIH-funded research

Ethical, multimodal AI for predicting preeclampsia risk in early pregnancy

Official title: Ethical, multimodal AI tool for prediction of preeclampsia risk in early pregnancy

Funded at Brigham and Women's Hospital · NIH-11556765 · Data updated 2026-11-12

A data-driven AI tool uses early-pregnancy information from medical records, ultrasound, and notes to predict preeclampsia risk and support safer pregnancy care.

Quick facts

Grant typeNIH-funded research
Study typeNIH-funded research
Funding institutionBrigham and Women's Hospital
NIH-funded
Lab location1 site (Boston, United States)
Project startSeptember 1, 2025
Project endAugust 31, 2027
Funding year2026
Award (this year)$1,048,975
NIH project number3OT2OD038029-01S1
Project IDNIH-11556765 on NIH RePORTER

Who could benefit from this research

Could help

Pregnant individuals in early gestation whose data are available in electronic health records, imaging, and related notes, particularly within partner healthcare systems.

Less likely to help

Very early pregnancies not captured in the datasets or those who do not receive likely actionable risk information from the model.

What this research studies

This project builds an ethically-centered, multimodal AI model that analyzes structured health data, ultrasound images, and unstructured physician notes from thousands of pregnancies to identify who is at risk of preeclampsia early on. It includes time-aware embeddings, strategies to handle missing data, and external validation with diverse datasets to ensure the model works across populations. The team collaborates with ethics and human factors experts to keep patient needs and values at the forefront of the development and deployment. By incorporating polygenic risk scores for a subset of individuals, the study aims to enhance predictive performance while maintaining privacy and fairness.

Why it matters

Potential benefit: If successful, the tool could enable earlier, personalized interventions and closer monitoring to prevent complications for mothers and babies.

How similar studies have gone: Previous multimodal AI efforts in obstetrics show promise, but this project emphasizes ethics, generalizability, and external validation to strengthen evidence.

Where this research is happening

  • Brigham and Women's Hospital
    Boston, United States
    Active

Researchers

  • Principal investigator: Kovacheva, Vesela — Brigham and Women's Hospital
  • Study coordinator: Kovacheva, Vesela

Related research

Other NIH-funded projects on the same topics.

About this research

  1. This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
  2. Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
  3. For full project details, budget, and progress reports, visit the official NIH RePORTER page.
Last reviewed 2026-11-14 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.