This UNO and UNMC Project Could Revolutionize How Nutrition Advice is Delivered to Expectant Mothers

Gestational diabetes is on the rise and poses serious health risks to mothers. Now, a collaboration between the University of Nebraska at Omaha (UNO) and the University of Nebraska Medical Center (UNMC) could revolutionize how nutrition advice is delivered to expectant mothers.

🔬 What’s new:

• Led by Chun-Hua Tsai, Ph.D., assistant professor of computer science at UNO’s Department of Information Systems and Quantitative Analysis (ISQA), the team is developing an AI-driven tool that turns a simple smartphone photo of a meal into personalized nutrition guidance for women with gestational diabetes.
• The system uses advanced artificial intelligence – including OpenAI’s GPT-4 Vision and other state-of-the-art models – to recognize foods in the photo and analyze portion sizes, then generates tailored dietary recommendations based on that analysis.
• Medical experts and dietitians are working alongside the AI, reviewing and refining its suggestions to ensure the nutrition advice is accurate, safe, and customized to each patient’s needs.

💡 Why it matters:

• Rates of gestational diabetes are increasing in the U.S. (along with related concerns like obesity and preterm birth), creating an urgent public health challenge for mothers and infants.
• Many patients find traditional food journaling ineffective and burdensome, which can make it harder to manage gestational diabetes. By making diet tracking as easy as snapping a photo, this approach could boost patient engagement and accuracy in reporting.
• A more engaging, AI-guided tool can help expectant mothers manage their health more easily and effectively, potentially leading to healthier pregnancies and better outcomes for both mom and baby.
• The technology also gives health care providers a new way to deliver personalized care while potentially reducing health care costs – all of which strengthens Nebraska’s reputation as a hub for health care innovation.

• Using a multimodal AI approach, the UNO-UNMC team built a system where a patient simply takes a photo of her meal, and the AI does the rest. Advanced vision and language models analyze the image to identify the foods and portion sizes, then cross-reference that information with nutritional guidelines to generate instant, tailored dietary advice.
• Throughout the development process, UNO’s Chun-Hua Tsai, Ph.D., worked alongside UNMC’s medical nutrition experts to train and fine-tune the system, ensuring the recommendations are both accurate and easy to understand. This interdisciplinary collaboration bridges technology and health care to make managing gestational diabetes more intuitive for patients.
• With promising initial results, the team is already looking ahead – preparing to seek additional NIH funding to broaden the research and even exploring the AI framework’s potential to predict which patients might develop gestational diabetes in the future.

🗣️ What they’re saying:

• Chun-Hua Tsai, Ph.D., assistant professor of computer science at the Department of Information Systems and Quantitative Analysis (ISQA): “We wanted to design a tool that makes managing gestational diabetes easier, not harder. By combining advanced AI with real-world clinical expertise, we’re turning something as simple as a smartphone photo into reliable, personalized guidance. Our hope is that this technology not only improves health outcomes for mothers but also empowers patients to feel more confident in their daily choices.”
• Ann Anderson Berry, M.D., professor in UNMC’s Division of Neonatology: “Gestational diabetes can be overwhelming for patients, but this approach makes it simpler. By harnessing AI to give immediate, tailored feedback, we’re empowering moms to manage their health more effectively and improving outcomes for both mother and baby. It’s a great example of how technology and medicine can team up to solve real-world problems.”
• Corrine K. Hanson, Ph.D., professor of medical nutrition at UNMC: “For many patients, keeping a traditional food diary is tedious and often ineffective. This tool turns a quick meal photo into instant, personalized nutrition guidance, which makes it much easier for women to stick to their diet plans. And because we’ve built the system hand-in-hand with clinical experts, providers can trust that the advice is accurate, and patients can feel confident following it.”

🤝 Grant information

• Funding source: University of Colorado (seed grant)
• Funding amount: $5,000
• Award number: Project ID UNO-00069835