Bethany Hedt-Gauthier
University of North Carolina at Chapel Hill, NC·Public Health & Epidemiology
After a cesarean delivery (c-section), the surgical wound can become infected. These surgical site infections (SSIs) follow 3–15% of cesareans in the United States and add to illness and death among new mothers.
- Fields
Public Health & Epidemiology
Medicine & Clinical Research
Mathematics & Statistics
- Topics
surgical site infection
cesarean section
c-section
- Grants
- 2 known grants, through May 2029
What they work on
- Build a software library that runs an existing photo-based surgical site infection algorithm offline on a smartphone, and integrate it with Insightiv Technologies into a full tool for community health workers.
- Test the usability and acceptability of the mHealth-community health worker tool with 30 CHWs in rural Rwanda, using usability assessments built into the design phase.
- Assess whether home diagnoses made with the tool at days 5 and 10 match a hospital physical exam at day 16, in 450 women who delivered by cesarean.
- Compare time-to-diagnosis of cesarean complications in a randomized trial of 1,350 women assigned to tool-based home follow-up or standard care, and gather mothers' views through focus groups.
- Evaluate how accurately existing visible-photo and thermal-image infection algorithms, trained in Rwanda, perform on wound images from 6,000 women in Rwanda, Ghana and Mexico, overall and by country.
- Retrain the image algorithms to predict infections accurately across diverse skin tones, and test whether adding clinical data improves their accuracy.
- Follow 1,200 infection-free women to days 20 and 30 to see whether later monitoring is needed and whether day-10 wound images predict delayed infections.
More about the research
Catching an infection early helps. But in rural areas, especially in sub-Saharan Africa, getting back to a clinic for a wound check costs money and is physically hard. The lab asks whether smartphone photos of the wound, read by computer algorithms and gathered by community health workers (CHWs, trained local workers who visit families at home), can make post-cesarean follow-up safer, cheaper and more accessible. Two projects connect here: one builds and tests a phone-based home follow-up tool in Rwanda, and the other checks and improves the image-reading algorithms across populations with different skin tones.
Why it matters
Mothers recovering from cesarean delivery in rural Rwanda, Ghana, Mexico and the rural United States could benefit from earlier detection of wound infections without costly trips to a hospital. A validated phone tool could let community health workers provide safe in-home follow-up. Datasets that cover a wide range of skin tones could help make AI infection-prediction algorithms less biased for women in the US and worldwide.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Valencia Koomson
Tufts University, MA·Engineering
Adapt the Medtronic Empower Health app into AHOMKA, a Ghana-specific mobile health platform, using a user-centered design process that is revised step by step with feedback from patients and clinicians.
Daniel Walker
Ohio State University, OH·Public Health & Epidemiology
Test how integrated data systems, CHW learning collaboratives and resilience skill building affect timely prenatal and postpartum care, depression and preterm birth, using a 2x2 factorial cluster randomized trial across Ohio's Pathways Community Hubs.
Kristin Beima-Sofie
University of Washington, WA·Public Health & Epidemiology
Assess the needs, preferences, facilitators and barriers that youth living with HIV in Kenya face when moving to adult care, and use these findings to build a first iTake Charge digital prototype.
The school
University of North Carolina at Chapel Hill: 72 labs on PI Pages, $1.6B a year on research, 523 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.