Nigerian-Born PhD Student Wins $30K Google Contest With AI Tool for Early Disease Detection

Jane Odum, a Nigerian-born doctoral candidate at the University of Georgia, has won first place in the MedGemma Impact Challenge for developing an AI-powered tool designed to strengthen disease surveillance in West Africa.

Her application, EpiCast, secured the $30,000 top prize in the Google-sponsored competition, which drew more than 850 teams from around the world. The contest challenges researchers to build human-centered AI solutions addressing complex healthcare issues.

The mobile-first platform is designed for low-resource settings, enabling frontline health workers to track patient symptoms and receive diagnostic support in their own language — helping to improve early detection and response to disease outbreaks.

Related post: SpendRule Secures $2M to Help Hospitals Track Spending

First Hand Experience 

Growing up in Nigeria, Odum witnessed both the Ebola and COVID-19 epidemics claim lives and overwhelm healthcare workers. Medical staff would often handwrite notes in different languages, limiting the efficiency of their systems. Odum was inspired to build a tool that would help community health workers speak in their own native languages while also streamlining diagnoses. 

“Early detection is everything in outbreak response,” Odum said. “If we can capture signals at the community level in real-time, we can change the course of an epidemic.”

Jane Odum’s disease surveillance app, EpiCast, runs directly on a mobile device rather than relying on cloud computing like most traditional AI systems. (Photo by Jason Thrasher)

Related post: Alaffia Targets Healthcare Waste with $55M Raise

Artificial Intelligence for the Healthcare Sector 

EpiCast allows healthcare workers across West Africa to describe and track patient symptoms in their native languages, rather than needing to mentally translate them into English. 

“Waiting even small amounts of time per patient can disrupt workflow in a busy clinic,” Odum said. “If the system is not fast and reliable, it will not be used.” 

Next, it converts their input into structured clinical data aligned with global health standards. By identifying symptoms, assessing severity levels, and mapping cases to standardized diagnostic codes, the program minimizes the delay in diagnosis. The result is a tool that connects informal clinical observations with formal surveillance systems, supporting earlier detection of outbreaks and faster public health response. 

Related post: 6 African Startups Using Tech to Transform Farming, Legal Services, E-Commerce, and Healthcare

Designing with the Community in Mind

Designed with low-resource communities in mind, EpiCast runs entirely on a mobile phone. Odum even optimized the advanced medical language models to function offline, essential for regions that frequently lose access to electricity. 

Odum’s work is an excellent example of how AI can be utilized to solve real-world healthcare issues. With her application, she is bringing efficient AI solutions to undersourced communities that need them the most. 

Main Image: Jane Odum l. (Photo by Jason Thrasher)