Tulane University professor creates AI-driven SMART-pred platform that aims to transform public health surveillance

A new artificial intelligence–powered platform developed at Tulane University could change how public health professionals detect and respond to disease by shifting from a reactive approach to one that anticipates health threats before they escalate. 

The project, known as SMART-pred, is led by Principal Investigator Dr. Samuel Kakraba, assistant professor of biostatistics and data science at the Celia Scott Weatherhead School of Public Health and Tropical Medicine and a faculty affiliate of the Connolly Alexander Institute for Data Science (CAIDS). The initiative recently received support through a joint seed grant program from CAIDS and the Weatherhead School focused on advancing AI and machine learning in public health research.  

Dr. Kakraba collaborated with Tulane faculty and students to bring SMART-pred to life. He worked alongside faculty members Dr. Sudesh K. Srivastav and Dr. Jeffrey G. Shaffer, doctoral student Edmund F. Agyemang, and former master's student Han Wenzheng, all from the Department of Biostatistics and Data Science.  

SMART-pred is designed to analyze large volumes of health data and identify patterns that signal disease risk or emerging public health concerns before those trends are visible through traditional surveillance systems. 

“Most of the systems we have are reactive,” Dr. Kakraba said. “The disease occurs, and then we respond. SMART-pred allows us to study patterns and predict outcomes ahead of time so we can intervene earlier.” 

Originally developed to detect early signs of Alzheimer’s disease through handwriting analysis, the platform demonstrated up to 91% accuracy, outperforming many existing diagnostic tools. That success led Dr. Kakraba and his team to expand the technology into a broader, disease-agnostic system for population health. The team published their findings in JMIR Aging, the top-ranked journal in Gerontology worldwide, with Q1 rankings in Geriatrics and Gerontology, Medical Informatics, and Health Informatics. 

“This is something we can definitely adapt to a broader audience and a broader community,” Dr. Kakraba said. 

Currently, the platform uses 10 machine learning algorithms to evaluate data simultaneously. Dr. Kakraba intends to expand the platform to use more than 20 algorithms, so SMART-pred can identify the most effective model for a given problem while also highlighting the key factors driving its predictions. This approach is designed to help public health professionals better understand and trust the results. 

SMART-pred has the potential to be applied across a wide range of health challenges. In maternal health, it could help identify patients at higher risk for complications. In cancer surveillance, it could detect unusual increases in incidence across specific communities. For infectious diseases, it could help forecast outbreaks and guide early intervention. 

By identifying subtle shifts in data, the platform may give public health agencies a critical head start. 

 SMART-pred can detect “subtle patterns in data before they even become an obvious pattern,” Dr. Kakraba said, noting that machine learning can recognize early signals that might otherwise go unnoticed. 

Advancing health equity is a central goal of the project. SMART-pred is designed to track outcomes across different populations and highlight disparities in real time, helping decision-makers allocate resources more effectively.  

The platform is also built with accessibility in mind. Its user-friendly interface allows public health practitioners without specialized technical training to use advanced analytics tools in their work. 

“It should be something that everybody can access and use,” Dr. Kakraba said. 

 The project brings together expertise from across disciplines, including public health, data science and medicine, and includes collaboration with the Louisiana Department of Health. Through the seed grant, CAIDS is also supporting the effort with computing infrastructure and student engagement opportunities. 

 During the current phase, the team is expanding the platform’s capabilities, validating it across multiple disease areas and working toward HIPAA compliance to support real-world implementation. 

 If successful, SMART-pred could have a lasting impact on public health systems in Louisiana and beyond by offering a scalable, cost-effective tool for earlier detection, better decision-making and more equitable health outcomes. 

 “SMART-pred represents a new model for public health… one that is AI-driven, explainable, affordable, and accessible to everyone,” Dr. Kakraba said. “I’m so thankful to CAIDS and the Weatherhead School for supporting our work with a seed grant, so we can bring SMART-pred into the real world.”