University of Texas Awarded Funding for Disease Relapse Prediction AI

Researchers at the University of Texas at Arlington (UTA) have been awarded a $450,000 grant from the National Institute of General Medical Sciences to develop a machine learning-based model to predict disease relapse.

The tool will review patient data to generate insights into which patients may need additional treatments to manage their conditions.

“With recent advances in screening, diagnosis and treatment, many diseases like cancer or cardiovascular disease can be identified in an early stage,” explained Suvra Pal, PhD, associate professor of statistics in the Department of Mathematics at UTA and lead on the project, in the press release.

“Fortunately, a significant proportion of patients living with these diseases will clinically be cured, meaning they will never experience recurrence, metastasis or death due to their primary disease. Our research aims to better identify which patients will be cured so treatment teams can focus on those who will need additional interventions,” Pal continued.

The model will analyze the time to occurrence of an event—like disease recurrence—and other patient characteristics to make its predictions. By leveraging machine learning, the tool will be equipped to sift through massive amounts of data, which the researchers hope will lead to high predictive accuracy.

The press release indicates that the tool will be deemed successful if its predictive accuracy reaches at least 85 percent.

“There are existing algorithms that attempt to predict who will be cured based on patient-related characteristics,” Pal stated. “Unfortunately, these algorithms come with several drawbacks that make [it hard for them] to meet the increasing needs for advanced applications. Our algorithm, based on advanced modeling strategies, circumvents the drawbacks with existing algorithms, and it will be developed into a software for free and nonprofit use.”

In the long term, the research team aims to develop even more powerful models to help predict which diseases and patients will be cured and improve how resources are allocated to improve care for patients with disease relapse.

The project also lays the foundation for the development of Pal’s proposed Center for Integrative Biostatistical and Experimental Research at UTA.

In addition, the researchers also hope that the project will expand the research horizons of UTA’s underrepresented students.

“This project will help build a unique integration of statistical expertise and biological significance in the research career of undergraduate students,” said Pal. “Our trainees will have a stronger foundation and be better equipped with interdisciplinary and multidisciplinary trainings for cutting-edge academic and industrial careers.”

The project underscores the potential for predictive analytics in healthcare.

Last year, researchers at Massachusetts General Hospital (MGH) successfully developed and validated an AI method to identify early-stage melanoma patients at risk for cancer recurrence.

Identifying these patients is crucial for improving survival rates, the research team indicated, as melanoma-related mortality typically occurs among patients who receive a diagnosis of early-stage melanoma and then experience a recurrence later that remains undetected until the cancer has spread.

To address this, the researchers designed a predictive algorithm that uses multiple key clinical and pathologic features of these melanomas to accurately forecast which patients are at highest risk.