With 80% accuracy, an AI-assisted tool could aid doctors in determining which patients should receive treatment for chronic pain.
Around a third of cancer survivors experience chronic pain—a serious condition that can significantly diminish a person’s quality of life, even when their cancer is in remission.
While physicians have various methods for managing chronic pain, identifying patients who are most susceptible to it is quite challenging. However, a recent study from researchers at the University of Florida and other institutions utilizes artificial intelligence to foresee which breast cancer patients are more likely to experience chronic pain. This predictive model may help physicians tackle the root causes that lead to persistent pain and ultimately improve treatment options.
“We aim to understand the elements that transition someone from having cancer to experiencing chronic pain and how we can effectively manage these factors,” stated Lisiane Pruinelli, Ph.D., M.S., R.N., FAMIA, the lead author of the study and a professor at the UF College of Nursing. “Our objective is to connect this information to specific patient profiles so we can early identify those at risk of developing chronic pain.”
The study’s findings were published on July 26 in the Journal of Nursing Scholarship. Among the authors are Pruinelli, Jung In Park, Ph.D., R.N., FAMIA, from the University of California, Irvine, and Steven Johnson, Ph.D., from the University of Minnesota.
Results indicated that the AI model, developed using extensive data from over 1,000 breast cancer patients, successfully predicted chronic pain development in more than 80% of cases. The primary factors linked to chronic pain included anxiety and depression, previous cancer treatments, and specific infections.
For a model like this to be implemented in medical practices, it would need to be integrated with electronic health record systems widely used in clinics, which requires further research. The researchers noted that AI advancements could enhance how doctors customize treatments according to individual patient characteristics.
“With the vast amount of data available and the utilization of artificial intelligence, we can now personalize treatments based on the unique needs of patients and how they may react to these treatments,” Pruinelli explained.
The study was grounded in the extensive data provided by the All of Us Research Program, a nationwide initiative by the National Institutes of Health aimed at gathering anonymized healthcare records from 1 million Americans.
“The contributions from individuals are crucial for making this possible,” Pruinelli remarked.
