AUG 05, 2024

AI Predicts Chronic Pain in Cancer Patients with 80% Accuracy

WRITTEN BY: Annie Lennon

An AI model correctly detected which breast cancer patients developed chronic pain more than 80% of the time. The corresponding study was published in the Journal of Nursing Scholarship

Around 35% of people who have breast cancer also have chronic pain, which is characterized by pain lasting more than three months. The condition is especially prevalent in female breast cancer survivors who are more susceptible to pain. Chronic pain has a severe impact on quality of life and challenges cancer treatment. Being able to identify chronic pain early and identify patients most at risk could help doctors address underlying conditions that contribute to making pain chronic and lead to more effective treatments. 

"We want to understand the factors that lead someone from having cancer to having chronic pain and how can we better manage these factors," said senior author of the study, Lisiane Pruinelli, Ph.D., professor of family, community, and health systems science in the University of Florida College of Nursing, in a press release

For the study, the researchers used a deep learning approach to identify breast cancer patients at risk of developing chronic pain. Built with data from 1131 breast cancer patients, the AI model correctly predicted which patients would develop chronic pain over 80% of the time. Leading factors linked to chronic pain included anxiety and depression, previous cancer diagnosis, and certain infections. 

“Our study could enhance early identification and personalized management of chronic pain in breast cancer patients using a deep learning-based prediction model, reducing pain burden and improving outcomes,” wrote the researchers in their paper. 

"Now with the amount of data we have, and with the use of artificial intelligence, we can actually personalize treatments based on patient needs and how they would respond to that treatment.[...] This wouldn't be possible if we didn't have people contributing their data," said Pruinelli.

 

Sources: Science Daily, Journal of Nursing Scholarship