A novel artificial intelligence (AI) model may prove to be effective at predicting which patients with breast cancer are likely to develop chronic pain, according to a recent study published by Park et al in the Journal of Nursing Scholarship. The findings may help physicians to better understand the underlying conditions that contribute to making pain chronic and ultimately may lead to more effective treatments.
Background
About 33% of patients with cancer may experience chronic pain—a debilitating condition that can dramatically reduce their quality of life, even if their cancer goes into remission. Although physicians have some tools to address chronic pain, determining which patients are most at risk is often challenging.
“We want to understand the factors that lead [patients] from having cancer to having chronic pain and how [we] can better manage these factors,” emphasized senior study author Lisiane Pruinelli, PhD, MS, RN, FAMIA, Professor of Family, Community, and Health Systems Science at the University of Florida College of Nursing. “Our goal is to link this information to some profile of patients, so we can identify early on [which] patients are at risk for developing chronic pain,” she added.
Study Methods and Results
In this study, researchers focused on detailed data of more than 1,000 patients with breast cancer and found the AI model could accurately predict which patients would develop chronic pain more than 80% of the time. The leading factors associated with chronic pain included anxiety, depression, previous cancer diagnoses, and certain infections.
The research was based on the large amount of data made available by the All of Us Research Program, a nationwide research campaign from the National Institutes of Health. This program collects anonymized health-care records from 1 million U.S. patients.
Conclusions
The researchers indicated that the rise of AI may have the potential to help physicians tailor their treatments to a patient’s unique disease characteristics. Implementing the AI model in clinical settings would require integrating it into the electronic health-care records systems that are currently ubiquitous in clinics, which would require additional research.
“Now, with the amount of data we have, and with the use of [AI], we can actually personalize treatments based on patient needs and how they would respond to that treatment,” underscored Dr. Pruinelli. “This wouldn’t be possible if we didn’t have people contributing their data,” she concluded.
Disclosure: For full disclosures of the study authors, visit sigmapubs.onlinelibrary.wiley.com.
