Photo Credit: ArLawKa AungTun
The following is a summary of “Using a Two-Steps Clustering and PCA Analysis for Stratified Chronic Non-Cancer Pain Care: A Retrospective Cross-Sectional Study,” published in the February 2025 issue of Journal of Pain Research by Peiró et al.
Researchers conducted a retrospective study to identify distinct states of individuals with chronic non-cancer pain (CNCP) using unsupervised cluster analysis to inform clinical recommendations in pain care.
They analyzed data from a real-world ambulatory CNCP cohort (n = 418) who completed a multidimensional patient-reported registry during an initial evaluation at a multidisciplinary academic pain unit. Clustering analysis was conducted based on pain intensity and relief, QoL, number of adverse events, and emergency department visits, and a study was performed (n = 120) following the stratified analysis.
The results showed that principal component analysis identified cut-off points distinguishing 6 clusters and 3 groups with varying pain intervention needs. These individuals had significantly different baseline clinical conditions and monitoring requirements. Those aged over 65 years, retired or on medical leave, and prescribed opioids and anxiolytics experienced a severe decline in daily QoL, with no significant differences based on sex.
Investigators concluded that these real-world data-driven clusters could aid screening, particularly where physical examinations were limited, with further analyses planned to confirm the replicability of this stratified care approach.
