Determinants of pain severity changes in ambulatory patients with cancer: an analysis from Eastern Cooperative Oncology Group trial E2Z02

Abstract

Purpose: To understand changes in pain severity over time and to explore the factors associated with pain changes in ambulatory patients with solid tumors.

Patients and methods: We enrolled 3,106 patients with invasive cancer of the breast, prostate, colon/rectum, or lung from multiple sites. At baseline and 4 to 5 weeks later, patients rated their pain level on a 0 to 10 numerical rating scale. A 2-point change in pain score was defined as a clinically significant change in pain. Multivariable logistic models were fitted to examine the effects of pain management and demographic and clinical factors on change in pain severity.

Results: We analyzed 2,761 patients for changes in pain severity. At initial assessment, 53.0% had no pain, 23.5% had mild pain, 10.3% had moderate pain, and 13.2% had severe pain. Overall, one third of patients with initial pain had pain reduction within 1 month of follow-up, and one fifth had an increase, and the improvement and worsening of pain varied by baseline pain score. Of the patients without pain at initial assessment, 28.4% had pain (8.9% moderate to severe) at the follow-up assessment. Logistic regression analysis showed that inadequate pain management was significantly associated with pain deterioration, as were lower baseline pain level, younger age, and poor health status.

Conclusion: One third of patients have pain improvement and one fifth experience pain deterioration within 1 month after initial assessment. Inadequate pain management, baseline pain severity, and certain patient demographic and disease characteristics are associated with pain deterioration.

Trial registration: ClinicalTrials.gov NCT00303914.

Fig 1.

CONSORT diagram. Mild pain, pain scores of 1 to 3; moderate pain, pain scores of 4 to 5; and severe pain, pain scores of 6 to 10. A total of 2,761 patients reported pain score at both initial and follow-up assessments.

Fig 2.

Change in pain severity by change in pain management between two visits in patients with pain at initial assessment (group 1, n = 1,298). A-A: adequately treated in both visits; A-U: adequately treated at initial, undertreated at follow-up; U-A: undertreated at initial, adequately treated at follow-up; U-U: undertreated in both visits; M: missing pain treatment data in at least one visit. P < .001 for Fisher's exact test to assess the significance of the overall association between pain management change (A-A, A-U, U-A and U-U) and pain severity change; P < .001 for χ² tests to compare the proportion of pain relief between patients with pain management of U-A and other patients (63.6% v 22.5%), and to compare the proportion of pain worsening between patients with pain management of A-U and other patients (67.4% v 15.7%).

Fig 3.

Change in pain management by pain level at follow-up assessment in patient groups 2 and 3. A-A: adequately treated in both visits; A-U: adequately treated at initial, undertreated at follow-up; M: missing pain treatment data in at least one visit.

Fig 4.

Change in pain management by amount bothered by adverse effects related to treatment of pain or other symptoms at initial assessment (n = 2,746). Fifteen patients had missing data for amount bothered by adverse effects. A-A: adequately treated in both visits; A-U: adequately treated at initial, undertreated at follow-up; U-A: undertreated at initial, adequately treated at follow-up; U-U: undertreated in both visits; M: missing pain treatment data in one visit. Those who were not bothered or slightly bothered by adverse effects were more likely to receive adequate treatment at both visits (57.9% v 48.2% for other patients, P < .001, χ² test), whereas those who were extremely bothered by adverse effects were more likely to receive undertreatment at both visits (30.0% v 11.1% for other patients, P < .001, χ² test).

Fig A1.

Change in pain severity by change in pain management between two visits in each patient group defined by pain level at initial assessment. A-A: adequately treated in both visits; A-U: adequately treated at initial, undertreated at follow-up; U-A: undertreated at initial, adequately treated at follow-up; U-U: undertreated in both visits; M: missing pain treatment data in at least one visit. Fisher's exact test was used to assess the overall association between pain management change (A-A, A-U, U-A, and U-U) and pain severity change; P < .001 for each patient group defined by initial pain level. χ² test was used to compare the proportion of pain relief between patients with pain management of U-A and other patients (P < .001 for each patient group defined by baseline pain level) and to compare the proportion of pain worsening between patients with pain management of A-U and other patients (P < .001 for each patient group).