Evolving Information Needs among Colon, Breast, and Prostate Cancer Survivors: Results from a Longitudinal Mixed-Effects Analysis

Abstract

Background: This study describes how cancer survivors' information needs about recurrence, late effects, and family risks of cancer evolve over the course of their survivorship period.

Methods: Three annual surveys were conducted from 2006 to 2008 in a cohort of Pennsylvania cancer survivors diagnosed with colon, breast, or prostate cancer in 2005 (round 1, N = 2,013; round 2, N = 1,293; round 3, N = 1,128). Outcomes were information seeking about five survivorship topics. Key predictors were survey round, cancer diagnosis, and the interaction between these variables. Mixed-effects logistic regression analyses were performed to predict information seeking about each topic, adjusting for demographic variables, clinical characteristics, and clustering of repeated observations within individuals.

Results: Information seeking about reducing risks of cancer recurrence was the most frequently reported topic across survivors and over time. Breast cancer survivors were more likely to seek about survivorship topics at round 1 compared with other survivors. In general, information seeking declined over time, but cancer-specific patterns emerged: the decline was sharpest for breast cancer survivors, whereas in later years female colon cancer survivors actually sought more information (about how to reduce the risk of family members getting colon cancer or a different cancer).

Conclusion: Cancer survivors' information needs varied over time depending on the topic, and these trends differed by cancer type.

Impact: Clinicians may need to intervene at distinct points during the survivorship period with information to address concerns about cancer recurrence, late effects, and family members' risks.

Figure 1

Predicted proportions of survivors who looked for information about cancer survivorship issues by survey round and cancer diagnosis Notes. Predicted proportions of the fixed portion of the mixed effects model, adjusted for covariates and clustering within individuals. Error bars indicate 95% confidence intervals. Rounds 1, 2, and 3 were conducted between 9–21 months, 21–33, and 33–45 months after initial diagnosis respectively.