Pre- and postdiagnosis physical activity, television viewing, and mortality among patients with colorectal cancer in the National Institutes of Health-AARP Diet and Health Study

Abstract

Purpose: Physical inactivity has been associated with higher mortality risk among survivors of colorectal cancer (CRC), but the independent effects of pre- versus postdiagnosis activity are unclear, and the association between watching television (TV) and mortality in survivors of CRC is previously undefined.

Methods: We analyzed the associations between prediagnosis (n = 3,797) and postdiagnosis (n = 1,759) leisure time physical activity (LTPA) and TV watching and overall and disease-specific mortality among patients with CRC. We used Cox proportional hazards regression to estimate hazard ratios (HRs) and 95% CIs, adjusting for known mortality risk factors.

Results: Comparing survivors of CRC reporting more than 7 hours per week (h/wk) of prediagnosis LTPA with those reporting no LTPA, we found a 20% lower risk of all-cause mortality (HR, 0.80; 95% CI, 0.68 to 0.95; P for trend = .021). Postdiagnosis LTPA of ≥ 7 h/wk, compared with none, was associated with a 31% lower all-cause mortality risk (HR, 0.69; 95% CI, 0.49 to 0.98; P for trend = .006), independent of prediagnosis activity. Compared with 0 to 2 TV hours per day (h/d) before diagnosis, those reporting ≥ 5 h/d of TV before diagnosis had a 22% increased all-cause mortality risk (HR, 1.22; 95% CI, 1.06 to 1.41; P trend = .002), and more postdiagnosis TV watching was associated with a nonsignificant 25% increase in all-cause mortality risk (HR, 1.25; 95% CI, 0.93 to 1.67; P for trend = .126).

Conclusion: LTPA was inversely associated with all-cause mortality, whereas more TV watching was associated with increased mortality risk. For both LTPA and TV watching, postdiagnosis measures independently explained the association with mortality. Clinicians should promote both minimizing TV time and increasing physical activity for longevity among survivors of CRC, regardless of previous behaviors.

Fig 1.

Timeline of data collection and analytic follow-up. Dashed line indicates lag time, whereas solid line indicates the follow-up time calculated in models. Thus, for prediagnosis analyses, follow-up started at age at colorectal cancer (CRC) diagnosis and ended at age at death or end of follow-up at December 31, 2011, whichever occurred first. In postdiagnosis models, follow-up time started at age at postdiagnosis questionnaire and ended at age at death or censoring. CVD, cardiovascular disease.

Fig 2.

Joint effects of (A) prediagnosis and (B) postdiagnosis leisure time physical activity (LTPA) and television (TV) viewing and mortality among individuals diagnosed with colorectal cancer. Low LTPA was categorized as < 1 h/wk of moderate- to vigorous-intensity physical activity, and high LTPA was categorized as ≥ 1 h/wk. Low TV was categorized as 0 to 2 h/d of TV watching, and high TV was categorized as ≥ 3 h/d. Models used age as the underlying time metric and adjusted for sex (male, female), cancer site (colon, rectum), tumor grade, tumor stage (local, regional), surgery (yes, no), radiation (yes, no), chemotherapy (yes, no), body mass index (continuous), self-reported health (excellent/very good, good, fair, poor), and smoking status (never, former, current).

Fig 3.

(A) All-cause mortality hazard ratios per 2.5-hour increase per week in postdiagnosis leisure time physical activity (LTPA). (B) All-cause mortality hazard ratios per 3.5-hour increase in postdiagnosis television (TV) viewing. Models were stratified by median value or category. Models were adjusted for sex (male, female), tumor site (colon, rectum), tumor grade, tumor stage (local, regional, unknown), surgery (yes, no), radiation (yes, no), chemotherapy (yes, no), body mass index (continuous), time reported watching TV (for panel A; 0 to 2, > 2 to 4, > 4 h/d) or time reported in physical activity (for panel B; 0, < 1, 1 to < 4, 4 to < 7, ≥ 7 h/wk), self-reported health (excellent/very good, good, fair, poor), and smoking status (never, former, current). Lag time was defined as the time from cancer diagnosis to follow-up questionnaire. LTPA and TV were treated as continuous and scaled by the median (2.5 h/wk and 3.5 h/d, respectively). BMI, body mass index; dx, diagnosis.