Musculoskeletal pain has been linked with subsequent cancer. The objective was to investigate associations between pain sites and specific cancers, and investigate the hypothesis that musculoskeletal pain is an early marker, rather than cause, of cancer. This was a cohort study in the General Practice Research Database. From a cohort of 46,656 people aged 50 years with a recorded musculoskeletal problem in 1996 but not during the previous 2 years, patients with a new consultation for back, neck, shoulder or hip pain in 1996 were selected and compared with 39,253 persons who had had no musculoskeletal consultation between 1994 and 1996. Outcome was incidence of prostate, breast, lung and colorectal cancer up to 10 years after baseline consultation. Strongest associations with prostate cancer were in the first year of follow-up for males consulting initially with back (adjusted hazard ratio 5.42; 95% CI 3.31, 8.88), hip (6.08; 2.87, 12.85) or neck problems (3.46; 1.58, 7.58). These associations remained for back and neck problems over 10 years. Significant associations existed with breast cancer up to 5 years after consultation in females with hip problems, and with breast and lung cancer in the first year after presentation with back problems. Previously observed links between pain and cancer reflect specific associations between pain sites and certain cancers. One explanation is liability for bony metastases from primary sites, and that pain represents a potential early marker of cancer. However, older patients with uncomplicated musculoskeletal pain seen in clinical practice have a low absolute excess cancer risk.
