Association of Quality and Technology With Patient Mobility for Colorectal Cancer Surgery

IMPORTANCE Many health care systems publish hospital-level quality measures as a driver of hospital performance and to support patient choice, but it is not known if patients with cancer respond to them. OBJECTIVE To investigate hospital quality and patient factors associated with treatment location. DESIGN, SETTING, AND PARTICIPANTS This choice modeling study used national administrative hospital data. Patients with colon and rectal cancer treated in all 163 English National Health Service (NHS) hospitals delivering colorectal cancer surgery between April 2016 and March 2019 were included. The extent to which patients chose to bypass their nearest surgery center was investigated, and conditional logistic regression was used to estimate the association of additional travel time, hospital quality measures, and patient characteristics with treatment location. EXPOSURES Additional travel time in minutes, hospital characteristics, and patient characteristics: age, sex, cancer T stage, socioeconomic status, comorbidity, and rural or urban residence. MAIN OUTCOMES AND MEASURES Treatment location. RESULTS Overall, 44 299 patients were included in the final cohort (mean [SD] age, 68.9 [11.6] years; 18 829 [42.5%] female). A total of 8550 of 31258 patients with colon cancer (27.4%) and 3933 of 13 041 patients with rectal cancer (30.2%) bypassed their nearest surgical center. Travel time was strongly associated with treatment location. The association was less strong for younger, more affluent patients and those from rural areas. For rectal cancer, patients were more likely to travel to a hospital designated as a specialist colorectal cancer surgery center (odds ratio, 1.45; 95% CI, 1.13-1.87; P = .004) and to a hospital performing robotic surgery for rectal cancer (odds ratio, 1.43; 95% CI, 1.11-1.86; P = .007). Patients were less likely to travel to hospitals deemed to have inadequate care by the national quality regulator (odds ratio, 0.70; 95% CI, 0.50-0.97; P = .03). Patients were not more likely to travel to hospitals with better 2-year bowel cancer mortality outcomes. CONCLUSIONS AND RELEVANCE Patients appear responsive to hospital characteristics that reflect overall hospital quality and the availability of robotic surgery but not to specific disease-related outcome measures. Policies allowing patients to choose where they have colorectal cancer surgery may not result in better outcomes but could drive inequities in the health care system.