Cost effectiveness of TAC versus FAC in adjuvant treatment of node-positive breast cancer

Abstract

Background: This economic analysis aimed to determine, from the perspective of a Canadian provincial government payer, the cost-effectiveness of docetaxel (Taxotere: Sanofi-Aventis, Laval, QC) in combination with doxorubicin and cyclophosphamide (TAC) compared with 5-fluorouracil, doxorubicin, and cyclophosphamide (FAC) following primary surgery for breast cancer in women with operable, axillary lymph node-positive breast cancer.

Methods: A Markov model looking at two time phases-5-year treatment and long-term follow-up-was constructed. Clinical events included clinical response (based on disease-free survival and overall survival) and rates of febrile neutropenia, stomatitis, diarrhea, and infections. Health states were "no recurrence," "locoregional recurrence," "distant recurrence," and "death." Costs were based on published sources and are presented in 2006 Canadian dollars. Model inputs included chemotherapy drug acquisition costs, chemotherapy administration costs, relapse and follow-up costs, costs for management of adverse events, and costs for granulocyte colony-stimulating factor (G-CSF) prophylaxis. A 5% discount rate was applied to costs and outcomes alike. Health utilities were obtained from published sources.

Results: For TAC as compared with fac, the incremental cost was $6921 per life-year (LY) gained and $6,848 per quality-adjusted life-year (QALY) gained. The model was robust to changes in input variables (for example, febrile neutropenia rate, utility). When G-CSF and antibiotics were given prophylactically before every cycle, the incremental ratios increased to $13,183 and $13,044 respectively.

Conclusions: Compared with FAC, TAC offered improved response at a higher cost. The cost-effectiveness ratios were low, indicating good economic value in the adjuvant setting of node-positive breast cancer patients.

Keywords: Adjuvant chemotherapy; breast cancer; cost analysis; economic model; prophylaxis.

FIGURE 1

The model as a decision tree. pDeath… = probability of death from the indicated state [No Relapse, Loc (locoregional) Relapse, distant Met (metastatic) Relapse]; pRelapse = probability of relapse from the No Relapse state; pMetRelapse = probability of distant Met relapse from the Loc Relapse state; PercentMetRelapse = proportion of distant Met Relapse.