COMPARISON OF AN AGGRESSIVE (UNITED-STATES) AND A LESS AGGRESSIVE (CANADIAN) POLICY FOR CHOLESTEROL SCREENING AND TREATMENT

Objective: To determine the point at which adverse quality-of-life effects engendered by an aggressive cholesterol-lowering strategy dictate the use of a less aggressive approach. Design: Decision analysis was used to compare the effects of the National Cholesterol Education Program (NCEP) guidelines, an aggressive program, with those of the Canadian Task Force on the Periodic Health Examination (CTF) guidelines, a more conservative program. Quality-adjusted life expectancy was calculated for a theoretical cohort of middle-aged men treated according to each program using Markov cohort analysis. Measurements: Guidelines were applied to the population of the Lipid Research Clinics Coronary Primary Prevention Trial (LRC-CPPT), under the assumption that cholesterol levels had the distribution of the age- and sex-matched general population. Outcomes were calculated using a three-state (health, coronary heart disease, and death) Markov model. State transition probabilities were calculated using bivariate (age and cholesterol) proportional hazards and logistic regression functions. Main Results: The result was a "toss-up"; the number of expected quality-adjusted life years was similar for both programs at all time intervals, although the conservative program was consistently slightly favored. The result was very sensitive to the disutility of dietary therapy (threshold value, 0.0014 compared with the baseline estimate of 0.02) but was also affected by the time frame of the analysis and the rate at which adverse effects of treatment decline. Conclusions: Even small disutilities associated with treatment may outweigh the benefits of aggressive cholesterol-lowering strategies. Research should be directed toward measuring these disutilities and finding ways to reduce their size. Incorporation of the disutility of treatment into policy formulation may result in less interventionist and less costly policies.