A multilocus genetic risk score for coronary heart disease: case-control and prospective cohort analyses

ROC curves are a popular method for displaying sensitivity and specificity of a continuous diagnostic marker, X, for a binary disease variable, D. However, many disease outcomes are time dependent, D(t), and ROC curves that vary as a function of time may be more appropriate. A common example of a time-dependent variable is vital status, where D(t) = 1 if a patient has died prior to time t and zero otherwise. We propose summarizing the discrimination potential of a marker X, measured at baseline (t = 0), by calculating ROC curves for cumulative disease or death incidence by time t, which we denote as ROC(t). A typical complexity with survival data is that observations may be censored. Two ROC curve estimators are proposed that can accommodate censored data. A simple estimator is based on using the Kaplan-Meier estimator for each possible subset X > c. However, this estimator does not guarantee the necessary condition that sensitivity and specificity are monotone in X. An alternative estimator that does guarantee monotonicity is based on a nearest neighbor estimator for the bivariate distribution function of (X, T), where T represents survival time (Akritas, M. J., 1994, Annals of Statistics 22, 1299-1327). We present an example where ROC(t) is used to compare a standard and a modified flow cytometry measurement for predicting survival after detection of breast cancer and an example where the ROC(t) curve displays the impact of modifying eligibility criteria for sample size and power in HIV prevention trials.

The Malmö Diet and Cancer study is a 10-year prospective case-control study in 45-64-year-old men and women (n = 53,000) living in a city with 230,000 inhabitants. One objective is to clarify whether a western diet is associated with certain forms of cancer whilst taking other life-style factors into account. Another broad question is whether oxidative stress and the activity in DNA-repairing systems influence the impact of diet on the development of all or certain forms of cancer. The study is also to act as a resource available for testing new hypotheses emanating from other studies. Initially food intake, heredity, socio-economic factors, life-style pattern, occupational situation, previous and current diseases, symptoms and medications, will be determined. Viable lymphocytes, granulocytes, erythrocytes, and plasma/serum will be stored in a biological bank together with tumour specimens gathered from cases. The incidence and mortality of all cancer forms will then be followed for 10 years by existing registries. Data from the initial examination in these cases will then be compared with those of control subjects not having developed any form of cancer. A biomarker programme, utilizing the biological bank, has been developed and is aimed at finding predictors and/or precursors of cancer. A high participation rate (> 70%) and a high quality biological bank are prerequisites for a successful project. The experience gathered so far indicates that these goals are feasible.