Objectives In cross-sectional studies of time-to-event data collected by patient examinations at a single random point in time, a fraction of them will not experience the event regardless of the length of the follow-up time. This is the case in clinical immunology studies that include a mixed population, with both immune-reactive and immune-tolerant (or non-susceptible) patients. In these cases, classical tests of current status data may perform poorly. New methods for testing these data are needed. Methods In the two-sample comparison setting, we propose a score test for testing the null hypothesis that survival does not differ in either the non-susceptible fraction or the time-to-event distribution among the susceptible fraction. Results In a wide range of scenarios, simulation results show interesting improvements in power for the proposed score test compared to the logrank-type test in most of the configurations we investigated. In a cross-sectional study of drug immunogenicity among treated multiple sclerosis patients, the proposed score test reveals that gender is associated with the immunogenicity of interferon.