On the utility of the lognormal model for analysis of breast cancer survival in Sweden 1961-1973

Abstract

Parametric models have been suggested as an alternative to conventional life table techniques for interpretation of observed survival patterns in cancer. This paper extends earlier work on breast cancer by studying the fit of Boag's lognormal model to the survival of 8,170 breast cancer cases reported to the Swedish Cancer Registry during 1961-1963. The model was also used to analyse the upward survival trend for breast cancer cases in Sweden during 1961-1973. The model fitted the 1961-1963 data well for the entire case material and for patients aged less than 70 years. It was therefore used to help explain whether the upward survival trend was due to long term cures or merely to protracted survival with cancer. The estimated cured proportion among patients aged less than 70 years rose from 33% +/- 2% (s.e.) during 1961-1963 to 40% +/- 3% for cases 1971-1973 (P less than 0.05). The median survival of uncured cases, was found to be similar during both periods, 4.5 and 4.6 years respectively. The model did not fit data for patients aged greater than 70 years. It is possibly too simplistic, and perhaps does not accurately describe the forces of mortality or their interactions in old patients. Another disadvantage is that large case materials are necessary in order to obtain estimates with reasonably small standard errors.