Could ovarian cancer prediction models improve the triage of symptomatic women in primary care? A modelling study using routinely collected data

CA125 is widely used as an initial investigation in women presenting with symptoms of possible ovarian cancer. We sought to develop CA125-based diagnostic prediction models, and to explore potential implications of implementing model-based thresholds for further investigation in pri-mary care. This retrospective cohort study used routinely collected primary care and cancer regis-try data from symptomatic, CA125-tested women in England (2011-2014). 29,962 women were in-cluded, of whom 279 were diagnosed with ovarian cancer. Logistic regression was used to devel-op two models to estimate ovarian cancer probability: Model 1 consisted of age and CA125 level; Model 2 incorporated further risk factors. Model discrimination (AUC) was evaluated using 10-fold cross-validation. The sensitivity and specificity of various model risk thresholds (≥1% - ≥3%) were compared with that of the current CA125 cut-off (≥35U/ml). Model 1 exhibited excellent dis-crimination (AUC:0.94) on cross-validation. The inclusion of additional variables (Model 2) did not improve performance. At a risk threshold of ≥1% Model 1 exhibited greater sensitivity (86.4% vs 78.5%) but lower specificity (89.1% vs 94.5%) than CA125 (≥35U/ml). Applying the ≥1% model threshold to the cohort, in place of the current CA125 cut-off, 1 in every 74 additional women identified had ovarian cancer. Following external validation, Model 1 could be used as part of a ‘risk-based triage’ system, in which women at high risk of undiagnosed ovarian cancer are select-ed for urgent specialist investigation while women at ‘low risk but not no risk’ are offered non-urgent investigation or interval CA125 re-testing. Such an approach has the potential to expedite ovarian cancer diagnosis, but further research is needed to evaluate the clinical impact and health-economic implications