The diagnostic performance of CA125 for the detection of ovarian and non-ovarian cancer in primary care: A population-based cohort study

Abstract

Background: The serum biomarker cancer antigen 125 (CA125) is widely used as an investigation for possible ovarian cancer in symptomatic women presenting to primary care. However, its diagnostic performance in this setting is unknown. We evaluated the performance of CA125 in primary care for the detection of ovarian and non-ovarian cancers.

Methods and findings: We studied women in the United Kingdom Clinical Practice Research Datalink with a CA125 test performed between 1 May 2011-31 December 2014. Ovarian and non-ovarian cancers diagnosed in the year following CA125 testing were identified from the cancer registry. Women were categorized by age: <50 years and ≥50 years. Conventional measures of test diagnostic accuracy, including sensitivity, specificity, and positive predictive value, were calculated for the standard CA125 cut-off (≥35 U/ml). The probability of a woman having cancer at each CA125 level between 1-1,000 U/ml was estimated using logistic regression. Cancer probability was also estimated on the basis of CA125 level and age in years using logistic regression. We identified CA125 levels equating to a 3% estimated cancer probability: the "risk threshold" at which the UK National Institute for Health and Care Excellence advocates urgent specialist cancer investigation. A total of 50,780 women underwent CA125 testing; 456 (0.9%) were diagnosed with ovarian cancer and 1,321 (2.6%) with non-ovarian cancer. Of women with a CA125 level ≥35 U/ml, 3.4% aged <50 years and 15.2% aged ≥50 years had ovarian cancer. Of women with a CA125 level ≥35 U/ml who were aged ≥50 years and who did not have ovarian cancer, 20.4% were diagnosed with a non-ovarian cancer. A CA125 value of 53 U/ml equated to a 3% probability of ovarian cancer overall. This varied by age, with a value of 104 U/ml in 40-year-old women and 32 U/ml in 70-year-old women equating to a 3% probability. The main limitations of our study were that we were unable to determine why CA125 tests were performed and that our findings are based solely on UK primary care data, so caution is need in extrapolating them to other healthcare settings.

Conclusions: CA125 is a useful test for ovarian cancer detection in primary care, particularly in women ≥50 years old. Clinicians should also consider non-ovarian cancers in women with high CA125 levels, especially if ovarian cancer has been excluded, in order to prevent diagnostic delay. Our results enable clinicians and patients to determine the estimated probability of ovarian cancer and all cancers at any CA125 level and age, which can be used to guide individual decisions on the need for further investigation or referral.

Fig 1. Flow diagram illustrating the identification of the study cohort and application of exclusion criteria.

UTS is a quality metric, provided by CPRD, which indicates if the data from a GP practice are of sufficient quality to be used in research [14]. CA125, cancer antigen 125; CPRD, Clinical Practice Research Datalink; NCRAS, National Cancer Registration and Analysis Service; UTS, up to standard.

Fig 2. Relationship between CA125 level and estimated probability of ovarian cancer, invasive ovarian cancer, and all cancers.

Estimated probabilities up to 8% are shown for ovarian cancer, invasive ovarian cancer, and all cancers. CA125 levels that correspond to the closest integer probabilities of 3% are indicated. The probabilities, which equate to a CA125 level of 35 U/ml, are also marked. Confidence intervals (95%) are displayed. Graphs showing probabilities at an extended range of CA125 values (up to 500 U/ml) for ovarian cancer, invasive ovarian cancer, and all cancer are included in S1 Fig, S2 Fig, and S3 Fig, respectively. Data used to construct these graphs (up to a CA125 level of 1,000 U/ml) are available via the University of Cambridge Repository [27]. CA125, cancer antigen 125; CI, confidence interval.

Fig 3. Relationship between CA125 level and estimated probability of ovarian cancer for women of different ages.

Estimated ovarian cancer probabilities are shown in relation to CA125 level for women of 30, 40, 50, 60, 70, and 80 years of age. CA125 levels that correspond to the closest integer probabilities of 3% are indicated in red. Confidence intervals (95%) are displayed. Data used to construct these graphs (up to a CA125 level of 1,000 U/ml) are available via the University of Cambridge Repository [27]. CA125, cancer antigen 125.