Predicting Primary Ovarian Insufficiency in Childhood Cancer Survivors

Get Permission

As reported in The Lancet Oncology, Im et al have developed risk-prediction models for primary ovarian insufficiency in long-term survivors of childhood cancer.

Study Details

In the study, models to predict age-specific risk of primary ovarian insufficiency were evaluated among 5-year survivors from the Childhood Cancer Survivor Study (CCSS). Prospective models used algorithms based on statistical or machine learning to consider all predictors, including cancer treatments. External validation of the models was performed among 5-year survivors in the St. Jude Lifetime (SJLIFE) cohort.

Key Findings

A total of 7,891 CCSS cohort survivors, including 922 with primary ovarian insufficiency, were included in the development of the risk-prediction model; 1,349 SJLIFE cohort survivors, including 101 with primary ovarian insufficiency, were included in the validation study.

Median follow-up from cancer diagnosis was 23.7 years (interquartile range [IQR] = 18.3–30.0 years) in the CCSS cohort and 15.1 years (IQR =10.4–22.9 years) in the SJLIFE cohort. Between the ages of 21 and 40 years, primary ovarian insufficiency prevalence increased from 7.9% (95% confidence interval [CI] = 7.3%–8.5%) to 18.6% (95% CI = 17.3%–20.0%) in the CCSS cohort and from 7.3% (95% CI = 5.8%–8.9%) to 14.9% (95% CI = 11.6%–19.1%) in the SJLIFE cohort.

Age-specific logistic regression models including ovarian radiation dosimetry or prescribed pelvic and abdominal radiation dose (receiver operating characteristic area under the curve [AUC] values = 0.76–0.78) and individual chemotherapy predictors performed well in the CCSS cohort for predicting primary ovarian insufficiency. In the SJLIFE validation cohort, good performance was observed with the prescribed radiation dose model (AUC = 0.88–0.95) and with a simpler model that included any exposures to pelvic or abdominal radiotherapy or alkylators (AUC = 0.82–0.90).

Evaluation of a SJLIFE-based polygenic risk score for primary ovarian insufficiency among 1,985 CCSS cohort survivors with available genotype data showed that the addition of the polygenic risk score improved average positive predictive value from 0.76 (95% CI = 0.63–0.89)  to 0.87 (95% CI = 0.80–0.94; P = .029) among CCSS cohort survivors treated with ovarian radiation and chemotherapy.

The risk calculator is available at

The investigators concluded, “Primary ovarian insufficiency risk-prediction models using treatment information showed robust prediction performance in adult survivors of childhood cancer.”

Yan Yuan, PhD, of the School of Public Health, University of Alberta, Edmonton, is the corresponding author for The Lancet Oncology article.

Disclosure: The study was funded by the Canadian Institutes of Health Research and U.S. National Cancer Institute. For full disclosures of the study authors, visit

The content in this post has not been reviewed by the American Society of Clinical Oncology, Inc. (ASCO®) and does not necessarily reflect the ideas and opinions of ASCO®.