Acute ovarian failure (AOF) is a condition when ovaries stop functioning before the age of 40. The cause of AOF can vary, but recent studies have suggested an increased risk of ovarian failure within five years of a cancer diagnosis. The objective of this study is to create a risk prediction model to provide optimum guidance to pediatric patients with cancer.
This is a cohort study in which the researchers developed two prediction models of acute ovarian failure risk: Childhood Cancer Survivor Study (CCCS) and St Jude Lifetime Cohort (SJLIFE). The study included 5,886 5-year survivors who were at least 18 years old and had complete treatment exposure. The risk prediction models were developed using logistic regression, support vector machines, and random forest. The primary outcome was a permanent loss of ovarian function within five years of a cancer diagnosis.
Both risk prediction models analyzed participants with acute ovarian failure. Both models used cumulative alkylating drug dose, hematopoietic stem-cell transplantation, and an interaction between age at cancer diagnosis and hematopoietic stem-cell transplantation.
The research concluded that both acute failure risk prediction models performed well and successfully identified the risk of AOF. These models were further utilized for ovarian radiation dosimetry and online risk calculators.