The ADNEX risk model for ovarian cancer diagnosis: improving performance across different hospitals and examiners

Ovarian cancer is a common cause of cancer mortality. Detection in
an early stage improves survival, as well as treatment by specialized
gynecological oncologists. Yet many tumors are harmless and are
best managed using a conservative wait-and-see approach. This
implies that good diagnostic and screening approaches are needed.
Research on screening has been unsuccessful, making good
diagnostic strategies even more important. In 2014, we introduced
the ADNEX diagnostic model, which estimates the risk of five tumor
types: benign, borderline, stage I invasive, stage II-IV invasive, and
secondary metastasis. Our recent large study in multiple hospitals
indicated that ADNEX had excellent diagnostic ability. ADNEX is
implemented in ultrasound machines and endorsed by national
guidelines and professional societies. However, ADNEX should be
further improved. First, despite excellent overall performance, we
should understand and reduce observed differences between
centers. Second, ADNEX was developed on patients selected for
surgery, and should be adapted to work for all patients with a newly
detected tumor. Third, we need to understand whether ADNEX works
less well when used by clinicians with limited experience. Fourth, we
should compare different statistical algorithms for developing the
model. Finally, ADNEX is the fruitful result of a combination of clinical
and statistical research. Therefore, we need to continue the statistical
research on prediction modeling.