AI holds significant promise in personalising and improving care for patients with ovarian conditions, a new systematic review and meta-analysis has found.
Yet, challenges persist in translating research into routine clinical care.
Promising Applications of AI in Ovarian Care
In the analysis, AI models exhibited high diagnostic accuracy for ovarian cancer through combining, for example, ultrasound scans and blood test results.
Across the 81 studies, AI models correctly identified ovarian cancer in approximately nine out of 10 cases, with a pooled specificity of 89–94%.
They were also highly accurate at ruling out ovarian cancer when it was not present, with a specificity of 85–91%.
Further, explainable AI tools effectively predicted complete surgical cytoreduction in advanced ovarian cancer – the removal of all visible cancer in theatre – with a pooled AUC of 0.87.
More broadly in reproductive medicine, AI algorithms aided physicians in optimising ovarian stimulation protocols and predicted follicular growth, reliably modelling ovarian response in IVF (with a pooled AUC of 0.81).
Translating Research into Routine Clinical Practice
Researchers reported, however, that challenges ultimately lie in realising the full potential of AI in ovarian care because of difficulties translating promising research findings into routine clinical practice.
They noted substantial heterogeneity across studies, reportedly driven by retrospective study designs, analysis of variable AI systems, and a lack of standardised validation of AI models.
Only 22% of analysed studies reported prospective, multicentre external validation.
It follows that researchers called for this rigorous validation to close the gap between research and routine clinical practice, along with standardised methodological and reporting frameworks, smooth integration with clinical workflow, and robust governance to ensure responsible and ethical AI use.
Nonetheless, authors concluded: “Artificial intelligence is a transformative force in the management of ovarian conditions.
“In gynaecologic oncology, AI enhances every phase of care, from early detection and accurate diagnosis to prognostic stratification and surgical planning.
“In reproductive medicine, AI personalises ovarian stimulation and refines the diagnosis of heterogenous endocrine disorders such as PCOS.”
Reference
Yu H, Peng L. Artificial intelligence in ovarian pathophysiology and management: a systematic review and meta-analysis. J Ovarian Res. 2026;DOI:10.1186/s13048-026-02083-0.
Featured image: nerthuz on Adobe Stock
