Artificial intelligence (AI) and machine learning (ML) in ovarian cancer - transforming detection, treatment, and prevention

Sep 23, 2026

Ovarian cancer remains a highly lethal malignancy, with advanced-stage diagnosis, recurrence, and chemoresistance, limiting clinical outcomes. Traditional biomarkers such as CA-125, BRCA1/2 status, and histopathology provide only a partial view of disease biology, often resulting in suboptimal, empiric treatment. This review highlights how AI/ML can improve diagnosis, risk stratification, therapeutic selection, and prevention by integrating imaging, clinical records, and multi-omics. It also addresses translational challenges and the role of explainable AI in clinical workflows.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages13

Reading Time33 min

AccessFree to download

Abstract

Keywords

Introduction

Clinical limitations of conventional biomarkers

AI/ML for multimodal, personalized oncology insights

Radiomics and enhanced prognostic modeling

Singh et al. Journal of Ovarian Research (2026) 19:91 [https://doi.org/10.1186/s13048-026-01979-1](https://doi.org/10.1186/s13048-026-01979-1) Journal of Ovarian Research REVIEW Open Access Artificial intelligence (AI) and machine learning (ML) in ovarian cancer: transforming detection, treatment, and prevention Mahavir Singh1,3*, Sai N. Betgeri2 and Sham S. Kakar 1,3* Abstract Ovarian cancer remains a highly lethal malignancy, with advanced-stage diagnosis, recurrence, and chemoresistance, thus limiting clinical outcomes. Traditional biomarkers such as CA-125, BRCA1/2 status, and histopathology offer only a partial view of disease biology, often leading to suboptimal and empiric treatment choices. Recent advances in artificial intelligence (AI) and machine learning (ML) provide new opportunities to improve diagnosis, risk stratification, therapeutic selection, and prevention. By integrating multimodal data, including imaging, clinical records, and multi-omics profiles, AI/ML models can uncover complex patterns that enhance the prediction of treatment response, toxicity, recurrence, and survival. Radiomics and radiomicsbased prognostic value (RPV/eRPV) models add further precision by extracting informative imaging phenotypes. Emerging architectures such as graph neural networks (GNNs) and transformer-based models extend these capabilities by modeling interactions among genetic alterations, pathways, and drug responses. Beyond disease management, AI-driven risk prediction and screening tools are gaining exciting relevance in preventive oncology. This review summarizes current and developing AI/ML applications across ovarian cancer care and highlights the translational challenges and opportunities for integrating explainable AI into the clinical workflows. Collectively, these recent innovations support a more personalized, data-integrated approach to reducing morbidity and improving patient outcomes. Keywords Artificial intelligence, Machine learning, Ovarian cancer, Precision oncology, Multi-modal data integration *Correspondence: Mahavir Singh [mahavir.singh@louisville.edu](mahavir.singh@louisville.edu); [gene2medicine@gmail.com](gene2medicine@gmail.com) Sham S. Kakar [sham.kakar@louisville.edu](sham.kakar@louisville.edu) 1Department of Physiology, School of Medicine, University of Louisville, Louisville, KY 40202, USA 2Department of Computer Science and Engineering, University of Louisville, Louisville, KY 40292, USA 3Brown Cancer Center, University of Louisville School of Medicine, Louisville, KY 40202, USA Introduction Cancer remains a leading cause of morbidity and mortality globally, and among gynecologic malignancies, ovarian cancer stands out for its particularly high lethality [1, 2]. By the end of 2025, it is estimated that over 2 million new cancer cases will be diagnosed in the United States, with more than 600,000 deaths [3]. Despite accounting for only approximately 4% of all cancers in women worldwide, ovarian cancer carries disproportionately high mortality, primarily due to late-stage presentation and limited precision in therapy selection [4]. High-grade serous ovarian cancer (HGSOC), the most common histologic subtype, is characterized by extensive molecular © The Author(s) 2026. Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If mat

FAQs

Why do traditional biomarkers often fall short in ovarian cancer care?

They provide only a partial view of disease biology, which can lead to suboptimal, empiric treatment choices and limited ability to capture factors driving outcomes.

How can AI/ML improve diagnosis and treatment selection in ovarian cancer?

By integrating multimodal data such as imaging, clinical records, and multi-omics profiles, AI/ML models can uncover patterns that enhance predictions of treatment response, toxicity, recurrence, and survival.

What role do radiomics-based models (RPV/eRPV) play?

They extract informative imaging phenotypes and add precision by stratifying patients into risk groups and supporting outcome prediction, including overall survival.

Sep 23, 2026

Uploaded by Genevieve