Would Artificial Intelligence Methods Improve Early Diagnosis and Progress of Ovarian Cancer?

Ovarian cancer is one of the most common cancers in women, characterized by advanced-stage diagnosis, poor prognosis, and high mortality rate. The predominant screening methods rely on ultrasound images and carbohydrate antigen 125, which has limitations such as a lack of specificity. More insight is needed to understand the etiology of ovarian cancer. Machine learning offers a solution to some of these issues and can be applied in diagnosing and prognosing ovarian cancer. This review article collects information on how machine learning models can be trained on a variety of data types, such as biomarkers, clinical factors, and medical imaging, and how these models can be used to classify benign and malignant tumors, predict survival rates, and determine response to drugs and treatment. Overall, we found that machine learning methods have shown great potential in applications in ovarian cancer, but more research needs to be conducted to further advance machine learning technologies in clinical practices.