Establish of an Initial Platinum-Resistance Predictor in High-Grade Serous Ovarian Cancer Patients Regardless of Homologous Recombination Deficiency Status

Oncogenic Pathways and Targeted Therapies in Ovarian Cancer

Epithelial ovarian cancer (EOC) is one of the most aggressive forms of gynaecological malignancies. Survival rates for women diagnosed with OC remain poor as most patients are diagnosed with advanced disease. Debulking surgery and platinum-based therapies are the current mainstay for OC treatment. However, and despite achieving initial remission, a significant portion of patients will relapse because of innate and acquired resistance, at which point the disease is considered incurable. In view of this, novel detection strategies and therapeutic approaches are needed to improve outcomes and survival of OC patients. In this review, we summarize our current knowledge of the genetic landscape and molecular pathways underpinning OC and its many subtypes. By examining therapeutic strategies explored in preclinical and clinical settings, we highlight the importance of decoding how single and convergent genetic alterations co-exist and drive OC progression and resistance to current treatments. We also propose that core signalling pathways such as the PI3K and MAPK pathways play critical roles in the origin of diverse OC subtypes and can become new targets in combination with known DNA damage repair pathways for the development of tailored and more effective anti-cancer treatments.

Predictive Value of Machine Learning for Platinum Chemotherapy Responses in Ovarian Cancer: Systematic Review and Meta-Analysis

BACKGROUND

Machine learning is a potentially effective method for predicting the response to platinum-based treatment for ovarian cancer. However, the predictive performance of various machine learning methods and variables is still a matter of controversy and debate.

OBJECTIVE

This study aims to systematically review relevant literature on the predictive value of machine learning for platinum-based chemotherapy responses in patients with ovarian cancer.

METHODS

Following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, we systematically searched the PubMed, Embase, Web of Science, and Cochrane databases for relevant studies on predictive models for platinum-based therapies for the treatment of ovarian cancer published before April 26, 2023. The Prediction Model Risk of Bias Assessment tool was used to evaluate the risk of bias in the included articles. Concordance index (C-index), sensitivity, and specificity were used to evaluate the performance of the prediction models to investigate the predictive value of machine learning for platinum chemotherapy responses in patients with ovarian cancer.

RESULTS

A total of 1749 articles were examined, and 19 of them involving 39 models were eligible for this study. The most commonly used modeling methods were logistic regression (16/39, 41%), Extreme Gradient Boosting (4/39, 10%), and support vector machine (4/39, 10%). The training cohort reported C-index in 39 predictive models, with a pooled value of 0.806; the validation cohort reported C-index in 12 predictive models, with a pooled value of 0.831. Support vector machine performed well in both the training and validation cohorts, with a C-index of 0.942 and 0.879, respectively. The pooled sensitivity was 0.890, and the pooled specificity was 0.790 in the training cohort.

CONCLUSIONS

Machine learning can effectively predict how patients with ovarian cancer respond to platinum-based chemotherapy and may provide a reference for the development or updating of subsequent scoring systems.

Diagnostics and treatment of ovarian cancer in the era of precision medicine - opportunities and challenges

Due to predictions of increasing incidences and deaths from ovarian cancer, this neoplasm is a challenge for modern health care. The advent of NGS technology has made it possible to understand the molecular characteristics of many cancers, including ovarian cancer. The data obtained in research became the basis for the development of molecularly targeted therapies thus leading to the entry of NGS analysis into the diagnostic process of oncological patients. This review presents targeted therapies currently in preclinical or clinical trials, whose promising results offer hope for their use in clinical practice in the future. As more therapeutic options emerge, it will be necessary to modify molecular diagnostic regimens to select the best treatment for a given patient. New biomarkers are needed to predict the success of planned therapy. An important aspect of public health is molecular testing in women with a familial predisposition to ovarian cancer enabling patients to be included in prevention programs. NGS technology, despite its high throughput, poses many challenges, from the quality of the diagnostic material used for testing to the interpretation of results and classification of sequence variants. The article highlights the role of molecular testing in ongoing research and also its role in the diagnostic and therapeutic process in the era of personalized medicine. The spread of genetic testing in high-risk groups, the introduction of more targeted therapies and also the possibility of agnostic therapies could significantly improve the health situation for many women worldwide.