Clinical Bioinformatics and Machine-Learning Models for Diagnosis, Prognosis and Prediction of Ovarian Cancer Comorbidities

Abstract

The advent of high throughput technologies such as next generation sequencing has produced vast datasets and fundamentally changed the landscape of clinical bioinformatics and translational medicine. With these huge, wide spread “omics” and clinical data available, it is becoming more and more practical to help doctors in clinical diagnostics and comorbidity prediction by providing appropriate tools and methods that could be applicable in personalized medicine for cancer patients. Building reliable models for the prediction of cancer using clinical and “omics” datasets is still a key challenge in genomic and clinical research. We have developed machine-learning models for integrating molecular and clinical information in order to improve ovarian cancer diagnosis, prognosis and prediction of the comorbidities. We have also developed network-centric data-mining approaches for the integration of multiple-omics datasets with clinical information, and novel and effective clinical software tools and comorbidity maps for the personalized and prospective medicine for the ovarian cancer patients.