OVARIAN CANCER DETECTION USING MACHINE LEARNING APPROACHES BASED ON CLINICAL DATA

Ovarian cancer is one of the most predominant forms of cancer in women. Currently, there is still no effective medication therapy available to treat this fatal illness. On the other hand, early discovery may lengthen the patients' lives. This work's main objective is to do predictive analytics for early diagnosis by applying machine learning models and statistical techniques to clinical data collected from 549 patient people. In statistical analysis, classification models to separate patients with benign from malignant ovarian cancer are constructed using Student's Gradient Boosting Machine (XG Boost). Furthermore, the predictive analysis results indicate that the machine learning model can distinguish between malignant and benign patients with up to 91% accuracy. Machine learning detection may be crucial to the diagnosis of cancer since early-stage detection is typically not possible.