Empirical Analysis with Component Decomposition Methods for Cervical Cancer Risk Assessment

Cervical cancer is one of the most common female diseases. This happens when a woman’s cervix changes. To make matters worse, these cancer cells have the potential to spread to other organs like the liver, bladder, rectum, and even the lungs.Cervical cancer has a high mortality rate, especially in low and middle-income countries, and is the fourth most frequent cancer in women worldwide, according to the World Health Organisation. Medical datasets, including those for diabetes, cervical cancer, and liver illness, are becoming increasingly important as the field of computer science and information technology develops. Cervical cancer risk assessment makes use of a wide variety of classification methods, including but not limited to few ML algorithms. Due to the imbalance and high number of missing values, the dataset underwent a rigorous data pre-processing phase. To further improve classification accuracy, we have proposed component decomposition techniques in our research. Our proposed classifiers, the Support Vector Classifier and the Logistic Regression, have an accuracy of 99.40%.