Regresar

Exploratory Data Analysis on Cervical Cancer Diseases

Abstract:

Cervical cancer is a major public health problem that mainly affects women with active sexual life. Exploratory Data Analysis is an essential technique to identify outliers, check assumptions, discover patterns, and determine associations between a set of variables. This technique plays an important role in the health area to assist researchers to find insights in the data and relevant aspects about diseases. In this paper, risk factors that cause cervical cancer disease are studied using data analysis tools for identifying relationships and hidden patterns in the data. The analysis is carried out using data related to women with human papillomavirus that is a risk factor for cervical cancer. The data were extracted from an electronic health record system. The dataset contains 143 records with 19 variables related to demographic information, cervical cancer risk factors, and cervical cancer cytology results of patients. To analyze the variables involved in the dataset, data analysis, and visualization tools are used.