Column

A dashboard for PH W251B students

Data source: risk_factors_cervical_cancer.csv

https://archive.ics.uci.edu/dataset/383/cervical+cancer+risk+factors

Background: This data was collected at the Hospital Universitario de Caracas in Carcas, Venezuela. The dataset contains risk factors from medical records, demographic information, and habits for 858 patients. Both patients who were and were not diagnosed with cervical cancer were included in this study sample. The data in this dashboard was donated to the UC Irvine Machine Learning Repository on March 2, 2017.

Research question: What do we know about risk factors associated with developing cervical cancer?

Significance: Understanding the risk factors for cervical cancer can be important for preventative public health interventions and medical research on identified risk factors.

Results: The underlying age distribution in this dataset is skewed to the right, meaning that the data has a larger representation of younger people. The largest age groups of cervical cancer cases are 26-33 and 34-42, respectively. Among these two age groups, patients were more likely to use hormonal contraceptives than the other age groups. However, there does not seem to be an overrepresentation of patients who use hormonal contraceptives for longer periods of time. Lastly, smoking did not seem to be a significant risk factor among patients who were diagnosed with cervical cancer as only two cases of cervical cancer were associated with smoking. Based on these results, we may want to prioritize exploring the associations between age as a risk factor for cervical cancer and expand the study sample to have a symmetric age distribution.

Column