Cervical Cancer Risk Factors from 858 Patients in Caracas, Venezuela

Hospital Universitario de Caracas in Venezuela collected demographic, habit, and medical history data from 858 patients to study cervical cancer risk. The dataset includes attributes such as age, sexual history, pregnancies, smoking, contraceptive use, and STDs, with a binary target variable derived from four diagnostic tests. It was contributed by researchers Kelwin Fernandes, Jaime S. Cardoso, and Jessica Fernandes.

Use Cases

• Binary classification to predict cervical cancer diagnosis based on demographic and behavioral risk factors.
• Feature importance analysis to identify key risk indicators from attributes like number of sexual partners and STDs.
• Studying the impact of hormonal contraceptives and IUD use on cancer risk over time.
• Handling missing data strategies for medical datasets where patients declined to answer certain questions.

Strengths

• Contains records for 858 patients, providing a substantive sample size for analysis.
• Includes a wide range of risk factor variables, from demographic details to specific STD diagnoses.
• Target variable is clearly defined as a logical OR of four diagnostic test results.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.

Provenance

Source

Hospital Universitario de Caracas, Caracas, Venezuela

Collection Method

Collected patient demographic information, habits, and historic medical records.

Time Range

null

Freshness

null

Geography

Caracas, Venezuela