Thoracic Surgery Data

The data is dedicated to classification problem related to the post-operative life expectancy in the lung cancer patients: class 1 - death within one year after surgery, class 2 - survival.

Characteristics
Multivariate
Subject Area
Health and Medicine
Associated Tasks
Classification

Attribute Type
--
# Instances
470
# Attributes
16

Info

The data was collected retrospectively at Wroclaw Thoracic Surgery Centre for patients who underwent major lung resections for primary lung cancer in the years 2007 to 2011. The Centre is associated with the Department of Thoracic Surgery of the Medical University of Wroclaw and Lower-Silesian Centre for Pulmonary Diseases, Poland, while the research database constitutes a part of the National Lung Cancer Registry, administered by the Institute of Tuberculosis and Pulmonary Diseases in Warsaw, Poland.


Introductory Paper

Boosted SVM for extracting rules from imbalanced data in application to prediction of the post-operative life expectancy in the lung cancer patients

By Maciej Ziȩba, Jakub M. Tomczak, M. Lubicz, J. Swiatek. 2014

Published in Applied Soft Computing

Provided by
University of California, Irvine


Creators
  • Marek Lubicz
  • Konrad Pawelczyk
  • Adam Rzechonek
  • Jerzy Kolodziej

DOI

10.24432/C5Z60N

Login to Download

New to AIM-AHEAD Connect?
Create an account!

Features

Attribute Name Role Type Demographic Description Units Missing Values
DGN Feature Categorical Diagnosis - specific combination of ICD-10 codes for primary and secondary as well multiple tumours if any no
PRE4 Feature Continuous Forced vital capacity - FVC (numeric) no
PRE5 Feature Continuous Volume that has been exhaled at the end of the first second of forced expiration - FEV1 (numeric) no
PRE6 Feature Categorical Performance status - Zubrod scale (PRZ2,PRZ1,PRZ0) no
PRE7 Feature Binary Pain before surgery (T,F) no
PRE8 Feature Binary Haemoptysis before surgery (T,F) no
PRE9 Feature Binary Dyspnoea before surgery (T,F) no
PRE10 Feature Binary Cough before surgery (T,F) no
PRE11 Feature Binary Weakness before surgery (T,F) no
PRE14 Feature Categorical T in clinical TNM - size of the original tumour, from OC11 (smallest) to OC14 (largest) (OC11,OC14,OC12,OC13) no
PRE17 Feature Binary Type 2 DM - diabetes mellitus (T,F) no
PRE19 Feature Binary MI up to 6 months (T,F) no
PRE25 Feature Binary PAD - peripheral arterial diseases (T,F) no
PRE30 Feature Binary Smoking (T,F) no
PRE32 Feature Binary Asthma (T,F) no
AGE Feature Integer Age Age at surgery (numeric) no
Risk1Yr Target Binary 1 year survival period - (T)rue value if died (T,F) no