Classification methods and ROC analysis for outcome prediction of patients following injuries. (7th February 2012)

• Record Type: Journal Article
• Authors: Koukouvinos, C.; Parpoula, C.; Theodoraki, E.-M.
• Is Part Of: International journal of biomedical engineering and technology. Volume 8:Number 1(2012)
• Page Start: 49
• Page End: 59
• Publication Date: 2012-02-07
• Subjects: data mining -- classification trees -- ROC analysis -- medical data -- outcome prediction; Biomedical engineering -- Periodicals; 610.28
• Languages: English
• ISSNs: 1752-6418

Abstract

Receiver Operating Characteristics (ROC) analysis is commonly used in medical decision making, and in recent years has been used increasingly in machine learning and data-mining research. In this study, it is used for assessing the performance of classification algorithms in predicting trauma patients' outcome. Data set comprised 8544 severely injured patients who had been admitted to Hellenic hospitals from the year 2005 to 2006. We analysed the demographic data and the factors that may have influenced the outcome in the group of patients with trauma and several combinations of significant factors were determined for that purpose.