Knowledge Discovery in Clinical Performance of Cancer Patients
Authors:
- John HaywardJHJohn Hayward
- Sergio AlvarezSASergio Alvarez
- Carolina RuizCRCarolina Ruiz
- Mary SullivanMSMary Sullivan
- Jennifer TsengJTJennifer Tseng
- Giles WhalenGWGiles Whalen
- 1 January 2008
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 51-58
Abstract
Our goal in this research is to construct predictive models for clinical performance of pancreatic cancer patients. Current predictive model design in medical oncology literature is dominated by linear and logistic regression techniques. We seek to show that novel machine learning methods can perform as well or better than these traditional techniques.We construct these predictive models via a clinical database we have developed for the University of Massachusetts Memorial Hospitalin Worcester, Massachusetts, USA. The database contains retrospective records of 91 patient treatments for pancreatic tumors.Classification and regression prediction targets include patient survival time, ECOG quality of life scores, surgical outcomes,and tumor characteristics. The predictive accuracy of various data mining models is described, and specific models are presented.Keywords
This publication has 7 references indexed in Scilit:
- Comparison of Endoscopic Ultrasonography and Multidetector Computed Tomography for Detecting and Staging Pancreatic CancerAnnals of Internal Medicine, 2004
- Prognostic Nomogram for Patients Undergoing Resection for Adenocarcinoma of the PancreasAnnals of Surgery, 2004
- Machine learning for medical diagnosis: history, state of the art and perspectiveArtificial Intelligence in Medicine, 2001
- A Decision-Theoretic Generalization of On-Line Learning and an Application to BoostingJournal of Computer and System Sciences, 1997
- Prognosing the Survival Time of Patients with Anaplastic Thyroid Carcinoma using Machine Learning1997
- Bagging predictorsMachine Learning, 1996
- Stacked generalizationNeural Networks, 1992