Welcome to the InfoSci Platform
Diagnostic Cost Reduction Using Artificial Neural Networks: The Case of Pulmonary Embolism

Diagnostic Cost Reduction Using Artificial Neural Networks: The Case of Pulmonary Embolism

Steven Walczak, Bradley B. Brimhall, Jerry B. Lefkowitz
Copyright: © 2008 |Pages: 23
ISBN13: 9781599046907|ISBN10: 1599046903|ISBN13 Softcover: 9781616927110|EISBN13: 9781599046921
DOI: 10.4018/978-1-59904-690-7.ch006
Cite Chapter Cite Chapter

MLA

Walczak, Steven, et al. "Diagnostic Cost Reduction Using Artificial Neural Networks: The Case of Pulmonary Embolism." Healthcare Information Systems and Informatics: Research and Practices, edited by Joseph Tan, IGI Global, 2008, pp. 108-130. https://doi.org/10.4018/978-1-59904-690-7.ch006

APA

Walczak, S., Brimhall, B. B., & Lefkowitz, J. B. (2008). Diagnostic Cost Reduction Using Artificial Neural Networks: The Case of Pulmonary Embolism. In J. Tan (Ed.), Healthcare Information Systems and Informatics: Research and Practices (pp. 108-130). IGI Global. https://doi.org/10.4018/978-1-59904-690-7.ch006

Chicago

Walczak, Steven, Bradley B. Brimhall, and Jerry B. Lefkowitz. "Diagnostic Cost Reduction Using Artificial Neural Networks: The Case of Pulmonary Embolism." In Healthcare Information Systems and Informatics: Research and Practices, edited by Joseph Tan, 108-130. Hershey, PA: IGI Global, 2008. https://doi.org/10.4018/978-1-59904-690-7.ch006

Export Reference

Mendeley
Favorite

Abstract

Patients face a multitude of diseases, trauma, and related medical problems that are difficult and costly to diagnose with respect to direct costs, including pulmonary embolism (PE). Advanced decision-making tools such as artificial neural networks (ANNs) improve diagnostic capabilities for these problematic medical conditions. The research in this chapter develops a backpropagation trained ANN diagnostic model to predict the occurrence of PE. Laboratory database values for 292 patients who were determined to be at risk for a PE, with 15% suffering a confirmed PE, are collected and used to evaluate various ANN models’ performance. Results indicate that using ANN diagnostic models enables the leveraging of knowledge gained from standard clinical laboratory tests, significantly improving both overall positive predictive and negative predictive performance.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.