Nonparametric Decision Support Systems in Medical Diagnosis

Abstract

Patients face a multitude of diseases, trauma, and related medical problems that are difficult and costly with respect to direct costs and diagnosis, including pulmonary embolism (PE), which has mortality rates as high as 10%. Advanced decision-making tools, such as nonparametric neural networks (NN), may improve diagnostic capabilities for these problematic medical conditions. The research develops a backpropagation trained neural network diagnostic model to predict the occurrence of PE. Laboratory database values for 292 patients who were determined to be at risk for PE, with almost 15% suffering a confirmed PE, were collected and used to evaluate various NN models' performances. Results indicate that using NN diagnostic models enables the leveraging of knowledge gained from standard clinical laboratory tests, specifically the d-dimer assay and reactive glucose, significantly improving overall positive predictive value, compared to using either test in isolation, and also increasing negative predictive performance.

Artificial Neural Networks and other AI Applications for Business Management Decision Support

“…An example of an AI application that operates on the expense side is an intelligent agent system for identifying optimal prices at auctions (Gregg & Walczak, 2006), which may be generalized to find optimal pricing on various resources through other market channels. Other ANN applications demonstrate how to achieve cost savings as well as improving the quality of care by developing a new business heuristic to eliminate unnecessary steps in treatment of patients (Walczak, Brimhall, & Lefkowitz, 2006) and reduce resource utilization and consequent waste (Walczak & Scharf, 2000).…”