Home Page | Table of Contents | Previous Page | Next Page

Artificial Intelligence in the Academic Setting

Artificial Intelligence in the Academic Setting: Promise of Favorable Impact on Teaching, Research and Patient Care
Bernard L. Maria, MD, MBA, Douglas D. Dankel II, PhD.
University of Florida

The management of complex medical conditions such as brain tumors is costly and requires a large team of medical experts. Medical decision-making for these patients is hampered by the frequent inaccessibility of the experts, inconsistencies in the management of different patients, and the fact that multiple experts often yield multiple opinions. The overall goals of this work were (1) to develop and validate an expert system (XNEO - Expert Neuro-Oncology) to assist the medical team deliver efficient, quality care to patients with brain tumors, and (2) to determine the feasibility of constructing expert systems to enhance teaching, research and patient care in an academic setting. Radiation Oncology residents enjoyed learning by using XNEO and it enabled the attendings to identify Rdecision nodes of uncertaintyS that are driving new clinical research. Importantly, residents using XNEO ordered appropriate ancillary tests for patients and made far fewer incorrect treatment decisions. The potential net effect of using artificial intelligence in academic medicine may be more meaningful learning opportunities for trainees, the discovery of new research opportunities, increased patient and family satisfaction, and decreased probability of medical liability. At a time of important transformations in healthcare, we will discuss how novel expert systems hold promise as tools to reduce medical costs, improve the quality of multi-expert medical care, and advance health care education.


Edited on December 4, 1995 / Updated on December 4, 1995
Southeastern Medical Informatics Conference / June 10, 1995
Location: http://www.med.ufl.edu/medinfo/smic95/abs19.html
Contact: Douglas Dankel / ddd@cis.ufl.edu

Home Page | Table of Contents | Previous Page | Next Page