|
|
||||||||
Department of Radiology, Michigan State University, East Lansing, Michigan
Correspondence: For reprints contact: David A. Gift, MS, Dept. of Radiology, B-220 Clinical Ctr., Michigan State University, East Lansing, MI 48824-1315.
ABSTRACT
An information-theoretic pattern recognition method was sued to construct descriptive models of data related to 1,674 radioisotope lung scan referrals for the purpose of assessing lung scan influence on diagnosis and management of pulmonary embolism. It was observed that, relative to other clinical information available prior to the scan, the lung scan significantly improved the ability of the models to predict diagnostic and management outcomes, implying that the lung scan has significant influence on these clinical decisions.
| HOME | HELP | FEEDBACK | SUBSCRIPTIONS | ARCHIVE | SEARCH | TABLE OF CONTENTS |
| JOURNAL OF NUCLEAR MEDICINE TECHNOLOGY | THE JOURNAL OF NUCLEAR MEDICINE |