Applying a statistical PTB detection procedure to complement the gold standard

Abstract This paper investigates a novel statistical discrimination procedure to detect PTB when the gold standard requirement is taken into consideration. Archived data were used to establish two groups of patients which are the control and test group. The control group was used to develop the stat...

Full description

Saved in:
Bibliographic Details
Published in:Computerized medical imaging and graphics 2011-04, Vol.35 (3), p.186-194
Main Authors: Noor, Norliza Mohd, Yunus, Ashari, Bakar, S.A.R. Abu, Hussin, Amran, Rijal, Omar Mohd
Format: Article
Language:English
Subjects:
Algorithms
Data Interpretation, Statistical
Digital chest radiographs
Discrimination
Gold standard
Humans
Internal Medicine
Malaysia
Mycobacterium
Other
Practice Guidelines as Topic
Pulmonary tuberculosis and lung cancer
Radiographic Image Interpretation, Computer-Assisted - methods
Radiographic Image Interpretation, Computer-Assisted - standards
Radiography, Thoracic - methods
Radiography, Thoracic - standards
Reproducibility of Results
Sensitivity and Specificity
Statistical graphical method
Tuberculosis, Pulmonary - diagnostic imaging
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Abstract This paper investigates a novel statistical discrimination procedure to detect PTB when the gold standard requirement is taken into consideration. Archived data were used to establish two groups of patients which are the control and test group. The control group was used to develop the statistical discrimination procedure using four vectors of wavelet coefficients as feature vectors for the detection of pulmonary tuberculosis (PTB), lung cancer (LC), and normal lung (NL). This discrimination procedure was investigated using the test group where the number of sputum positive and sputum negative cases that were correctly classified as PTB cases were noted. The proposed statistical discrimination method is able to detect PTB patients and LC with high true positive fraction. The method is also able to detect PTB patients that are sputum negative and therefore may be used as a complement to the gold standard.
ISSN:0895-6111
1879-0771
DOI:10.1016/j.compmedimag.2010.10.002