HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS		QUICK SEARCH:   [advanced] Author: Keyword(s): Year:  Vol:  Page:
Guest Access | Sign In via User Name/Password

This Article Full Text Free Full Text (PDF) Free Submit a response Alert me when this article is cited Alert me when eLetters are posted Alert me if a correction is posted Citation Map Services Email this article to a friend Similar articles in this journal Similar articles in ISI Web of Science Similar articles in PubMed Alert me to new issues of the journal Add to My Personal Article Archive Download to citation manager Citing Articles Citing Articles via HighWire Citing Articles via ISI Web of Science (15) Citing Articles via Google Scholar Google Scholar Articles by El-Solh, A. A. Articles by Grant, B. J. B. Search for Related Content PubMed PubMed Citation Articles by El-Solh, A. A. Articles by Grant, B. J. B.

Predicting Active Pulmonary Tuberculosis Using an Artificial Neural Network^*

^* From the Department of Medicine (Drs. El-Solh and Grant), Division of Pulmonary and Critical Care Medicine, the Division of Infectious Disease (Dr. Hsiao and Ms. Goodnough), and the Department of Radiology (Dr. Serghani), Erie County Medical Center, and the Veterans Affairs Medical Center, State University of New York at Buffalo, School of Medicine and Biomedical Sciences, Buffalo, NY.

Correspondence to: Ali El-Solh, MD, Division of Pulmonary and Critical Care Medicine, Erie County Medical Center, 462 Grider St, Buffalo, NY 14215; e-mail: solh{at}buffalo.edu

Background: Nosocomial outbreaks of tuberculosis (TB) have been attributed to unrecognized pulmonary TB. Accurate assessment in identifying index cases of active TB is essential in preventing transmission of the disease.

Objectives: To develop an artificial neural network using clinical and radiographic information to predict active pulmonary TB at the time of presentation at a health-care facility that is superior to physicians' opinion.

Design: Nonconcurrent prospective study.

Setting: University-affiliated hospital.

Participants: A derivation group of 563 isolation episodes and a validation group of 119 isolation episodes.

Interventions: A general regression neural network (GRNN) was used to develop the predictive model.

Measurements: Predictive accuracy of the neural network compared with clinicians' assessment.

Results: Predictive accuracy was assessed by the c-index, which is equivalent to the area under the receiver operating characteristic curve. The GRNN significantly outperformed the physicians' prediction, with calculated c-indices (± SEM) of 0.947 ± 0.028 and 0.61 ± 0.045, respectively (p < 0.001). When the GRNN was applied to the validation group, the corresponding c-indices were 0.923 ± 0.056 and 0.716 ± 0.095, respectively.

Conclusion: An artificial neural network can identify patients with active pulmonary TB more accurately than physicians' clinical assessment.

Key Words: c-index • neural network • nosocomial outbreaks • tuberculosis

This article has been cited by other articles:

				P. S. Heckerling, B. S. Gerber, T. G. Tape, and R. S. Wigton Prediction of Community-Acquired Pneumonia Using Artificial Neural Networks Med Decis Making, March 1, 2003; 23(2): 112 - 121. [Abstract] [PDF]

				R Freeman, J Magee, and A Barrett Identifying sputum specimens of high priority for examination by enhanced mycobacterial detection, identification, and susceptibility systems (EMDISS) to promote the rapid diagnosis of infectious pulmonary tuberculosis J. Clin. Pathol., August 1, 2001; 54(8): 613 - 616. [Abstract] [Full Text] [PDF]