NEURALTB WEB SYSTEM - Support to the Smear Negative Pulmonary Tuberculosis Diagnosis

Carmen Maidantchik, José Manoel de Seixas, Afrânio Kritski, Fernanda C. de Q Mello, Rony T. V. Braga, Pedro H. S. Antunes, João Baptista de Oliveira e Souza Filho

2007

Abstract

The World Health Organization estimates that one third of the world population is infected by mycobacterium tuberculosis. Tuberculosis (TB) affects mainly poor health places in developing countries. Therefore, it became mandatory to develop more efficient, fast, and inexpensive analysis methods. This paper presents a decision support system that uses neural networks to sustain TB diagnosis. The output is the probability that a patient has or not the illness and an assigned risk group. The NeuralTB system encapsulates the knowledge needed for efficient anamnesis interview integrated to demographic and threat factors typically known for tuberculosis diagnosis. It was developed with the Web technology and data were described with a markup language to enable an efficient communication and information exchange among experts. Data collected during the whole process can be used to identify possible new factors or symptoms, since the infection transmission may evolve. This information can also support tuberculosis control governmental entities to define effective actions to protect the health and safety of the population.

References

  1. Castelo A., Kritski A.L., Werneck A., Lemos A.C., Ruffino Netto A., et al., 2004. Brazilian Directives for Tuberculosis. J Brás Pneumo, 30 (supl 1). 1- 86. In Portuguese.
  2. Chapman, A., 2005. Principles of Data Quality, Report, Global Biodiversity Information Facility.
  3. Cook, J., 2000. XML Sets Stage for Efficient Knowledge Management, IT professional, v.2, n.3, 55-57.
  4. El-Solh, A.A., Hsiao, C.-B., Goodnough, S., Serghani, J., Grant, B.J.B., 1999. Predicting Active Pulmonary Tuberculosis using an Artificial Neural Network. Chest, 116, 968-973.
  5. Hendriks, P., Vriens, D. 1999. Knowledge-Based Systems and Knowledge Management: Friends or Foes?. Information & Management, v.35, n.2 (Feb), 113-125.
  6. Kohavi, R., 1995. A study of cross-validation and bootstrap for accuracy estimation and model selection. In International Joint Conference on Artificial Intelligence.
  7. Mello, F.C.Q., 2001. Smear Negative Pulmonary Tuberculosis Predicting Models, Ph.D. Thesis, Medicine Faculty, Federal University of Rio de Janeiro, Brazil. In Portuguese.
  8. Perkins, M.D.., Kritski, A.L., 2002. Perspectives. Diagnostic Testing in the Control of Tuberculosis. In: Bull WHO, 80 (6), 512-513.
  9. Probst, G., Raub, S., Romhardt, K. 1999. Managing Knowledge: Building Blocks for Success, 368 pp, ISBN: 0-471-99768-4.
  10. Rabarijaona, A., Dieng, R., Olivier, C., Quaddari, R. 2000. Building and Searching an XML-Based Corporate Memory, IEEE Intelligent Systems, v.15, n.3 (May), 56-63.
  11. Sarmiento, O., Weigle, K., Alexander, J., Weber, D.J., Miller, W., 2003. Assessment by Meta-Analysis of PCR for Diagnosis of Smearnegative Pulmonary Tuberculosis, Journal of Clinical Microbiology, 41, 3233-3240.
  12. Santos, A.M. 2003. Neural Networks and Classification Trees Applied to Smear Negative Pulmonary Tuberculosis Diagnosis, Ph.D. Thesis, COPPE/ UFRJ, Rio de Janeiro, Brazil. In Portuguese.
  13. Santos, A.M., Pereira, B.B., Seixas, J.M., Mello, F.C.Q., Kristski, A.L., 2006. Neural Networks: an Application for Predicting Smear Negative Pulmonary Tuberculosis. In: Balakrishnan, N.; Auget, J.L.; Mesbah, M.; Molenberghs, G. (org.). In: Advances in Statistical Methods for The Health Sciences. 279-292.
  14. Seixas, J.M., Calôba, L.P., Delpino, I., 1996. Relevance Criteria for Variable Selection in Classifier Design. In: International Conference on Engineering Applications of Neural Networks, 451-454.
  15. Vassali, M.R., Seixas, J.M., Calôba, L.P., 2002. A Neural Particle Discriminator Based on a Modified Art Architecture. In: IEEE International Symposium on Circuits and Systems, v. II., 121-124.
  16. World Health Organization (WHO), 2002. Stop TB annual report 2001.
Download


Paper Citation


in Harvard Style

Maidantchik C., Manoel de Seixas J., Kritski A., C. de Q Mello F., T. V. Braga R., H. S. Antunes P. and Baptista de Oliveira e Souza Filho J. (2007). NEURALTB WEB SYSTEM - Support to the Smear Negative Pulmonary Tuberculosis Diagnosis . In Proceedings of the Ninth International Conference on Enterprise Information Systems - Volume 2: ICEIS, ISBN 978-972-8865-89-4, pages 198-203. DOI: 10.5220/0002366401980203


in Bibtex Style

@conference{iceis07,
author={Carmen Maidantchik and José Manoel de Seixas and Afrânio Kritski and Fernanda C. de Q Mello and Rony T. V. Braga and Pedro H. S. Antunes and João Baptista de Oliveira e Souza Filho},
title={NEURALTB WEB SYSTEM - Support to the Smear Negative Pulmonary Tuberculosis Diagnosis},
booktitle={Proceedings of the Ninth International Conference on Enterprise Information Systems - Volume 2: ICEIS,},
year={2007},
pages={198-203},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002366401980203},
isbn={978-972-8865-89-4},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Ninth International Conference on Enterprise Information Systems - Volume 2: ICEIS,
TI - NEURALTB WEB SYSTEM - Support to the Smear Negative Pulmonary Tuberculosis Diagnosis
SN - 978-972-8865-89-4
AU - Maidantchik C.
AU - Manoel de Seixas J.
AU - Kritski A.
AU - C. de Q Mello F.
AU - T. V. Braga R.
AU - H. S. Antunes P.
AU - Baptista de Oliveira e Souza Filho J.
PY - 2007
SP - 198
EP - 203
DO - 10.5220/0002366401980203