Review on Data Mining Methods for Tuberculosis Diagnosis

Rusdah Rusdah, Edi Winarko

ISICO 2013 · 2013 · 11 citations · 17 references

Concepts

Abstract

Tuberculosis, which is the oldest human disease wit h the highest mortality rates among infectious diseases, continues to be the worl d's attention. Previous methods to diagnose tuberculosis are tuberculin test, Sputum-s mear microscopy and chest radiography. Unfortunately, these methods are time consuming and perform poorly. Furthermore, they require varied sensitivity, Mycob acterium tuberculosis bacilli alive, sputum which is difficult to obtain from chi ldren, trained personnel to avoid human error, and hence, high cost. Researchers keep developing accurate data mining methods for rapid Tuberculosis diagnosis to reduce the rate of growth of the world population of tuberculosis patients. This paper aims to provide state-of-the-art of data mining methods in diagnosing Tuberculosis u sing clinical symptoms as input parameters. First, it introduces tuberculosis and c urrent methods used for tuberculosis diagnosis. Then it discusses technique s for preprocessing data and data mining methods for tuberculosis diagnosis currently used. The result shows that the most frequently used variables are sweating at nigh t, more than 3 weeks of cough, fever, weight loss, age, and chest pain respectivel y. Support Vector Machine and Bayesian Network gave the highest accuracy compared to other methods.

References

17