JMIR Publications

ABSTRACT

Background:

Technological advancement has led to the growth and rapid increase of tuberculosis (TB) medical data generated from different healthcare operations areas including diagnosis. Prioritizing better adoption and acceptance of innovative diagnostic technology to reduce the spread of TB significantly benefits developing countries. Trained scent TB detection rats technology is used in Tanzania and Ethiopia for operational research to complement other TB diagnostic tools. This technology has increased new TB case detection due to its speed, cost-effectiveness, and sensitivity. During the TB detection process, rats produce vast amounts of data, providing an opportunity to find interesting patterns that influence TB detection performance.

Objective:

This paper aims at developing models that predict if the rat would HIT the sample or not using ML techniques

Methods:

Classification supervised ML technique uses different ML algorithms such as Decision Tree, Random Forest, Naïve Bayes, Support Vector Machine (SVM), and k-Nearest Neighbor (kNN) to build predictive models that categorize data and assign a label to manipulated and newly encountered data.

Results:

The study found that the inclusion of variables related to whether the sample contained TB or not increased the performance accuracy of the predictive model

Conclusions:

The results may be of importance to TB rats’ trainers and TB decision-makers by taking actions to maintain the usefulness of the technology and increase rats’ TB detection performance.