Transfer Learning for tuberculosis screening by single-channel ECG

Abstract

Tuberculosis is one of the leading causes of death in the world. The majority of the population is not able to regularly conduct specific examinations, such as x-ray examinations, for the presence of tuberculosis. Currently, there are mobile devices for measuring ECG, which allow you to take measurements without leaving your home. This article explores the possibility of determining tuberculosis based on a single- channel mobile ECG. One of the general top-performance neural networks is used as a classifier. This article also explored the possibility of such a classification based not on raw data, but the generated image. The image allows you to interpret the prediction of the neural network and makes it possible for the doctor to understand the model’s decision better. The article shows the promising quality and provides proof of concept of such screening. Different ratios of precision and recall are provided, which can be adjusted depending on the situation.