A research paper has been published this week focusing on the use of AI and machine learning to support early detection of pulmonary tuberculosis via chest radiography, following an international study across 10 countries.
The deep learning system (DLS) was trained to detect active pulmonary tuberculosis (TB), with the study highlighting the tool sensitivity of 88% and its specificity 79%. The researchers noted that using the DLS as a prioritisation tool for confirmatory testing reduced the cost per positive case detected by 40-80% compared to using confirmatory testing alone.
To help catch the disease early, Google researchers developed an AI-based tool to help identify patients who are likely to have active TB based on their chest X-ray.
Google said in their news release : “By using this screening tool as a preliminary step before ordering a more expensive diagnostic test, our study showed that effective AI-powered screening could save up to 80% of the cost per positive TB case detected.”
“Our AI-based tool was able to accurately detect active pulmonary TB cases with false-negative and false-positive detection rates that were similar to 14 radiologists.”
“To make sure the model worked for patients from a wide range of races and ethnicities, we used de-identified data from nine countries to train the model and tested it on cases from five countries. These findings build on our previous research that showed AI can detect common issues like collapsed lungs, nodules or fractures in chest X-rays.”
The AI system produces a number between 0 and 1 that indicates the risk of TB. Google noted that for the system to be useful in a real-world setting, there needs to be agreement about what risk level indicates that patients should be recommended for additional testing.
To develop the tool further, research studies are now planned with Apollo Hospitals in India and the Centre for Infectious Disease Research in Zambia (CIDRZ) to take place later this year.
