Novel AI model may lead to personalised tuberculosis treatments: Study

'Our multimodal AI model accurately predicted treatment prognosis and outperformed existing models that focus on a narrow set of clinical data,' said Sriram Chandrasekaran, associate professor at the University of Michigan.

New Delhi: Scientists have developed a new artificial intelligence (AI) model to predict treatment outcomes of tuberculosis (TB) patients, an advance that may lead to personalised treatments for the bacterial disease.

The study, published in the journal iScience, analysed multimodal data including diverse biomedical data from clinical tests, genomics, medical imaging and drug prescriptions from TB patients.

By analysing data from patients with varying levels of drug resistance, the researchers discovered biomedical features predictive of treatment failure.

They also uncovered drug regimens effective against specific sets of drug-resistant TB patients.

"Our multimodal AI model accurately predicted treatment prognosis and outperformed existing models that focus on a narrow set of clinical data," said Sriram Chandrasekaran, corresponding author and associate professor at the University of Michigan, US.

"We identified drug regimens that were effective against certain types of drug-resistant TB across countries, which is very important due to the spread of drug-resistant TB," added study first author Awanti Sambarey, a postdoctoral fellow at the University of Michigan.

Using AI, the team examined more than 5,000 patients.

"This is real-world data we're talking about, so patients from different countries have different admission protocols. We worked with more than 200 biomedical features in our analysis; we examined demographic information such as age and gender as well as prior treatment history," Sambarey said.

"We also noted if the patients had other comorbidities, such as HIV, and then we worked with several imaging features such as their X-ray, CT scans, data from the pathogens, drug-resistance data, as well as genomic features and what mutations the pathogen had," she said.

The researchers noted that it is very difficult clinically to look at the data all together. That is where the role of AI comes in handy.

The team also studied the impact of the type of drug resistance present.

"You can look at a specific snapshot of the data, such as genomic features and find what mutations the infecting pathogen had, and ask what some of the long-term treatment implications are," Sambarey added.

The researchers found that certain drug combinations worked better in patients with some types of resistance but not others, leading to treatment failure. They also found that drugs with antagonistic pharmaceutical interactions could result in worse outcomes.

"Using AI to weed out antagonistic drugs early in the drug-discovery process can avoid treatment failure down the line," Chandrasekaran noted.

"Instead of a one-size-fits-all treatment approach, we hope that the study of multimodal data will help physicians treat patients with more personalized treatments to provide the best outcomes," Sambarey added.