Tuberculosis (TB) is the second deadliest infectious killer worldwide. Daily, more than 4,100 people die from TB, a largely-treatable disease, and nearly 30,000 people fall ill. According to the World Health Organisation, one-fourth of the world’s population is infected with TB.
To make matters worse, the lockdown restrictions imposed to contain COVID-19 exacerbated the situation due to restricted access to diagnostics and treatments. This resulted in 4.1 million cases going undiagnosed, with India the worst hit (41% of cases), followed by Indonesia (14%) and the Philippines (12%).
Despite these dire statistics, all is not lost. The advent of AI and Machine Learning (ML) has resulted in technological advances that are playing a pivotal role in curbing the spread of TB, and aiding in better treatment approaches. How does AI help eradicate TB?
Early detection is key
AI can play a vital role in efficient and accurate clinical decision-making by assisting in medical image recognition, streamlining workflow through the automation of repetitive tasks, relieving administrative burdens, and treatment management.
A recent study in Radiology found that an AI system detects TB in chest x-rays at a level comparable to radiologists. AI would be highly beneficial in areas with limited radiologist resources, which would include a large portion of the global population: more than two-thirds of the world’s people lack access to diagnostic imaging. Qure.ai, with its deep learning technology for automated interpretation of radiology exams and scans, is at the forefront of these advances.
Surveillance and control
AI can help predict TB burden at a subnational level by identifying hot spots, i.e. areas of relative disease. EPCON has used AI to increase active case finding in Pakistan (read about it here). The tracking and surveillance of TB cases is essential for disease control. AI-powered systems can identify high-risk populations, analyze TB transmission patterns and predict potential outbreaks, allowing health officials to take proactive measures to prevent the spread of disease.
The European Respiratory Journal notes that one of the important challenges facing TB patients is adherence to medication regimes. AI can help personalize treatment plans by analyzing a patient’s medical history, genomics and other data to predict effective treatment. More effective treatments are likely to have better adherence.
Improved treatment outcomes also reduce the risk of drug-resistant TB. In fact, US researchers have recently used machine learning, as published in the journal Cell Reports Medicine, to predict the effectiveness of multi-drug treatment combinations for TB. This may help in the design of new therapy regimens.
Public health policies
Information is central to planning and management. AI algorithms have the capacity to analyze large datasets to identify patterns and trends in TB incidence and prevalence. This can help allocate resources, such as pharmacy stock and diagnostic tools, more effectively leading to the strengthening of healthcare systems. In low and middle income countries, resources are frequently concentrated in more urban settings - rural dwellers are at increased risk of disease progression if resources are not distributed optimally.
To conclude, AI is a powerful tool in the fight against TB. By enabling early detection, improving treatment and drug adherence, strengthening local and regional healthcare systems, and identifying disease hotspots, AI can help achieve the World Health Organization’s goal of ending the TB pandemic by 2035.