Advanced AI can now end the global TB crisis

Prevention and early diagnosis of tuberculosis is the key to its treatment

To achieve the goals set out in the end TB strategy, patients must be placed at the center of service delivery, and early diagnosis and prevention are the first steps. A strong infrastructure for testing and an adequate and trained workforce are the essential principles required to achieve this. 2021 Global TB Report, However, the finding shows that spending on TB diagnosis, treatment and prevention services has fallen from $5.8 billion to $5.3 billion, which is half of the global target of fully funding the tuberculosis response of $13 billion annually by 2022. less than .

The importance of data as well as the current situation has fostered awareness and acceptance of the need for development in our approach to healthcare workflows. This acceptance is facilitated by rapid steps by machine learning and artificial intelligence (AI) driven solutions specially designed to meet medical needs.

The role of AI in diagnosis is growing rapidly. The broad areas in which it can assist hospitals and clinicians include efficient and accurate clinical decision-making, medical image recognition, streamlining workflows through automation of repetitive tasks, relieving administrative burden and treatment management. Huh. In particular, the field of radiology has accelerated to adopt the use of AI solutions. This is because this field is data-driven and diagnosis depends on visual confirmation and interpretation of chest X-rays by a trained radiologist. This is where a significant challenge lies.

The global shortage of radiologists is one of the untold problems of healthcare. more than two third (5.2 billion) not one in 7.9 billion people on Earth have access. This skill paucity is a key factor behind growing issues in lung health care and is an area that AI solutions can impact by reducing the time pressure and resource-packed medical imaging professionals, allowing them to access imaging data. It helps to process a lot. Triage critical cases and generate reports.

There are various organizations developing AI solutions for medical imaging. is one of them Qure.ai, which has received FDA/CE approval for identifying and prioritizing abnormalities in chest X-rays. Let’s look at an example of how Qure.ai’s solution was deployed and contributed to mitigating issues and augmenting existing tuberculosis systems.

According to WHO, India is facing the highest burden of TB in the world. In a country with such a dense population, even hospitals in city centers struggle to manage the diagnosis-to-treatment cycle of this highly contagious disease. One of the major concerns for clinicians in urban facilities is TB triage, as potentially infected patients go missing before a proper diagnosis can be provided due to a lack of resources.

In the northwestern state of Rajasthan, Baran District Hospital caters to an area of ​​1.2 million residents. It is a tertiary care facility with a dedicated tuberculosis center and a range of radiology services and capabilities. It receives patient references from the local population and migrants from neighboring states. In 2019, the percentage of newly detected TB cases crossed 80% of the total notification, which is higher than the previous years. As a result, chest physicians at the hospital were struggling with a large TB patient base and were in dire need of assistance.

Qure.ai teamed up with the hospital to begin widespread deployment and real-time testing of its AI-powered chest X-ray solution. Its integration into clinical workflows has positively impacted clinical capability in several key areas. The notification rate increased by 33% and the number of drop-outs of the estimated cases decreased from 72% to 53%.

The use of AI tools for TB screening is at a critical moment. The Global TB Report recommends increasing investment in tuberculosis research to rapidly advance technological breakthroughs and innovation. AI-based interventions are a lever to achieve this.

Also, AI has an important role to play in the diagnosis and treatment of the world’s deadliest cancer – lung cancer. About 75% of patients die within five years of diagnosis because symptoms are detected in the later stages of the disease when it is harder to treat. About 35% of lung nodules are missed on initial screening and the initial symptoms are spontaneous and often ruled out.

When physiological indicators of lung cancer are identified earlier, the outcomes of patients are improved dramatically. The main task of the radiologist in the screening workflow is to search for pulmonary nodules and assess their malignant risk based on size, shape, structure, type, location and growth. These can also be evaluated by AI solutions, which can perform CT scans and detect lung nodules that may not even be visible to the naked eye.

Thus, AI can play an important role as a parallel diagnostic tool, selectively automating repetitive procedures, enhancing clinicians’ efforts and acting as a second pair of eyes to avoid any delay in treatment. Don’t be After all, the potential of AI to impact healthcare and benefit stakeholders is infinite, limited only by our imagination.

Article Originally appeared in the World Economic Forum.

Read also: The oceans contain 50 times more carbon than the atmosphere. A ‘code of conduct’ can save it