Science India Bureau
India may have put the second wave of COVID-19 behind itself but the heart-rending devastation it has left in its wake will not be forgotten for a very long time to come. It was a historically unprecedented situation when the best equipped of Indian cities — Delhi, Mumbai, Pune and Bengaluru, to name a few — cracked up under the onslaught of the virus.
In such a scenario, the ravages that the second wave of COVID-19 caused on rural India can only be conjectured, especially because the data is shocking — there is less than one radiologist per million people in the villages of India. Deaths, in such a case, are caused as much by the infection as by the lack of early intervention due to reduced access to RT-PCR test, newly emerging virus strains, and delay in start of treatment, among other factors.
But the doomsday scenario which has gripped the world since the start of the pandemic last year has shown many streaks of silver lining. In India, specifically, its technologists, scientists and entrepreneurs have been at the forefront of turning the crisis into an opportunity with innovations that are best suited to meet the needs of the country.
To its detractors, love at first sight must be an illusion – the wrong term for what is simply iOne such innovation that has come up to assist in the fight against COVID-19 is a new AI software called ‘XraySetu’ that has been devised for early intervention through rapid screening of COVID-19 over WhatsApp.
XraySetu has been developed by ARTPARK (AI & Robotics Technology Park), a not-for-profit foundation established by the Indian Institute of Science (IISc), Bengaluru, with the support from the Department of Science & Technology (DST), Government of India, in collaboration with Bengaluru-based Health-Tech start-up, Niramai.
It is especially going to be useful to people in rural areas of the country who do not have access to doctors to diagnose COVID-19 and to latest medical technologies. The specially-designed platform cuts out the delay in intervention through rapid screening of COVID-19 with chest X-ray interpretation for doctors who have access to X-ray.
The AI-driven technology uses X-ray images that are sent via WhatsApp to help determine if the subject is suffering from COVID-19. Though the images sent over WhatsApp can be highly pixelated due to lack of good quality cameras or due to compression generated by the app, XraySetu can identify COVID-19 infection even from low-resolution chest X-ray images. Users are being invited to test the beta version of the technology. The platform is supported by WhatsApp, Amazon Web Services, CDAC, Kaleyra and NVIDIA.
It also has semantic annotations of affected areas for review and localised heatmap by doctors to help them verify easily with other modalities and has served close to 1,200 plus reports so far from the interior parts of India. XraySetu is quick and simple for busy doctors to use. It comes in a play and plug format and does not require integration with existing systems. This could be the model for the future of Indian healthcare, accessible to everyone wherever they might be.
Founder and CEO of ARTPARK Umakant Soni said that the XraySetu has been developed in collaboration with start-up Niramai and IISc and no fee is being charged currently for this. “We are planning to create a strong network of 10,000 doctors who are trained in leveraging XraySetu so that when the third COVID-19 wave comes, we are ready with solutions that can reach doctors in rural areas,” Soni said. He also revealed that the technology has been operational and around 500 doctors have used it.
Tested and validated with over 1,25,000 X-ray images from National Institute of Health, UK as well as over 1,000 Indian COVID-19 patients, XraySetu has shown excellent performance with 98.86% sensitivity and 74.74% specificity.
“We need to scale up the technology for addressing the needs of 1.36 billion people. Built with the collaboration of industry and academia, XraySetu paves the way for exponential technologies like AI to leapfrog and provide cutting-edge healthcare technology to rural India in an extremely cost-effective manner,” Soni added.
Prof Chiranjib Bhattacharyya of IISc said, “In the absence of COVID-positive X-ray images, we developed a unique Transfer Learning framework that leverages easily available X-ray images of lungs, not necessarily COVID-positive, to learn useful features which have high predictive power. We also developed a confidence score which is guided by the areas of lungs that are infected. The system outputs a prediction, localises the infected parts, and creates a report which gives a confidence score, all within a few minutes.”
Besides COVID-19, the AI powered software can also detect 14 additional lung-related ailments, including tuberculosis, asthma and pneumonia. It can further be used for both analogue and digital X-rays and has been successfully piloted by more than 300 doctors in rural areas over the last 10 months. Technologies like XraySetu can enable cutting-edge AI-driven systems powering mobile primary health centres (PHCs), which can make healthcare more accessible even across rural India at a fraction of the cost.
Here’s how the tests can be conducted using XraySetu
- To conduct the health check, a doctor simply needs to visit www.xraysetu.com and click on the ‘Try the Free XraySetu Beta’ button.
- The platform will then redirect the person to another page, wherein he or she can choose to engage with the WhatsApp-based chatbot via web or smartphone application.
- The doctor can however simply send a WhatsApp message to the phone number +91 8046163838 to start the XraySetu service. Then they just need to click the picture of the patient’s X-ray and obtain the 2-page automated diagnostics with annotated images in 10 to 15 minutes.
- While extending the probability of the COVID-19 contraction, the report also highlights a localised heatmap for a quick perusal of the doctor.
