How AI is changing healthcare in India – it reads scans, predicts risks and more
New Delhi: In the past, health care was only about doctors, medicines and diagnostics. In the new post-pandemic world around us right now, a new element has entered this simple equation: artificial intelligence (AI).
Technology, which is now a big part of several sectors across industries, is being used in several hospitals across India for various purposes – from reading scans to predicting risk.
Covid-19 has only solidified the role of AI in healthcare, with hospitals even detecting the extent of lung damage, especially in the second wave when the Delta variant of the SARS-CoV-2 virus led to a rapid deterioration in lung health.
While the use of AI is still widespread in radiology, especially for diseases like tuberculosis (TB), it is increasingly being used for other purposes, including preventive health check-ups, in particular to predict the risk of heart disease.
The government of India too bet big on AI to help it track outbreaks across India. A tool currently being developed by a private company in collaboration with the National Center for Disease Control (NCDC) will analyze all health-related media reports, to create a database of outbreaks of 33 diseases – some of which can become epidemics – which are monitored under the Integrated Disease Surveillance Program (IDSP).
For most hospitals and companies developing AI tools specifically for healthcare facilities, the journey began about four years ago, primarily with radiology.
“The first use of AI was in radiology. There is a feature that we all know: facial recognition. We started using AI for image identification, then we partnered with companies to validate the results. During the Covid pandemic, especially during the second wave, we used AI to analyze CT scans to determine the degree of lung infection,” said Dr. Bharat Aggarwal, Chief Technology Officer, Max Healthcare, Delhi.
“We are also doing a lot of research on the use of AI for TB detection and have partnered with some healthcare start-ups. We are also looking at the use of AI for detect psychiatric diseases and cognitive disorders of the brain,” he added. noted.
Read also : Two Hospitals in Faridabad, Chennai Launch New Center for Rapid Organ Transplant Services
Boost for underserved areas
Seventeen years after the launch of the National Rural Health Mission, infrastructure and labor shortages continue to plague large swaths of India, especially rural areas. This is where AI could become an enabler, according to companies working in the field.
AI-based solutions company Deeptek.ai was established in 2017. Partners in the firm include Indian Institute of Technology (IIT) graduate Ajit Patil and radiologist Dr. Amit Kharat. The many projects the company is working on include one in Chennai that uses AI for tuberculosis screening, Patil said.
“Our first such project is in Chennai. We are working with the Stop TB partnership to run these TB screening vans. Previously the detection rates were around 50 out of 100,000 scans but now with the use of AI it has increased to 500. Now we are bringing the same solution to rural clinics in Uttar Pradesh “, he told ThePrint.
In the long term, he said, AI could become autonomous (like driverless cars) where the role of human experts would be limited to validation.
“It is especially important for a country like India because there are only 12,000 radiologists for the whole country. There is a shortage of radiologists worldwide in fact,” he added.
Prashant Warrier, CEO of qure.aianother company working in the health sector, told ThePrint that his company is currently working at around 600 sites on projects that include tuberculosis screening, early detection of lung cancer and also help patients with Stroke to get early interventions.
The company’s AI-based solution for neurological patients, called qERcan quantify critical abnormalities such as brain bleeds, skull fractures, and strokes to help emergency physicians prioritize conditions requiring urgent attention.
Wadhwani AI, which works in partnership with the Indian government, is working on several TB control projects that include not only radiological tools but also the prediction of the risk of ‘Loss to Follow Up (people who do not show up for follow-up appointments). This is important for TB because treatment is a long process that can take 6-9 months and many people experience side effects that cause them to give up halfway through.
“To help frontline health workers identify underweight newborns and monitor their growth, we are developing smartphone-based technology that provides accurate, timely, geolocated and tamper-proof weight estimation,” said said a Wadhwani AI spokesperson. says ThePrint.
“Globally, 2.4 million children died in the first month of life in 2019, or around 6,700 neonatal deaths every day. Research suggests that many of these deaths are preventable if the baby’s weight can be determined within the first week after birth – a huge problem in countries like India where a significant number of births still take place at home , without a qualified midwife or health professional. present,” the spokesperson said.
During the pandemic, the company had also developed AI-based cough sound analysis technology to help identify patients at risk for Covid before administering lab tests, even if they were asymptomatic.
Read also : Move on Zomato’s 10-Minute Delivery, Hyderabad Platform Aims to Deliver Ambulance in 8 Minutes
There is, however, a long way to go and many challenges ahead, said Dr Aggarwal.
“The systems are not fully suited to the use of AI, even computer systems are not. The accuracy of communication alerts needs to be increased. Over time however, as the database s “widens, the accuracy will be higher. This has many advantages,” he said.
“It’s machine learning, so there’s no distraction, although the lack of lateral thinking can be both positive and negative. Unlike a human doctor, the AI won’t look beyond the dataset/images presented to it,” he added.
The best-known AI program in healthcare was IBM’s Watson, used for cancer detection. In one published study in the Future Healthcare Review, US researchers wrote, “IBM’s Watson has received considerable media attention for its focus on precision medicine, particularly cancer diagnosis and treatment. Watson uses a combination of machine learning and NLP (natural language processing) capabilities.
“However, initial enthusiasm for this application of technology faded as customers realized the difficulty of teaching Watson how to treat particular types of cancer and integrating Watson into care processes and systems. Watson is not a single product, but a collection of “cognitive services” delivered through application programming interfaces (APIs), including speech and language-based data analysis programs, vision and machine learning. Most observers believe that Watson APIs are technically capable, but supporting cancer treatment was too ambitious a goal.
The main challenge for AI is data collection, given concerns about data security and privacy.
“The algorithms used in machine learning systems and AI can only be as good as the data. High quality data is crucial for high quality algorithms. However, the call for high quality data in discussions about AI often go without further specification or guidance on what it actually means,” the Wadhwani AI spokesperson explained.
“Since there are multiple sources of error in all data collection, users of AI-related technology should have a good understanding of the data source and potential data gaps. AI systems based on incomplete or biased data can lead to inaccurate results that violate fundamental human rights, including discrimination. Being transparent about the data used in AI systems helps prevent possible rights violations. This is especially important in the era of big data, where data volume is sometimes valued over quality,” the spokesperson added.
(Editing by Amit Upadhyaya)
Read also : Towards self-sufficiency: India now manufactures 35 pharmaceutical raw materials that were previously imported