The importance of collaboration in the fight against Covid-19 – analysis
One thing is for sure: We have a whole new disease that is spreading. It is virulent and will possibly affect everyone in one way or another. India’s healthcare system, even without the coronavirus (Covid-19), is overloaded. Now imagine what will happen when this new disease makes its way through this healthcare system. We must not only defend ourselves against Covid-19, but fight to survive.
The government realizes the threat Covid-19 poses to India’s medical and economic health, and has made some strong political decisions to contain its spread. For example, completely restricting the entry of foreign citizens has widespread implications and this must have been a difficult decision to make. Given that India has one of the lowest cases worldwide, we can learn from the experiences of other countries and use its data to our advantage.
On February 1, during her speech on the budget, Finance Minister Nirmala Sitharaman said:
“… establish hospitals in PPP mode. In the first phase, those Aspirational Districts will be covered, where there are currently no hospitals connected to Ayushman … Using machine learning and AI, in the Ayushman Bharat scheme, health authorities and the medical fraternity can attack the disease … “
That the government will partner with private industry in areas where it is lacking or unable to provide services, combined with the view that machine learning and Artificial Intelligence (AI) will be imperative in providing healthcare, that is precisely what is needed today. While the government’s partnership with private players is being discussed to expand the testing and treatment of Covid-19, it seems that they have all forgotten India’s private sector computing expertise, especially in artificial intelligence and machine learning.
There are many engineers in Indian research and development (R&D) centers of global giants like GE, Philips, Siemens, Google and Microsoft working in AI. If we add to this the creation of deep technology and research groups working on AI for health care, you will have a ready ecosystem of specialists who can create AI tools to fight Covid-19. The government needs to explore partnerships with such players, provide them with appropriate data, and essentially make a Public-Private Partnership (PPP) for data analysis and AI.
More than 6,500 real-time PCR (RT) tests have been performed for Covid-19 in India and around 115 patients have been confirmed. All clinical data, imaging data (including raw dicom files for X-rays and CT scans), laboratory data, RT-PCR, and viral genomics data and results of treatment results should be immediate open source and be available to researchers. Once this is done, the AI development process can begin.
Artificial intelligence systems are based on “learning” from pre-existing data. India has a unique opportunity to use AI in the fight against Covid-19, as a full-blown outbreak appears to be a few weeks away. Since Indian data alone would not be sufficient to create robust clinically applicable AI systems, we must take the initiative to generate a global collaboration for consolidation of Covid-19 data at the patient level. Countries can contribute anonymous patient data to central databases that can be accessed by researchers from across India and the world.
After making the data available, the government can expect a big response from AI developers. There will need to be robust performance benchmarks and automated evaluation systems to determine the best AI tools first, and then incorporate them.
Here are some types of AI tools that can be used at different stages of the disease:
One, predicting the progression of Covid-19 at the population level; two, medical imaging-based AI techniques; three, predicting clinical results in diagnosed patients.
Since our healthcare industry will be greatly affected when Covid-19 is spread across the country, we must use all available options to combat it. Partnering with the industry to develop advanced AI and data analysis tools in a PPP provides an effective way to start developing tools to predict, diagnose and forecast like never before.
It will not be easy. The development of these tools is based on access to data at the patient level, which does not exist in India. The government will need to devise collaborations focused on exchanging data with countries that have more Covid-19 cases, which will allow Indian AI experts to create accurate and quick solutions to fight this war.
Vidur Mahajan, is head of R&D, Center for Advanced Research in Image, Neuroscience and Genomics.
The opinions expressed are personal.