How AI can help win the fight against Coronavirus

Nicole Junkermann, international entrepreneur and investor, and the founder of NJF Holdings explains how AI technology can help win the fight against Coronavirus and transform the future of healthcare.

Coronavirus has pushed healthcare systems to their limits and pushed researchers to rapidly search for solutions. Now is the time to turn to technology and ensure that cutting-edge research in artificial intelligence (AI), machine learning, and health informatics are part of our pandemic response.

From predictive care to precision health testing, many clinicians and hospitals are already using AI to improve day-to-day care. Health AI has become increasingly sophisticated and efficient, and a new wave of investment and research in the wake of the coronavirus crisis could spur even more innovation.

Numerous tech companies, universities, and researchers are stepping up to apply AI technology to pandemic response. Already, Microsoft, Google, and several small start-ups such as BlueDot and OWKIN are tapping into the immense power of combining human teams with machines in order to combat the pandemic.

“The solution to COVID-19 is not likely going to come from one person, one company or one country,” said Peter Lee, corporate vice president for microsoft healthcare. “This is a global issue, and it will be a global effort to solve it.”

The most successful interventions will come from human-machine collaboration – but we must take great care to implement AI technologies with a clear understanding of how they will interface with people working on the frontlines of the coronavirus crisis.

The Power of Human-Machine teams

More than 7,000 miles away from Wuhan, China, an AI warning system developed by Toronto start-up BlueDot was among the first in the world to identify the emerging risk from COVID-19. In a report by Forbes “How AI may prevent the next coronavirus outbreak”, BlueDot’s AI system constantly scans through 100,000 official and mass media sources in 65 languages each day in order to detect outbreaks in real-time. And on the last day of December 2019, the system alerted one of BlueDot’s human employees to a potential pneumonia-like outbreak in China’s Hubei province. 

That employee was able to recognise parallels to the 2002 SARS outbreak and pursue further modelling of the disease, which led BlueDot to publish the first scientific paper on COVID-19, accurately predicting its global spread.

“While diseases spread fast, knowledge can spread even faster,” said BlueDot in a blog post. The company argues that traditional disease surveillance, which relies primarily on people, takes a great deal of time and often results in public health officials missing relevant warnings or receiving crucial information when it’s too late.

Researchers are building AI systems to augment – not replace – human expertise and capabilities, allowing for more informed healthcare responses and decisions.

At Stanford University’s Institute for Human-Centered AI, researchers and clinicians are already developing AI-based methods to help hospitals manage the flood of COVID-19 patients. Dr Ron Li, clinical assistant professor at Stanford Medicine, is exploring how to use machine learning to identify patients who will need intensive care before the patient’s condition deteriorates. Li’s team is working to apply an existing machine learning model on patient deterioration to coronavirus patients. The goal is to roll this technology out allowing the decisions taken by hospital clinicians to be augmented by reliable data that is generated with AI.

“The benefit of having a machine learning model is that it learns very quickly. It can learn over thousands or hundreds of thousands of patients, whereas as a clinician I can only learn from the limited patient population I see,” said Li during Stanford’s virtual conference on COVID-19 and AI. “Also, it can do things at scale – some things that humans can’t do.”

Stanford professor Binbin Chen is using AI to help develop a COVID-19 vaccine. According to Stanford, Chen’s team “uses AI to examine fragments of SARS-CoV-2 to determine how they might apply to COVID-19 vaccines.” By combining immunology principles and machine learning tools, the team can predict immunogenic components of a virus that help scientists get closer to determining what components to include in that virus’s vaccine.

Microsoft is also pioneering human-machine teams and announced the launch of its “C3.ai Digital Transformation Institute,” which will bring together scientists, academics, and private companies to explore AI techniques to mitigate the spread of COVID-19.

“In these difficult times, we need – now more than ever – to join our forces with scholars, innovators, and industry experts to propose solutions to complex problems. I am convinced that digital, data science, and AI are a key answer,” said Gwenaëlle Avice-Huet, executive vice president of ENGIE, an energy company that is part of the new partnership.

AI technology to prepare for the next crisis

The application of AI tools reaches far beyond one virus. As we fight coronavirus, we must also look beyond the current crisis and recognise the great potential this technology has for the future of healthcare.

In the field of neuroscience, Google’s DeepMind Health is using machine learning to develop algorithms that mimic the human brain. DeepMind Health also created a “mobile medical assistant,” which helps doctors and nurses spot serious kidney conditions earlier and helps clinicians deliver better care to patients with acute kidney injuries or sepsis.

“Patient care can be improved, and healthcare costs reduced, through the use of digital tools,” said DeepMind. “Together, they form the foundation for a transformative advance in medicine, helping to move from reactive to preventative models of care.”

As technology improves and as investment increases, it becomes clear that AI has the potential to transform healthcare across the board. In order to tackle the biggest challenges facing medicine and public health, we must continue equipping researchers, data scientists, and clinicians with powerful AI tools, as well as improve our implementation of human-machine collaborations in the real-world. These powerful AI tools aren’t replacing human knowledge or decision-making, but rather giving healthcare professionals more information and models to tackle coronavirus. We must recognise the great potential of AI technology to improve not only our response to this pandemic, but also the future of healthcare in general.