Last Thursday (9 April), 40 hospitals under the University of Pittsburgh Medical Center (UPMC) became the first American healthcare institutions to be part of an international treatment trial called REMAP-COVID19 which aimed to find an effective intervention for the ongoing coronavirus pandemic. On top of the US, the trial also enrolled patients with moderate to severe symptoms from Europe, Australia and New Zealand.
Recruited patients will continue to receive care at wherever they have been admitted to but about 12.5% of them will be given placebo at the beginning of the trial. The rest will be randomly selected to various therapies ranging from antibiotics, antivirals, steroids or medications that regulate one’s immune system. The data will be fed into a worldwide machine learning system, which integrates with UPMC’s electronic health records to examine, in a non-stopping manner, which combination of therapies will lead to the best outcome.
Many small AI initiatives
Since Covid-19 has no known cure, researchers keen on finding one have to start from scratch. Traditionally, developing a new drug is time-consuming and costly because they have been tested broadly and repeatedly to ascertain its safety and efficacy. Often, by the time a plausible solution is found, the viral outbreak has already moved on. As the number of infected individuals mount, healthcare systems are under tremendous pressure to ensure there’s enough beds, ventilators, protective gears and staff to prevent collapse.
Thus, in the time of a pandemic, it’s usually a trade-off between scrambling through what’s readily available or waiting for clinical trials to be completed. As of now, there are over 500 listed, Covid-19 related clinical trials for treatments and vaccines. In order to be ahead of everyone else as well as time, some, like the one mentioned above, believes they have to get hold onto an accelerator known as artificial intelligence (AI).
While AI may have sped up the search for a pandemic cure, it may also have given rise to many small initiatives and instigated unnecessary competition among them. As Tedros Adhanom, Director-General of the World Health Organization (WHO) said in a press briefing back in March, “multiple small trials with different methodologies may not give us the clear, strong evidence we need about which treatments help to save lives”.
WHO subsequently launched a multi-country clinical trial – called “Solidarity” – to test four drug regimens including antimalarial drug – Chloroquine/ Hydroxychloroquine; experimental antiviral drug – Remdesivir, and a combination of two HIV drugs as the agency endorses “researchers around the world to come together” and “systematically evaluate experimental therapeutics”.
Searching for coronavirus treatment is not a lone race
Indeed, there’s still a lot to learn about Covid-19. AI will only be great tool if it can get hold onto real-time and insightful data and this can never be a lone effort. It appears that given the scale of the pandemic, more people are willing to share their data and resources. As early as 11 January, a team from Shanghai’s Fudan University who sequenced the DNA of coronavirus had shared the genome on a free online database. Subsequently, others joined in and there are now over 250 of the sequences being found on GenBank.
On 16 March, researchers and leaders from the Allen Institute for AI (Artificial Intelligence); Chan Zuckerberg Initiative; Georgetown University’s Center for Security and Emerging Technology; Microsoft and the National Library of Medicine at the National Institutes of Health launched the COVID-19 Open Research Dataset (CORD-19). The dataset comes with more than 29,000 published or on preprint server scientific articles, all of which come in a format that is easily digest by computers. This is to facilitate the work of fellow AI experts, in hope that they will develop new solutions or techniques to battle against the ongoing pandemic or other related diseases.
On 20 March, close to 80 American and Chinese scientists and doctors had a video-conference together to share their thoughts and experiences in combating Covid-19. When the US knew about the “convalescent plasma” (i.e., blood plasma obtained from those who have recovered from Covid-19) trial in China may help in preventing the worsening of symptoms in patients, the US Food and Drug Administration (FDA) immediately approved similar trial to take place in the country.
Nevertheless, some experts warned that one should not hold out too much hope on any of these trials until a real solution has been developed. Sometimes, disproportionate media portrayal and inappropriate communications from some countries’ leadership may lead the public to think that there is a definite cure out there waiting to be uncovered. Such false positivity is aggravated by the society’s desperate hope in bringing a closure to the entire pandemic. Most of us need to recognize that while finding a Covid-19 treatment may not be a lone race, it will also be a long race.