COVID-19 and e-brain

Artificial intelligence or e-brain is a strategic riposte to COVID-19 and presently it can be defined as Machine learning, Natural language processing, and Computer vision applications to edify computer devices to consume big data-based models for pattern recognition, explanation, and prediction. Since the outbreak of COVID-19, there has been a hustle to use and explore AI, and other data analytic tools. USA declared AI/machine intelligence as a foremost bestowment to the recent outbreak and can be used to predict the seasonality pattern of COVID-19 that can right now help in stabilizing the financial markets of Asia.
The concrete and possible contributions of AI or machine intelligence against COVID-19 mainly encompass six areas i.e., early warnings/alerts, tracking & prediction, data dashboards, diagnosis and prognosis, treatments/cures, and lastly social control. Talking about the early warning, Canadian and U.S based AI models (Blue dot and Health Map), helped in predicting the pandemic, and at earliest they issued warnings before the announcement by WHO.
Operational researchers of ‘Bluedot’ had also promulgated and warned different cities about the global spread of the disease. In light of this, the fundamental nature of these activities required human interpretation that remains central in appraising its output. It is therefore rightly, stressed that human input from assorted disciplines is needed out of the blue for the optimal application of Artificial intelligence or e-brain. To track and predict the dynamics of COVID-19, AI plays its role, as clearly evident from the previous epidemics of the Zika virus (2015) for which a dynamic network was developed for its prediction. But some of the troubles which are faced during the accurate forecasting of a pandemic spread include deficient historical/unbiased data, big data harvested from social media handles, and the fact that COVID-19 pandemic differs from previous outbreaks. To tackle these hurdles with big data hubris and algorithm dynamics, the big social media platforms such as Facebook, and YouTube have started using Artificial intelligence more doggedly for content moderation including the removal of fake news circulated on social media handles.
The lockdown policy amidst the COVID-19 resulted in the diminution of human staff that ultimately led to error-prone content moderations. Hence it again illustrates the need for human input to apply Artificial intelligence strategically. Based on this, most of the forecasters preferred to use epidemiological models, like Metabiota, GLEAMviz, and Robert Koch Institutes’ epidemiological model. Hence, tracking and predicting the spread of COVID-19 will be a precious data input for public health authorities to plan, prepare, and manage this pandemic. This methodology of tracking of COVID-19 led to the emergence of an industry of data dashboards like (NextStrain, UpCode, John’s Hopkins’ JHU CSSE, HealthMap, and Microsoft Bing’s AI tracker) that envisage this pandemic and give us its global impression.
For the treatment and control of any medical insult, early diagnosis is the prime target; the same is the case with COVID-19. In this regard, Artificial intelligence may offer useful input, in particular with an image-based medical diagnosis like X-rays and CT scans that are all time available in the hospitals.
Studies have revealed, AI as accurate as humans, and also a time-saving contrivance for our frontline heroes (radiologists). Moreover, it is faster and cheaper than standard tests for COVID-19 (like PCR) and could serve as a surrogate for doctors when fast judgment or diagnosis is needed. From a lung CT scan, the AI is designed to swiftly identify lung lesions of possible COVID-19 patients which all provide a quantitative report to assist clinicians in making a fast judgment. While a manual interpretation of a CT scan can take up to 15 minutes, AI can finish reading the image in 10 seconds.
An AI called COVID-Net has been developed to diagnose COVID-19 in chest x-rays using data from patients with various lung conditions. In conclusion, the application of AI to diagnose COVID-19, and to make a prognosis of how patients may progress, has spurred much research effort but is not yet widely operational. After disease diagnosis, therapeutic/drug interventions press into service and AI was lauded for its potential to contribute to new drug discoveries even before the COVID-19 outbreak. In the case of COVID-19, several research labs and data centers are recruiting AI to hunt for drugs and vaccines against COVID-19.
The hope is that AI can accelerate both the processes of discovering new drugs as well as for repurposing existing drugs like Barcitinib, Remdesivir, Lopinavir, Arbidol, chloroquines. Knowing the above facts about AI, it has also conquered in serving society by scanning public places for people potentially infected, and by enforcing social distancing and lockdown measures. Thermal imaging by infrared cameras at airports and train stations is exercised to scan crowds for fever and sometimes used with a facial recognition system, which can locate the subject with higher body temperature. Larsen & Toubro (L&T), India’s biggest engineering conglomerate, is also using new technologies, artificial intelligence, and its digital platforms to support local authorities in 20 cities so that they can monitor and implement measures to combat the spread of COVID-19.
As Artificial intelligence or e-brain plays its trump card, there are some constraints like ‘Too Little and Too Much Data’ that have been detected and analyzed. Too little figures can result in biased data, therefore for COVID-19, there is a dire need for new training data, more diagnostic testing, and sharing of correct information with candour together with a more collaborative, and multidisciplinary approach for improving the knack of AI.
As I mentioned too much data as one of the constraints of AI, the proof is in front of our eyes, huge paraphernalia of news aired on media channels and social networks snowed under too much noisy and outlier data that ultimately disturbs the algorithms of AI. Being a researcher and doctor, I have come across the deluge of scientific papers and new data being generated every hour, and more than 100 scientific articles on the pandemic now appear daily putting a greater challenge to data analytic tools.
Bottomline: The wrath of the COVID-19 pandemic is compelling countries globally to use digital services for healthcare and monitoring, population screening, tracking the infection, allocating resources, and managing communication and responses. Surely this multifunctional broach will be a useful tool to diagnose, predict, and treat COVID-19 infections and will lend a hand in managing socio-economic impacts. Recuperating Artificial intelligence will be a worthwhile pursuit of dropping the fears caused by pandemics. Thus, the efficient Artificial intelligence needs high-quality input unbiased data because “it’s a case of garbage in, garbage out”. So, the creation of unbiased time series data for AI training is necessary. So, we must fight it with every available powerful tool like artificial intelligence, only with them, we will succeed in winning this global crisis.