Artificial Intelligence vs Covid-19
How AI has reinforced the medical workforce to tackle Covid-19!
Each one of us is well aware of Covid-19, the pandemic that we have been trying to outrun since the past two years. And almost each one of us would agree to the fact that our healthcare system wasn’t ready for such an outbreak. The pandemic has highlighted several alarming gaps in our healthcare system, some of which were known even before the pandemic itself, and in order to fill these gaps, we don’t have enough medical workforce. Therefore, the medical organizations have shifted their attention to technology, and more specifically, Artificial Intelligence (AI).
In this blog, we will together explore some of the latest endeavors made by the AI community of researchers and developers in order to alleviate these gaps, and ensure a better, safer and more affordable healthcare for the wider populace. But before we dive further, let me highlight one very important point. The audience intended for this blog is each and every curious person who would like to know more about how AI has aided the medical workforce in these hard times of Covid-19, and knowledge of AI is not required whatsoever. I will be mentioning additional resources wherever possible for those of you who would like to know more about the concepts in-depth, and for those who have heard the term “AI” for the first time, let me put-in a very simple definition of AI for your reference (Borrowed from Britannica).
Artificial Intelligence is defined as the ability of a digital computer or computer-controlled robot to perform tasks commonly associated with intelligent beings.
Now, without any further ado, let’s go through a quick outline of the various efforts that we will be discussing in this blog.
- AI to Diagnose Covid Within Minutes
- Moderna’s Covid-19 Vaccine
- Computational Predictions of Protein Structures associated with Covid-19
- AI Project for NHS Supply Chain
- Greece Using ML Algorithm for Covid Testing of Travellers
- Covid-19 Assessment Bot
- AI that Predicts Covid-19 Patient Deterioration
- NHS Tackling Covid-19 Backlog with AI and Robots
- ML Predicts which Covid Patients will Recover
AI to Diagnose Covid Within Minutes
The researchers at the University of the West of Scotland have developed an AI program, which when coupled with X-rays can diagnose Covid within a few minutes, as opposed to a standard PCR test which can take around 2 hours, and it’s 98% accurate! The program uses the X-ray technology, comparing scans to a database of around 3000 images belonging to patients with Covid-19, healthy individuals, and people with viral pneumonia, and then it utilizes something known as a Convolutional Neural Network (CNN) to make a diagnosis. To know more about this, read on!
Moderna’s Covid-19 Vaccine
US pharmaceutical and biotechnology company Moderna has become a household name thanks to its Covid-19 vaccine, but when it was formed in 2010, it was just a biotech startup born in the Amazon Web Services (AWS) cloud. Moderna’s digital infrastructure leverages workflow automation, data capture, and AI to accelerate processes and deliver insight to it’s scientists, and additionally, Moderna parallelizes drug development processes that are typically staged sequentially. And by virtue of their infrastructure, they were able to move from sequence to dosing in just 65 days, a process that normally takes several years. To know more about this, read on!
Computational Predictions of Protein Structures associated with Covid-19
DeepMind opened access to AlphaFold, a model that finds the shapes of proteins, and to its output so far — a potential cornucopia for biomedical research. It also released the structure predictions of several under-studied proteins associated with SARS-CoV-2, the virus that causes Covid-19. The company published research that describes how to use AlphaFold to find the shapes of both general and human-specific proteins. These structure predictions have not been experimentally verified, but they may contribute to the scientific community’s interrogation of how the virus functions, and serve as a hypothesis generation platform for future experimental work in developing therapeutics. To know more about this, read on!
AI Project for NHS Supply Chain
A collaboration between Sheffield University and AI healthcare marketplace Vamstar is aiming to help the NHS to manage its supply chain more efficiently. The researchers say the new platform will help the NHS order essential supplies such as personal protective equipment (PPE) from low-risk suppliers, and will ease future shortages like those experienced in the first wave of the pandemic. Additionally, the platform will allow NHS buyers to evaluate the credibility, and capability of suppliers to fulfill their order. To know more about this, read on!
Greece Using ML Algorithm for Covid Testing of Travellers
Greece, like many other countries, lacked the capacity to test all the travellers, particularly those not displaying symptoms. One option was to test a sample of visitors, but Greece opted to trial an approach rooted in AI. With the help of researchers from the University of Southern California, the government launched a system that uses a ML algorithm to determine which travellers entering the country should be tested for Covid-19, which was found to be more effective at identifying asymptomatic people than was random testing or testing based on a traveller’s country of origin. According to an analysis, during the peak tourist season, the system detected two to four times more infected travellers than did random testing. To know more about this, read on!
Covid-19 Assessment Bot
The U.S. Centers for Disease Control and Prevention (CDC) released a Covid-19 assessment bot that can quickly assess the symptoms and risk factors for people worried about infection, provide information and suggest a next course of action such as contacting a medical provider or, for those who do not need in-person medical care, managing the illness safely at home. The bot, which utilizes Microsoft’s Healthcare Bot service, is available on the CDC website. It is one of the solutions that uses AI to help the CDC and other front-line organizations respond to the Covid-19 related inquiries, freeing up doctors, nurses, administrators and other healthcare professionals to provide critical care to those who need it. To know more about this, read on!
AI that Predicts Covid-19 Patient Deterioration
A research team from New York University, Center for Data Science have developed an AI system that could potentially help to predict the deterioration of emergency room Covid-19 patients. The team developed the AI system using a dataset of 19,957 chest X-ray exams collected from 4,722 patients who tested positive for Covid-19. The system leverages Deep Convolutional Neural Networks to perform risk evaluation from chest X-ray images. The AI also learns from routinely collected clinical variables using a Gradient Boosting model, and combining the predictions from both the systems, they predicted each patient’s overall risk of deterioration over varying time horizons, ranging from 24 to 96 hours. To know more about this, read on!
NHS Tackling Covid-19 Backlog with AI and Robots
The Covid-19 pandemic has left many routine NHS services facing huge backlogs, and in order to tackle these lengthy waiting lists, NHS England has announced £160 million in funding. Major plans include implementing systems that use AI to decide who is treated first, giving an option to GP patients to be assessed by AI, with chat-bots able to refer people to see a physiotherapist or mental health therapist, and issuing robots to elderly patients, with remote controlled technology used, so consultants in hospital can make visual assessments of vulnerable patients while they remain at home. To know more about this, read on!
ML Predicts which Covid Patients will Recover
The researchers have developed a new tool that uses ML to better predict health outcomes for hospitalized Covid patients, and help physicians make more informed treatment decisions. Developed by Charity-University Medicine in Berlin, this tool can estimate how well an infected person will fare based on a blood sample. The researchers conclude that blood protein tests, if validated in larger cohorts, may be useful in both identifying patients with the highest mortality risk, as well as for testing whether a given treatment changes the projected trajectory of an individual patient. To know more about this, read on!
A little about ME 👋
You can safely skip this section, if you have no interest in knowing the author, or you already know me. I promise that there is no hidden treasure in this section 😆.
I am a Machine Learning and Deep Learning Enthusiast, and this is my third piece of content based on the same. If you like it, do put your hands together 👏 and if you would like to read further articles based on Machine Learning and Deep Learning #StayTuned.
