The Covid-19 Open AI Consortium (COAI) intends to bring breakthrough medical discoveries and actionable findings to the fight against the Covid-19 pandemic.
COAI aims to increase collaborative research, to accelerate clinical development of effective treatments for Covid-19, and to share all of its findings with the global medical and scientific community. COAI will unite collaborators: academic institutions, researchers, data scientists and industrial partners, to fight the Covid-19 pandemic.
This will be the first of three interviews with principal leaders behind COAI.
Sanjay Budhdeo is a practicing physician. He holds Medical Sciences and Medical degrees from Oxford University and a Masters Degree from Cambridge University, as well as Membership of the Royal College of Physicians. Sanjay has research experience in neuroimaging, epidemiology and digital health. Prior to joining Owkin as a Partnership Manager, he was a Senior Associate at Boston Consulting Group, where he focused on data and digital in healthcare. He sits on the Patient Safety Committee at the Royal Society of Medicine and was previously a Specialist Advisor at the Care Quality Commission.
What was it that inspired you to join OWKIN?
When practicing as a doctor, I saw many patients who had conditions we couldn’t treat with medications, where there was only so much we could do. As a researcher, I was frustrated by the traditional approaches to analysis, at a time when there was access to ever more data. Trying to make the connection between fields that had evolved separately — such as epidemiology and imaging – proved really challenging. Machine learning was for me a way to connect the dots from my work as a researcher and a physician, being able to derive individual-level insights that could impact the diagnosis and treatment for the entire patient population.
You have research experience in both epidemiology and digital health. Could you share with us some of the previous projects that you have worked on?
In epidemiology, I worked on the UK’s 1946 birth cohort — a fascinating long-term study that has tracked subjects born in a single week over the course of their life. In one project, I looked at when these subjects started learning to sit, stand and walk, and saw that this was associated with their ability to perform more complicated tasks later in life. I also looked at whether into the reasons behind this association — were there differences in genetics or in brain structure? In digital health, my focus has been on interoperability — the connections between electronic medical records in hospitals that enable sharing of data about patients between hospitals. This is really important for direct clinical care, so a doctor has a complete idea of what’s happened to you before, but it’s also really important to enable to use of machine learning models in the clinical setting.
OWKIN is spearheading an AI-driven research collaboration called the COVID-19 Open AI Consortium (COAI). Could you describe what this project is?
COAI is Owkin’s response to the concerns we’ve heard from our partner clinical and academic institutions. It’s clear to us that there are important clinical questions that need to be answered for Covid-19 — for example, how can we identify patients at risk of severe disease? What are the potential treatments that could be trialled against COVID-19 infections? Our aim is to increase collaborative research and share all findings with the global medical and scientific community. COAI draws on the strengths of collaborators across the health and tech space — including universities, hospitals, startups and biopharma companies. We are creating specific research areas, and the first area we’ve announced is in cardiovascular complications in Covid-19 patients, with additional research areas going live soon.
One of the initial projects will be understanding cardiovascular complications. What type of insights are we hoping to gain from the COAI?
Our aim is to produce clinically useful information about the risk of acute cardiovascular complications from Covid-19 infections. We’re exploring this question from multiple angles, using different types of data across different countries. It’s great to work with internationally leading clinical researchers to get to the heart of these questions.
Prediction and characterization of immune responses is another aspect of COAI. What are some of the data points that you believe should be analyzed to fully understand why some humans are capable of building an immune response, while others require medical assistance?
Our body’s system of defence is amazingly complex and intricate. There are many types of cells involved in our immune response. Some of the cells directly combat foreign invaders. Other cells will produce pro-inflammatory chemicals called cytokines, which act as homing signals to target the immune response, and tagging specific cells for destruction. What we’re learning is that the balance of particular cytokines – including IFN1, IFN gamma and IL-10 – is very important in mediating this immune response. Machine learning can be very helpful to examine a very rich dataset containing the levels of many cytokines and other blood markers, and generate insights into what the key players are here, while taking into account the complex interplay between different factors.
Understanding how to treat patients in order to achieve the best patient outcome, is possibly one of the most important projects being undertaken by COAI. In your opinion, what are the first steps that need to be undertaken to understand this?
An important first step is risk stratification. We want to understand which patients are at the highest risk of having severe disease — including lung complications like acute respiratory distress syndrome, heart complications such as myocarditis, and other organ or system-specific sequelae. This risk stratification question is important for several reasons. First, as a doctor you might want to monitor a patient differently if you know they’re at higher risk of compilations. Second, as a hospital, you want to be able to predict the demand for intensive care facilities and plan according to that demand. Third, if you’re a researcher or biopharma company, you can include that subgroup of patients in trials, a treat them early to get an optimal response to your medication. In all of those cases, our ultimate aim is to improve patient outcomes
Can you explain why data science is so important for fighting COVID-19?
Data science, in its broadest sense, is at the heart of the fight against COVID-19. Important questions about the modelling of COVID-19 infection rates remain. We can use real-world patient data to identify drugs which could be usefully repurposed to treat COVID-19 patients. There is an incredible amount of information we are discovering about the virus which will help us to better design a vaccine. There is so much that we don’t know about the virus including how it affects people and we are learning more and more thanks to many varieties of data – biochemical, genetic, clinical, and from cellphones.
What do you believe are some of the insights that we can learn from AI analyzing this data?
For me, the sweetspot of AI is really in helping to derive conclusions at the level of the individual from population-level data. We can think about which patients might benefit from which therapies to combat COVID-19 infection, or help to predict which areas might become local hotspots for COVID-19 infection. There’s also a lot of activity in the discovery space, both in terms of potential medications, and for vaccine candidates. AI can really help us deliver novel biological insights much more quickly.
Who should be joining the COVID-19 Open AI Consortium project?
We’re speaking to a number of players within and outside of the healthcare space. This includes hospitals, universities and pharmaceutical companies, but also other start-ups, NGOs and policy organisations. We’re particularly excited to hear from clinicians who have gathered data and would like help with analysis.
Is there anything else that you would like to share about either the COAI project or COVID-19?
I’m really excited to share this initiative with you! If you want to collaborate, we’d be happy to discuss — get in touch at COAI@owkin.com
Thank you for the fantastic interview. Readers who wish to learn more, may read our article describing the COAI project.
The second interview in this series was with Dr. Stephen Weng, Principal Investigator.
The third interview in this series was with Folkert W. Asselbergs, Principal Investigator
You may also visit the Covid-19 Open AI Consortium website.
Intel AI Powered Virtual Assistant Mobilized to Assist Reopening of Military Museum
A Canadian museum is safely reopening from its pandemic closure with the help of a virtual
The Ontario Regiment Museum houses North America’s largest collection of operational military vehicles, many dating back to the 1940s. The collection allows the public to experience a piece of history, both at the museum and through the historical films in which the vehicles often appear.
At the start of the pandemic in early 2020, CloudConstable began working with the museum to design Master Corporal Lana as an AI virtual assistant who would greet
Before Lana’s deployment, COVID-19 closed the museum to the public. But with over 120 military vehicles that need constant servicing and driving, the museum needed its volunteers to continue their essential maintenance and operations work at the site.
“The Ontario Regiment Museum is one of the few museums in the world with such a large and diverse collection of operating military vehicles, which help people experience history in a very real way. Regular maintenance is crucial, even during the worst of the pandemic, which is why we turned to CloudConstable and Intel to help build an autonomous solution,” said Jeremy Blowers, executive director of the Ontario Regiment Museum.
CloudConstable relied on the Intel RealSense team’s insight that Lana’s existing and unique capabilities — already built on the Intel RealSense Depth Camera and using the Intel® Distribution of OpenVINO™ toolkit for accelerated machine vision inferences — could be extended for a more comprehensive and safer COVID-19 screening solution. Adding an Intel® NUC 9 Pro with Intel Active Management Technology, as part of the Intel vPro® platform, the team reworked Lana to take temperatures via thermal scans and ask a series of questions to assess COVID-19 risk and exposure. Since June, Lana has provided an enhanced, fully automated and touchless screening process so volunteers can continue to do their important work with the vehicles.
“Intel RealSense technology is used to develop products that enrich people’s lives by enabling machines and devices to perceive the world in 3D. CloudConstable leverages Intel’s technology to help create a state-of-the-art natural voice and vision interface with touchless, self-service COVID-19 screening,” said Joel Hagberg, head of product management and marketing, Intel’s RealSense group.
With the Ontario Regiment Museum now preparing to reopen to the public, CloudConstable, along with Intel, is now working to bring the new COVID-19 protection capabilities into the original concept for Lana as a greeter for visitors. Lana will greet visitors, provide contactless check-in, scan temperatures and ensure the museum adheres to visitor limits and other COVID-19 health protection protocols. Eventually, she’ll even thank them for coming and help visitors keep in touch with all the latest activities at the museum.
U.S. National Institutes of Health Turns to AI for Fight Against COVID-19
The National Institutes of Health has turned to artificial intelligence (AI) for diagnosis, treatment, and monitoring of COVID-19 through the creation of the Medical Imaging and Data Resource Center (MIDRC).
What is the MIDRC?
The MIDRC consists of multiple institutions working together, led by the National Institute of Biomedical Imaging and Bioengineering (NIBIB), which is part of NIH. The collaboration aims to develop new technologies that will help physicians detect the virus early and create personalized therapies for patients.
Bruce J. Tromberg, Ph.D., is Director of the NIBIB.
“This program is particularly exciting because it will give us new ways to rapidly turn scientific findings into practical imaging tools that benefit COVID-19 patients,” Tromberg said. “It unites leaders in medical imaging and artificial intelligence from academia, professional societies, industry, and government to take on this important challenge.”
One of the ways experts assess the severity of a COVID-19 case is by looking at the features of infected lungs and hearts on medical images. This can also help predict how a patient will respond to treatment and improve the overall outcomes.
The big challenge surrounding this method is that it’s difficult to rapidly and accurately identify these signatures and evaluate the information, especially when there are other clinical symptoms and tests.
Machine Learning Algorithms
The MIDRC aims to develop and implement new and effective diagnostics. One of these will be machine learning algorithms, which solve some of those issues. Machine learning algorithms can help physicians optimize treatment after accurately and rapidly assessing the disease.
Guoying Liu, Ph.D., is the NIBIB scientific program lead on the new approach.
“This effort will gather a large repository of COVID-19 chest images,” Liu explained, “allowing researchers to evaluate both lung and cardiac tissue data, ask critical research questions, and develop predictive COVID-19 imagining signatures that can be delivered to healthcare providers.”
Krishna Kandarpa, M.D., Ph.D., is director of research sciences and strategic directions at NIBIB.
“This major initiative responds to the international imagining community’s expressed unmet need for a secure technological network to enable the development and ethical application of artificial intelligence to make the best medical decisions for COVID-19 patients,” Kandarpa said. “Eventually, the approaches developed could benefit other conditions as well.”
Some of the other major names on this project include Maryellen L. Giger, Ph.D., who is taking the lead. She is Professor of Radiology, Committee on Medical Physics at the University of Chicago. Co-investigators include Etta Pisano, MD, and Michael Tikin, MS, from the American College of Radiology (ACR), Curtis Langlotz, MD, Ph.D., and Adam Flanders, MD, from the Radiological Society of North America (RSNA), and Paul Kinahan, Ph.D., from the American Association of Physicists in Medicine (AAPM).
Through collaborations between the ACR, RSNA, and AAPM, the MIDRC will work toward rapid collection, analysis, and dissemination of imagining and other clinical data.
While many believe that the adoption of AI for pandemic-related solutions is long overdue, the National Institutes of Health’s new MIDRC is a step in that direction. It is only a matter of time before AI plays a major role in the detection, response, and eventual prevention of global pandemic causing viruses.
Supply Chains after Covid-19: How Autonomous Solutions are Changing the Game
Early measures by the material handling industry to curb the coronavirus pandemic saw border and plant closures all over the world. While for machine and vehicle manufacturers in eastern Europe and China production is in full swing again, the rest of Europe, North America and other western countries are struggling to get back to their pre-Covid-19 production strength.
Restrictions in freight transport across Europe are still very noticeable and are causing bottlenecks in supply chains. The strict stay-at-home-orders imposed in most European countries to contain the pandemic have had and are having a major impact on industrial production as the personnel are simply missing on site.
Security measures like keeping minimum distance or wearing masks are proving to be an organizational challenge for many production facilities around the world. In order to be able to comply with the safety requirements, in many premises only half of the workforce is allowed on-site, or the production line is divided into shifts. This in turn is restricting the flow of goods. Even when components exist, they stockpile, and cannot be integrated due to a lack of staff or time for those on reduced activity.
After the crisis, the industry will face new challenges. There is already speculation about a trend moving away from globalization towards regionalization. It is not necessarily the sourcing of production that could be affected by a possible regionalization, but rather warehouse management. Regardless of restricted supply chains, access to material inventory is essential for every production line. As a lesson-learned from the Covid-19 crisis, we could see a move from large central warehouses to smaller regional warehouses.
The automotive industry, for instance, was hit hard by supply shortages due to restrictions stemming from the pandemic. Automotive OEMs and their suppliers have long and complex supply chains with many steps in the production process. After the experienced bottlenecks, their follow-up measures might include a diversification of suppliers, as well as the decentralization of inventories in order to maintain agility in case of a crisis.
This presupposes digitalization of warehouse management: if existing stockpiling data is used rationally, transparency in the entire supply chain can easily be created. This would mean everyone involved could use existing data to optimize their processes. This requires intelligent warehouse management systems (WMS) and intelligent solutions for material handling to work hand-in-hand.
Automated guided vehicles (AGVs) are not a novelty in in-house material handling processes but their evolution could hold the key to the industry’s future. Since their introduction, technologies in autonomous vehicles have developed rapidly, enabling the transport of people in complex environments. Bringing this level of intelligence to industrial vehicles hails the next era of logistics automation: new AGV generations accessing complex outdoor environments are a real game changer and could potentially become more attractive after the Covid-19 crisis. As these vehicles become increasingly deployed in dynamic environments without infrastructure, these technologies have quickly migrated from manufacturing applications to supporting warehousing for manufacturing and distribution.
The process automation in supply chains – part of the so-called Industry 4.0 – will play a significant role. It could allow companies to keep or even reduce overall logistics operational costs, and eventually maintain a minimal operational flow even in times of crisis.
Rethinking the industrial supply chain: intelligence is key
The autonomous tow tractor TractEasy by autonomous technology leader EasyMile is a perfect example of this new generation. It masters the automation of outdoor and intralogistics processes on factory premises, logistics centers and airports. The company is currently demonstrating the maturity of these autonomous tow tractors at automotive supplier Peugeot Société Anonyme (PSA)’s manufacturing plant in Sochaux, France. Operated by GEODIS, PSA is using the tractor to find opportunities to optimize costs in the flows on its site.
The impact of the ongoing crisis has revealed the fragility of existing supply chains. Companies are reassessing large and complex procurement networks. Ultimately, the Covid -19 pandemic is putting supply chains to the test, but global supply chains should be prepared for crises as part of risk management anyway. The sheer number of natural disasters in recent years has meant that the international supply chains have been repeatedly overhauled. From this point of view, the Covid-19 crisis is an example of unpredictability that supply chains have to adapt to in order to develop.
What is certain is that the industry is on an upward trend toward more sustainable and stable industrial ecosystems. Automation is a concept that will play a major role in these future considerations, from manufacturers to logistic operators across the globe.
- Dimitris Vassos, CEO, Co-founder, and Chief Architect of Omilia – Interview Series
- Human Brain’s Light Processing Ability Could Lead to Better Robotic Sensing
- Game Developers Look To Voice AI For New Creative Opportunities
- Udacity Launches RPA Developer Nanodegree Program in Conjunction with UiPath
- AI Used To Identify Gene Activation Sequences and Find Disease-Causing Genes