The White House’s Office of Science and Technology Policy is asking researchers to analyze thousands of scholarly articles with artificial intelligence (AI) technology. All of the articles, which numbers around 29,000, could provide answers to questions about the coronavirus. About 13,000 of the articles in the database are in their entirety and are machine-readable. As for the other 16,000 articles, the database has partial text and summaries.
Over the last few days, U.S. government officials have worked with American tech companies and research institutions to secure legal permission to make the coronavirus papers available.
The open data set is known as the COVID-19 Open Research Dataset, or CORD-19. It will constantly add new information into one centralized hub, providing researchers and others with a single place to access it.
The partnership announced by the White House includes the Chan Zuckerberg Initiative, Microsoft Research, the Allen Institute for Artificial Intelligence, the National Institute of Health’s National Library of Medicine, Georgetown University’s Center for Security and Emerging Technology, Cold Spring Harbor Laboratory and the Kaggle AI platform, which is owned by Google.
According to U.S. CTO Michael Kratsios, the CORD-19 dataset is the “most extensive collection of machine readable coronavirus literature to date.”
The National Academy of Sciences, Engineering, and Medicine worked with the World Health Organization (WHO) to develop “high priority” questions. These questions revolve around the relationship between coronavirus and genetics, incubation, treatment, symptoms, and prevention.
Some of the research present in the database is pre-publication research pulled from resources such as medRxiv and bioRxiv. These are open access archives.
Cori Bargmann is the Chan Zuckerberg Initiative Head of Science.
“Sharing vital information across scientific and medical communities is key to accelerating our ability to respond to the coronavirus pandemic,” Bargmann said.
According to the Call to Action released by the White House, the database collection was developed through the use of Microsoft’s web-scale literature curation tools, which identified and brought together different scientific work from around the globe. The Chan Zuckerberg Initiative provided access to pre-publication content, the National Library of Medicine provided access to literature content, and the Allen AI team formatted the content so that it could be analyzed.
Dr. Eric Horvitz is Chief Scientific Officer at Microsoft.
“It’s all-hands on deck as we face the COVID-19 pandemic,” said Horvitz. “We need to come together as companies, governments, and scientists and work to bring our best technologies to bear across biomedicine, epidemiology, AI, and other sciences. The COVID-19 literature resource and challenge will stimulate efforts that can accelerate the path to solutions on COVID-19.”
Many are hoping that this approach works and provides a new way to utilize AI technology and machine learning in the future. One of those people is Dr. Dewey Murdick, Director of Data Science at Georgetown University’s Center for Security and Emerging Technology. Dr. Murdick helped coordinate the project.
“This valuable new resource is the fruit of unselfish collaboration and now offers the opportunity to find answers to important questions about COVID-19,” Dr. Murdick said. “Once the crisis has passed, we hope this project will inspire new ways to use machine learning to advance scientific research.”
If this project succeeds in proving much-needed answers about coronavirus, it could be used as a model in the future. AI technology is a powerful tool, and it can analyze the results of experts and institutions throughout the globe much faster than humans. This means a faster response time whenever a pandemic or other crisis breaks out, which could save many lives and prevent economic turmoil.
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.
Stefano Pacifico, and David Heeger, Co-Founders of Epistemic AI – Interview Series
Epistemic AI employs state-of-the-art Natural Language Processing (NLP), machine learning and deep learning algorithms to map relations among a growing body of biomedical knowledge, from multiple public and private sources, including text documents and databases. Through a process of Knowledge Mapping, users’ work interactively with the platform to map and understand subsets of biomedical knowledge, which reveals concepts and relationships and that are otherwise missed with traditional search.
We interviewed both Co-Founders of Epistemic AI to discuss these latest advances.
Stefano Pacifico comes from 10+ years in applied AI and NLP development. Formerly at Bloomberg, where he spent 7 years, and was at Elemental Cognition before starting Epistemic.
David Heeger is a Silver Professor of data science and neuroscience at NYU, and has spent his career bridging computer science, AI and bioscience. He is a member of the National Academy of Sciences. As founders they bring together the expertise of building applied large-scale AI and NLP systems for understanding large collections of knowledge, with expertise in computational biology and biomedical science from years of research in the area.
What is it that introduced and attracted you to AI and Natural Language Processing (NLP)?
Stefano Pacifico: When I was in college in Rome, and AI was not popular at all (in fact it was very fringe), I asked my then advisor what specialization I should have taken among those available. He said: “If you want to make money, Software Engineering and Databases, but if you want to be weird but very advanced, then choose Artificial Intelligence”. I was sold at “weird”. I then started working on knowledge representation and reasoning to study how autonomous agents could play soccer or rescue people. Then two realizations made me fall in love with NLP: first, autonomous agents might have to communicate with natural language among themselves! Second, building formal knowledge bases by hand is hard, while natural language (in text) already provides the largest knowledge base of all. I know today these might seem obvious observations, but they were not as mainstream before.
What was the inspiration behind launching Epistemic AI?
Stefano Pacifico: I am going to make a bold claim. Nobody today has adequate tooling to understand and connect the knowledge present in large, ever-growing collections of documents and data. I had previously worked on that problem in the world of finance. Think of news, financial statements, pricing data, corporate actions, filings etc. I found that problem intoxicating. And of course, it’s a difficult problem; and an important one! When I met my co-founder, Dr. David Heeger, we spent quite a bit of time evaluating startup opportunities in the biomedical industry. When we realized the sheer volume of information generated in this field, it’s as if everything fell in its right place. Biomedical researchers struggle with information overload, while attempting to grapple with the vast and rapidly expanding base of biomedical knowledge, including documents (e.g., papers, patents, clinical trials) and databases (e.g., genes, proteins, pathways, drugs, diseases, medical terms). This is a major pain point for researchers and, with no appropriate solution available, they are forced to use basic search tools (PubMed and Google Scholar) and explore manually-curated databases. These tools are suitable for finding documents matching keywords (e.g., a single gene or a published journal paper), but not for acquiring comprehensive knowledge about a topic area or subdomain (e.g., COVID-19), or for interpreting the results of high throughput biology experiments, such as gene sequencing, protein expression, or screening chemical compounds. We started Epistemic AI with the idea to address this problem with a platform that allows them to iteratively:
- Shorten the time to gather information and build comprehensive knowledge maps
- Surface cross-disciplinary information that can be otherwise difficult to find (real discoveries often come from looking into the white space between disciplines);
- Identify causal hypotheses by finding paths and missing links in your knowledge map.
What are some of both the public and private sources that are used to map these relations?
Stefano Pacifico: At this time, we are ingesting all the publicly available sources that we can get our hands on, including Pubmed and clinicaltrials.gov. We ingest databases of genes, drugs, diseases and their interactions. We also include private data sources for select clients, but we are not at liberty to disclose any details yet.
What type of machine learning technologies are used for the knowledge mapping?
Stefano Pacifico: One of the deeply held beliefs at Epistemic AI is that zealotry is not helpful for building products. Building an architecture integrating several machine learning techniques was a decision made early on, and those range from Knowledge Representation to Transformer models, through graph embeddings, but include also simpler models like regressions and random forests. Each component is as simple as it needs to be, but no simpler. While we believe to have already built NLP components that are state-of-the-art for certain tasks, we don’t shy away from simpler baseline models when possible.
Can you name some of the companies, non-profits, or academic institutions that are using the Epistemic platform?
Stefano Pacifico: While I’d love to, we have not agreed with our users to do so. I can say that we had people signing up from very high-profile institutions in all three segments (companies, non-profits, and academic institutions). Additionally, we intend to keep the platform free for academic/non-profit purposes.
How does Epistemic assist researchers in Identifying central nervous system (CNS) and other disease-specific biomarkers?
Dr. David Heeger: Neuroscience is a very highly interdisciplinary field including molecular and cellular biology and genomics, but also psychology, chemistry, and principles of physics, engineering, and mathematics. It’s so broad that nobody can be an expert at all of it. Researchers at academic institutions and pharma/biotech companies are forced to specialize. But we know that the important insights are interdisciplinary, combining knowledge from the sub-specialties. The AI-powered software platform that we’re building enables everyone to be much more interdisciplinary, to see the connections between their individual subarea of expertise and other topics, and to identify new hypotheses. This is especially important in neuroscience because it is such a highly interdisciplinary field to begin with. The function and dysfunction of the human brain is the most difficult problem that science has ever faced. We are on a mission to change the way that biomedical scientists work and even how they think.
Epistemic also enables the discovery of genetic mechanisms of CNS disorders. Can you walk us through how this works?
Dr. David Heeger: Most neurological diseases, psychiatric illnesses, and developmental disorders do not have a simple explanation in terms of genetic differences. There are a handful of syndromic disorders for which a specific mutation is known to cause the disorder. But that’s not typically the case. There are hundreds of genetic differences, for example, that have been associated with autism spectrum disorders (ASD). There is some understanding for some of these genes about the functions they serve in terms of basic biology. For example, some of the genes associated with ASD hold synapses together in the brain (note, however, that the same genes typically perform different functions in other organ systems in the body). But there’s very little understanding about how these genetic differences can explain the complex suite of behavioral differences exhibited by individuals with ASD. To make matters worse, two individuals with the same genetic difference may have completely different outcomes, one diagnosed with ASD and the other, not. And two individuals with completely different genetic profiles may have the same outcome with very similar behavioral deficits. To understand all this requires making the connection from genomics and molecular biology to cellular neuroscience (how do the genetic differences cause individual neurons to function differently) and then to systems neuroscience (how do those differences in cellular function cause networks of large numbers of interconnected neurons to function differently) and then to psychology (how do those differences in neural network function cause differences in cognition, emotion, and behavior). And all of this needs to be understood from a developmental perspective. A genetic difference may cause a deficit in a particular aspect of neural function. But the brain doesn’t just sit there and take it. Brains are highly adaptive. If there’s a missing or broken mechanism then the brain will develop differently to compensate as much as possible. This compensation might be molecular, for example, upregulating another synaptic receptor to replace the function of a broken synaptic receptor. Or the compensation might be behavioral. The end result depends not only on the initial genetic difference but also on the various attempts to compensate relying on other molecular, cellular, circuit, systems, and behavioral mechanisms.
No individual has the knowledge to understand all this. We all need help. The AI-powered software platform that we’re building enables everyone to collect and link all the relevant biomedical knowledge, to see the connections and to identify new hypotheses.
How are biopharma and academic institutions using Epistemic to tackle the COVID-19 challenge?
Stefano Pacifico: We have released a public version of our platform that includes COVID specific datasets and is freely accessible to anyone doing research on COVID-19. It is available at https://covid.epistemic.ai
What are some of the other diseases or genetic issues that Epistemic have been used for?
Stefano Pacifico: We have collaborated with autism researchers and are most recently putting together a new research effort for Cystic Fibrosis. But we are happy to collaborate with any other researchers or institutions that might need help with their research.
Is there anything else that you would like to share about Epistemic?
Stefano Pacifico: We are building a movement of people that want to change the way biomedical researchers work and think. We sincerely hope that many of your readers will want to join us!
Thank you both for taking the time to answer our questions. Readers who wish to learn more should visit Epistemic AI.
- Matt Carlson, VP Business Development at WiBotic – Interview Series
- U.S. National Institutes of Health Turns to AI for Fight Against COVID-19
- WiBotic Receives Industry-First FCC Approval for High Power Wireless Charging of Robots
- AI Browser Tools Aim To Recognize Deepfakes and Other Fake Media
- Dave Ryan, General Manager, Health & Life Sciences Business at Intel – Interview Series