Show Posts

This section allows you to view all posts made by this member. Note that you can only see posts made in areas you currently have access to.

Messages - Md. Sumon-ul Islam

Pages: [1] 2 3
It's no secret that hospitals are at the epicenter of the COVID-19 crisis. Every day, highly infectious patients stream into medical facilities and threaten to infect healthcare workers and other patients. Healthcare experts and hospitals are fighting back by turning to artificial intelligence (AI) and the Internet of Things (IoT) to aid in the battle.

"AI can help in various ways," observes Eyal Zimlichman, deputy general director, chief medical officer, and chief innovation officer at Sheba Medical Center in Tel Hashomer, Israel. "AI tools will help us gain quicker insights into treatment protocols, patient assessment, and prediction of changes in the clinical situations. Furthermore, AI can help gain insights on an epidemiological level."

Chakri Toleti, founder and CEO of, an Orlando, FL, company that has developed an AI platform for hospitals, says the technology can reduce the risk for staff and the public. "AI-powered thermal entry sensors automate temperature screenings of people entering a healthcare facility. It identifies persons with a fever."

AI is the New Medicine
Hospitals and healthcare experts on the front lines of the COVID-19 pandemic increasingly are turning to machine learning, deep learning, and other AI methods to identify patterns, trends, and risks—and take steps to battle the virus. "Information regarding patient movement in the community might allow us to predict outbreaks locally and adjust policy accordingly," Zimlichman says.

For example, the Seattle, WA-based Allen Institute for Artificial Intelligence (AI2) has developed the Semantic Scholar Project, which uses natural language processing to sort through social media data and scholarly papers in order to spot patterns that might escape human detection. Others are looking to tap smartphone location data to gain insights.

At hospitals, AI is helping staff make more informed decisions. AI can generate prediction models that show the most effective clinical pathways for highly acute conditions, such as coronavirus. "This will help us better utilize resources, such as ICU beds and ventilators, as well as improve patient outcomes," Zimlichman says.

Medical facilities are also putting AI to work in other, often more direct, ways. At Tampa General Hospital in Florida, for example, anyone entering one of the facility's six entrances is screened using an AI-based temperature detection solution that incorporates image scanning and thermal inferencing. The solution recognizes behavioral patterns and identifies people with a fever; medical staff can then intervene immediately.

The system, developed by, reduces the need for manual screening, freeing up medical staff to spend more time tending to critical functions of triage and care delivery, Toleti says. The platform uses a sensor-fusion stack that runs specialized AI algorithms and neural networks. Once it detects abnormal readings, it sends notifications to care team members so an appropriate intervention can occur.

Playing It Safe
Another facility on the front lines of AI is Sheba Medical Center. It has incorporated several IoT and AI functions to aid in decision-making, patient quality, and overall safety. For example, "With the COVID-19 pandemic, we are using AI-based monitors that continuously track our COVID-19 patients and use AI-based alerts to predict imminent clinical deterioration," Zimlichman says.

The hospital uses a system from Woburn, MA-based EarlySense Ltd. that relies on sensors, including one in a patient's mattress, to identify possible patient problems in its 40-bed intensive care unit (ICU). Software applies machine learning to filter data and determine when a patient is likely to experience respiratory failure or sepsis within the next six to eight hours. The facility also uses an AI-powered control tower from CLEW Medical to better manage the ICU.

As medical experts take aim at COVID-19, other AI-based technologies are emerging. Rob Mesirow, U.S. Connected Solutions/IoT Practice leader at business and technology consulting firm PwC, says image recognition used with AI can aid in hand-washing or scrubbing and other critical tasks, though medical facilities, restaurants, and others that use this technology must be aware of privacy concerns. "The right systems can dramatically improve behavior and compliance," he says.

Despite remarkable advances in AI—and the potential benefits for battling a pandemic such as COVID-19—not everyone is entirely sold on the concept. Some experts argue that the technology is relatively new, and not all AI systems are ready for primetime use. For instance, some argue that thermal detection systems aren't accurate and dependable.

Nevertheless, Zimlichman believes that AI, along with the IoT and other digital technologies, will revolutionize medical care and the battle against COVID-19. "AI in the next few years will provide decision support to clinicians, allowing improved decision-making that would lead to better quality and patient safety, as well as more efficient care. Hospitals have much to gain from AI as they treat the most complicated and expensive cases, as well as those that pose higher patient safety risk."


You’ve heard of chloroquine by now. Originally developed by German scientists in the 1930s, the anti-malaria drug is based on a natural compound present in the bark of certain South African trees. For nearly a century it’s been saving lives globally, but remained under the radar of countries where malaria isn’t a big problem.

Thanks to COVID-19, chloroquine is back in the media spotlight as a potential treatment to reduce severe coronavirus symptoms.

To be clear: we don’t know if it works. Chinese physicians threw the drug (along with a whole other bucketful) in a last-ditch attempt on severe COVID-19 sufferers who were dying. Some got better. Many didn’t. Without clinical trials—which are ongoing—positive effects could’ve been just wishful thinking.

Chloroquine isn’t an isolated story. Several potential existing drugs are being investigated for COVID-19, though at the moment “there are no definitively effective drugs,” Dr. Li Haichao told Singularity Hub. Li is a respiratory and critical care physician at Peking University First Hospital and a member of the national emergency medical rescue team to Wuhan.

What ties these promising drug candidates together, however, is that none of them are “new,” that is, none were specifically developed for coronavirus—or any virus. Yet they all have traits that make them potentially powerful drugs to combat the new virus that’s been wreaking havoc across the globe.

Repurposing available drugs is perhaps the fastest route to an SOS treatment in any outbreak. Rather than developing new drugs from scratch—a daunting effort that could last a decade—existing drugs, especially those already approved by regulatory agencies, could storm into action much faster and save lives.

For now, in the face of this brand-new virus, scientists are making educated guesses based on expertise and intuition to select a few potential drug candidates.

What if there’s another way?

This week, a preprint paper outlined how deep neural networks could help doctors search for antivirals against a new target. Especially intriguing is the fact that the algorithm doesn’t just look at experimental drugs—it also screens through a library of compounds, already approved for other ailments, that could also potentially work for coronavirus symptoms. Tapping an existing, approved drug is like asking a friend for help rather than an online stranger: you already understand the drug’s safety and metabolism profiles, and that increases trust.

But it’s not all ponies and rainbows. AI-based drug repurposing is perhaps even more dangerous than de novo drug discovery. Familiarity is a double-edged sword; it’s exactly because you trust an approved drug that you’re less inclined to question its safety. The margin of therapeutic and toxic doses of chloroquine, for example, is narrow, and poisoning can be life-threatening. AI could help—but fundamentally it’s up to clinical trials to validate.

Why Does Drug Repurposing Work?
The preprint is one recent attempt at a fascinating movement in using AI for drug discovery.

AI’s role in drug discovery has been touted in many ways: finding new targets, scouring for novel candidate molecules that improve “hit rate”—that is, how many go through rigorous clinical trials and make it to market. Most AI-based attempts focus on finding new compounds; yet with COVID-19 rapidly destroying global health and wealth economies, drug repurposing is emerging as a previously undervalued bet.

The idea of using a drug for one disease on another may seem strange. If it takes a decade to develop a drug against one disease, why would it work for something else?

The reason is biological similarity.

Nature is kinda lazy. Although the Covid-19 virus is new to humans, it’s not exactly an alien species unknown to evolution. As a coronavirus—or heck, a virus itself—we have a basic idea, based on previous similar viruses such as SARS and MERS, of how it infects cells and how it rapidly transmits. Studies are underway to decipher why it’s so freaking effective compared to its cousins, but that’s the crux: there are previous examples to look at.

On the human “recipient” side, we can also match up how our bodies respond at the molecular or even genetic level to such an infection compared to other viruses. After infection, a virus fundamentally changes how a cell’s protein factories work. Because viruses can’t replicate themselves, they require our cell’s manufacturing facilities to reproduce, which changes the cell’s gene expression profile. It’s like looking at a city’s satellite image before and after being hit by the virus—there are notable changes in traffic, air pollution, artificial lights, and so on, relatively easy to distinguish.

Here’s the main idea: if a drug changes gene expression profiles similarly between two different circumstances—say, two different infections, one of which is new—then it’s conceivable that the drug can work for the new infection. At least, that’s the logical, AI-based point of view.

From an ER physician’s perspective, all of the above is too complicated to consider in real life. Why use chloroquine in Covid-19 patients? Because, controversially, it has anti-viral properties on isolated cells in labs, even though to date, “no acute virus infection has been successfully treated by chloroquine in humans.” The use of chloroquine was a desperate attempt: Chinese doctors administered the drug as a last-ditch, gut-feeling effort, because it seemed to have (unconfirmed) beneficial effects against SARS more than a decade ago. Gene expression was the last thing on their minds.

Where Does AI Come In?
Unlike human doctors, AI does have the ability to dig deeper into drug effects at the molecular or genetic level. As a purely fictional example: from a deep neural net’s perspective, if a drug that works on HIV triggers the same genetic expression changes in patients with COVID-19, perhaps the drug could also work for the new coronavirus.

Using AI for drug repurposing isn’t new—hundreds of studies on the topic have come out in recent years. The tough part is setting up the experiment.

The preprint, for example, is based on a hypothesis using SARS, a virus similar to the one that causes COVID-19. A gene, dubbed COPB2, was previously found essential to help SARS replicate in the body. Because the COVID-19 virus and SARS have at least 86 percent similarity in their genome, a drug that works for SARS could in theory be promising for battling COVID-19. This is in line with most drugs currently tested against the new coronavirus—most were initially developed for other viruses.

Here’s where machine learning comes in. The team first looked at the genetic profile of cells without the COPB2 gene, which (if the gene is essential for COVID-19) means that they are at least partially resilient against SARS, and maybe against the new coronavirus. They then screened through mass chemical libraries to find compounds that trigger a similar genetic profile in cells as eliminating the COPB2 gene altogether.

The neural net yielded a list of experimental and approved compounds that matched the profile. One “sanity check” chemical, for example, was previously found to reduce SARS replication in infected cells.

An AI Savior?
If you have questions and doubts—good, you should. We’re still in the beginning stages of tackling COVID-19. This means that there’s very little data on the virus that can be used to train AI. The preprint used SARS as a proxy, which is logical, especially because we know so little yet about the new coronavirus. To their credit, the team also calls for academic and industry collaborations to experimentally validate their results.

However, is COPB2 necessary for COVID-19 to hijack your cells? No clue! We simply don’t have enough data to confirm either way. Would the drug candidates against SARS work for the COVID-19 virus? No one knows.

And that’s the lesson. Drug repurposing in a crisis is often a Hail Mary attempt. Doctors are desperate. But without taking a step back and running controlled trials, we will let hope take over data and truth to the detriment of scientists, physicians, and patients alike. AI, without doubt, has the potential to blast open a world of potential repurposed drug candidates, ranked by predicted efficacy. That’s really great: rather than a handful of promising drugs, we could have ones that we haven’t even thought of.

But it’s also dangerous to run away with AI-recommended hype, especially for drugs already on the market. Just because they’re safe for one tested disorder doesn’t mean they’ll act the same for another. Everyone is impatient to find refuge—but that’s exactly why scientific objectivity needs to kick in first.


Tom Siebel’s Unified AI-Big Data Front Against COVID-19

If AI is to help turn back the COVID-19 tide in a timeframe that saves lives and livelihoods, data scientists will need to build machine learning models fast and run them on a platform that scales to the global pandemic’s enormous complexities. Even more, vast amounts of Coronavirus-related data will be needed so models can be trained to produce valid epidemiological and treatment research results. And given the time pressures of this crisis, data scientists must be freed from the shackles of data wrangling and cleansing, which can consume 80 percent of their time.

But does such an AI development environment exist? And where can the data, in a cleansed and usable format, be found? Thomas Siebel, chairman and CEO of, says his company has both, and he’s giving them away for free., which boasts some of the world’s largest at-scale enterprise AI implementations (Con Edison, Enel, U.S. Air Force, Royal Dutch Shell), is leading a two-pronged effort to fight COVID-19. On the technology side, the Data Transformation Institute is a consortium of research universities, supercomputing centers and Microsoft Azure that will pursue research projects, the results of which Siebel told us will be released into the public domain, using the AI Suite and its model-driven architecture designed for enterprise-scale AI applications. On the data side, the company on April 13 will release for public use the first of two tranches of an aggregated COVID-19 data lake from more than 30 information sources, which will have been unified and federated using the AI Suite’s data-wrangling capabilities, ready for use by data scientists.

The effort leverages experience gained by Siebel and his team not only at but also from their years running Siebel Systems, a creator of CRM software formed in 1993 that became a $2 billion company and merged with Oracle in 2006. The platform that evolved into the C3 AI Suite, funded by Siebel when he formed the company in 2009, was eight years in development before becoming commercially available. is now comprised of more than 500 employees and grew by roughly 100 percent last year, Siebel said.

“Some of these projects we’re getting involved in, like building these large-scale discrete event simulations, taking a massive amount of data and predicting what it will look like in seven days, OK, that's a hard process,” Siebel said of COVID-19 modeling workloads. “So the amount of data that you need to be able to aggregate, synthesize, and process – the number of CPU cycles that you need to be able to do that with acceptable levels of precision  – this is a computationally extraordinarily extensive problem. In terms of scaling, it's mind-numbing. When we start mapping these large genome sequence databases, you're going to run into scaling issues on data size and data processing capability, people are going to spool up, they're going to build machine learning models, that will take tens of thousands of virtual machines operating in a parallel process.”

Delivering the most extreme of the compute-intensive cycles will be the National Center for Supercomputer Applications (NCSA) at the University of Illinois/Urbana and its Blue Waters system, and the Perlmutter supercomputer, due for completion by spring 2021, at Lawrence Berkeley National Laboratory’s National Energy Research Scientific Computing Center.

The effort is one of many resource sharing, crowdsourcing efforts formed to combat COVID-19. Data analytics and business intelligence specialist Tibco has released its COVID-19 Visual Analysis Hub, a site for using the company’s Spotfire analytics software to track the pandemic’s spread and impact based on data from the Center for Systems Science and Engineering at Johns Hopkins University (also used in’s COVID-19 data lake) and other sources.

Among other efforts that emerged this week, Domino Data Lab, provider of an open data science platform, announced complimentary access to its data science platform to COVID-19 researchers. WellAI released a  software application for COVID-19 researchers based on algorithms that read and summarize large amounts of medical literature, available at From China, Huawei Cloud announced as part of its Anti-COVID-19 Partner Program free access to cloud and AI services, such as its EIHealth that includes viral genome detection, antiviral drug in silico screening and AI-assisted CT patient screening service, as well as free cloud resources worth up to $30,000 (US). Tavares is making its xGT graph analytics tool, for in-memory computation capable of ingesting terabytes of data, available at no cost to data scientists working on COVID-19. (For other COVID-19-related analytics and data sources available free of charge, see “COVID-19 Spurs Offers for Free Software, Data, and Training” at sister publication Datanami.)

At, Siebel said the Digital Transformation Institute ( DTI) has issued its first call for COVID-19 research proposals dealing with such challenges as slowing the pandemic’s spread, speeding development of medical treatments and designing and repurposing of drugs or clinical trials. DTI will initially fund more than 26 research projects funded with more than $57 million from the company along with $310 million in the form of in-kind contributions from and its C3 AI Suite and Microsoft Azure cloud resources. Winning proposals will be selected by June 1, Siebel said.

He’s optimistic that the project work, when released publicly, will quickly be accepted and adopted because “it's been blessed by Berkeley, Princeton, Carnegie Mellon so, I mean, the National Institutes of Health and the CDC are going like it.”

While computing and machine learning resources are valuable to projects of this type, Siebel said they’re not the most valuable.

“When you're dealing with AI at research institutions,” he said, “the scarcest resource isn’t computing capacity going into bioinformatics and it’s not human capital. It's the availability of real data. So these data scientists and researchers, because they do not have access to large public health databases due to HIPAA regulations and what have you, they're forced to synthesize data.”

While the first traunch of the COVID-19 Data Lake will be released next week, the second will be released in May. The open data sets will be accessible at via utilities that support access through a RESTful API using common tools, such as Python, R, Ex Machina and Microsoft Power BI. said researchers and developers are invited to help expand data lake by enhancing its functionality, developing analytics and predictive models and contributing additional data sets through a crowdsourcing model.

“We started working with NIH, the CDC and all of these research institutions to basically aggregate the largest unified, federated data image that consists of all the data that we're able to find on COVID-19,” said Siebel, adding that partnered with Amazon Web Services on this aspect of the Coronavirus project. “And by a unified aggregate image…, it's not simply that all of these data are in one place, they're in one place and fully connected. This is an extremely large dataset where we've connected the articles on the disease to the patient who has the disease to the CT scan that indicates the disease. All of these pointers are there in a unified data image that we can navigate using a knowledge graph…and perform data science.”

Siebel said 50 employees have been assigned to COVID-19 project work.

“In many ways, I think this crisis is a test,” Siebel said. “It's a test of us as individuals and how we behave. It's a test of the strength of our social fabric and how well it holds up under crisis, (because) it might get pretty tense out there in the next month. It’s a test of the strength of our government institutions, and at a less significant level,, it's going to be a test of the resilience of corporate leaders.”

“And you know, if we have some small impact at the edge of this crisis, I'll be honest with you, if this is all the company ever accomplishes, I'll be happy. If this is all we accomplish in the history of this company, I’ll feel the last 10 years will have been successful.”


For frontline healthcare professionals who require information urgently, an Artificial Intelligence (AI) messaging app could help speed things up. The app is currently used in the National University Hospital and there are plans to extend its use to other hospitals in Singapore. Isabelle Lim reports.


COVID-19: AI can be a useful tool to combat pandemics, provided its use, including for tracking, is responsible, ethical and human-centered, says PACE rapporteur

“Although Artificial Intelligence (AI) may prove a useful ally in overcoming the COVID-19 pandemic, we should not forget that its use may raise serious human rights concerns that can undermine the trust placed in governments,” said Deborah Bergamini (Italy, EPP/CD), PACE rapporteur on the need for democratic governance of Artificial Intelligence.

Echoing concerns expressed by other international bodies, Ms. Bergamini warned that, while there was a need for innovative efforts to confront the pandemic, “human rights, civil liberties and rule of law principles may be exposed or damaged if we do not tread this path with great caution”.

“The use of AI and surveillance technology to track the spread of the Coronavirus, or enhance monitoring and detection capabilities, may seem an effective response, but any excessive or unethical use may result in grave violations of the right to privacy and non-discrimination,” she added.

“AI cannot be considered a silver bullet for pandemics, but it is definitely a powerful tool that can help generate information to enable more precise and effective strategies for the prevention of, detection of and response to outbreaks, thus contributing to public health, if used properly,” she added.

“Α responsible, ethical and human-centered AI is needed now more than ever. It is crucial that the use of these tools is limited both in terms of purpose and time, and that national authorities scale back any newly-acquired monitoring capabilities after the end of this pandemic,” she concluded.


In response to the COVID-19 pandemic, the White House on Monday joined a number of research groups to announce the release of the COVID-19 Open Research Dataset (CORD-19) of scholarly literature about COVID-19, SARS-CoV-2, and the Coronavirus group. The release came with an urgent call to action to the world’s AI experts to “develop new text and data mining techniques that can help the science community answer high-priority scientific questions related to COVID-19.”
A publicly available and machine-readable dataset, CORD-19 consists of over 29,000 scholarly articles, including over 13,000 with full text about COVID-19, SARS-CoV-2, and related coronaviruses.
Worldwide total confirmed cases of COVID-19 have surged to 190,535 as of March 17 according to a Johns Hopkins University map. The World Health Organization (WHO) yesterday said the total number of cases and deaths outside China had overtaken the total number of cases in China.
Meanwhile, the rapid acceleration in new coronavirus literature has researchers struggling to keep up.
“It’s difficult for people to manually go through more than 20,000 articles and synthesize their findings. Recent advances in technology can be helpful here. We’re putting machine-readable versions of these articles in front of our community of more than 4 million data scientists. Our hope is that AI can be used to help find answers to a key set of questions about COVID-19,” said Anthony Goldbloom, Co-Founder and Chief Executive Officer at Kaggle.
The CORD-19 dataset challenge hosted on Kaggle defines 10 tasks based on key scientific questions developed in coordination with the WHO and the National Academies of Sciences, Engineering, and Medicine’s Standing Committee on Emerging Infectious Diseases and 21st Century Health Threats. Questions include for example “What is known about transmission, incubation, and environmental stability?” and “What has been published about information sharing and inter-sectoral collaboration?”
The tasks are detailed on Kaggle. Submissions must be contained in a single notebook made public on or before the submission deadline. Participants are free to use other datasets in addition to CORD-19, but those datasets must also be publicly available on either Kaggle,, or Semantic Scholar.
The CORD-19 dataset was built by the Allen Institute for Artificial Intelligence, the Chan Zuckerberg Initiative, Georgetown University’s Center for Security and Emerging Technology, Microsoft Research, the National Library of Medicine — National Institutes of Health, and the Kaggle AI platform owned by Google — in coordination with The White House Office of Science and Technology Policy.
“It’s all hands on deck as we face the COVID-19 pandemic,” said Dr. Eric Horvitz, Chief Scientific Officer at Microsoft. “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.”


According to Microsoft chief technology officer (CTO) Kevin Scott, biometric smart rings being worn by healthcare workers at a San Francisco hospital are an example of the sort of benefits we could expect if more funding going into artificial intelligence (AI) technology as a consequence of the COVID-19 outbreak.

Scott, who has a new book about AI coming out this week, argues that investing in the technology could reap major benefits for an American healthcare system that is taking a beating due to the spread of COVID-19 throughout the country.

Speaking with The Seattle Times, he compares this investment in AI and the benefits it would bring to another period of rapid technological change in recent history.

“I think our reaction to this horrible pandemic we’re having now could produce a wave of investment and innovation in biotechnology that defines the next 75 years,” he said. “The way that the industrialization of the modern world post-World War II has defined the past 75 years.”

One example he gives of a current benefit of this investment are biometric smart rings that healthcare workers at Zuckerberg San Francisco General Hospital wear to monitor their heart-rate data, body temperature, and blood oxygen saturation as a way of predicting the early onset of COVID-19.

“So, if you just imagine what would happen to a world where, for this whole range of conditions you’d have a combination of cheap, wearable biometric sensing … that really could just fundamentally change the cost of health care and the general wellness of people that would have access to these technologies,” said Scott.

The use of AI and biometric technology in healthcare has grown steadily over the past year, crossing further over into the mainstream consumer market as companies like Apple invest more into the healthcare capabilities of their wearables.


Responding to the fighting against COVID-19, AI4EU members have contributed ideas and grouped for possible solution developments on the AI4EU Platform and among its community. AI4EU Web Café is also enabling the innovators and developers of the European AI community to present the latest AI developments in creating tools and solutions in the effort to help frontline forces in the fight against the COVID-19.

The week of 13 April 2020, AI4EU Web Café hosts two sessions, bringing a freshly developed solution in the effort to help the frontline medical staff to protect themselves effectively while providing care to those in need.

The special COVID-19 Web Café is titled: The CIIRC RP95-3D Protective Half-Mask – The Fast Track from Scientific Idea to The Real Production as The CIIRC’s Contribution in The Fight Against the Coronavirus Pandemic. The Speakers are Dr. Vit Dockal and Dr. Pavel Burget from the CIIRC of Czech Technical University in Prague.

On a regular weekly Web Café session next week, AI enthusiasts also have a chance to learn about the natural and artificial intelligence on Web.

Dr. Fabien Gandon is a Research Director and Senior Researcher at Inria, France, will present a talk titled “Linking Natural and Artificial Intelligence on the Web”.

The talk’s motivation was that the Web was essentially perceived as a huge distributed library of linked pages, a worldwide documentary space for humans. In the mid-90s, with wikis and forums, the Web was re-opened in read-write mode and this paved the way to numerous new social media applications.

The Web is now space where three billion users interact with billions of pages and numerous software. In parallel, extensions of the Web were developed and deployed to make it more and more machine-friendly supporting the publication and consumption by software agents of worldwide linked data published on a semantic Web.

As a result, the Web became a collaborative space for natural and artificial intelligence raising the problem of supporting these worldwide interactions. In particular, these hybrid communities require reconciling the formal semantics of computer science (e.g. logics, ontologies, typing systems, etc.) on which the Web architecture is built, with the soft semantics of people (e.g. posts, tags, status, etc.) on which the Web content is built. This talk will present some of the challenges and progresses in building this evolution of a Web toward a universal space to link many kinds of intelligence.


Suki, a startup that makes an AI-powered voice assistant for doctors, received two pieces of news from major clients less than three weeks ago. The first was that they’d need the product to accommodate telemedicine visits. The second was that they’d need auto-filled clinical notes to quickly process patients who test positive for COVID-19 — “Hey, Suki, write up a completed clinical note for COVID-19.”

The clients sent Suki their requirements and the data they’d gathered so far, and CEO Punit Soni called a meeting with his COO, head of customer success, product lead, sales lead and marketing lead.

It was 4 p.m. The meeting lasted 20 minutes. By 9 a.m the next day, the new offerings were deployed.

To be fair, the viral outbreak had been on the team’s radar for about a month. Team members didn’t know how severe it would get or what response it would require, but they knew one thing: Healthcare professionals would need support, and AI would be one way to give it to them.

“In hindsight it’s obvious, but I hadn’t thought about how telemedicine would explode with doctors unable to see patients because of infection issues,” Soni said. “But that’s the cool part about being a tech startup. Not only are you super agile, you have the ability to create and deploy a product in 24 hours flat. All I need is data. That’s one of the big reasons why AI is the future.”

For many, the rapid spread of the novel coronavirus — and worldwide confusion about how to best contain it — makes human limitations seem starker than ever. We can’t treat patients if we don’t have the hospital beds. We can’t curb the virus’ spread if we don’t know who has it, or if we can’t find a vaccine.

AI only knows what we tell it, but it does what we cannot: take in large amounts of disparate information and detect patterns. As we scramble to save lives and stabilize our world, some companies are using algorithms to give us an edge.

Dr. Yale Tung Chen, an emergency medical doctor in Madrid, wrote a tweet on March 9: “Day 1 after #COVID diagnosis. Sore throat, headache (strong!), Dry cough but not shortness of breath. No lung US abnormalities. I will keep a #POCUS track of my lungs. #coronavirus”

“POCUS” is an acronym for point-of-care ultrasound. Beneath the text is an ultrasound image of Chen’s lungs. The bottom right corner of the image reads, in Spanish, “Captured with Butterfly iQ.”

Some health tech companies — like medical imaging startup Butterfly Network, the creator of Butterfly iQ — were uniquely positioned to respond to the outbreak. Butterfly iQ is a handheld, AI-powered ultrasound device that sends images to a user’s mobile phone for automated interpretation.

The startup had been monitoring COVID-19 since its outbreak in mid-January in the Asia Pacific region, where physicians were reporting the importance of lung imaging in tracking and treating the virus. Since Butterfly Network’s scanner could serve as a cleaner, less expensive alternative to X-rays and CT scans, the product’s relevance was clear to the company early on.

After noticing physicians like Chen sharing images of infected lungs on social media, the startup launched a landing page where medical professionals can share images and learn how to use the scanner for lung ultrasounds. Butterfly Network also hosted a webinar last Thursday to help healthcare workers recognize a COVID-19-positive lung.

AI comes into play in two ways. First, automated image analysis makes it easier for people with less training to use the scanner effectively. As hospitals shift assignments to manage an influx of sick patients, workers unfamiliar with the nuances of lung imaging could end up screening patients — and may benefit from a more accessible device.

Second, as more medical professionals use Butterfly Network’s scanner to check for symptoms of COVID-19, the company’s cloud-based system gets more robust data about the virus and what it looks like. That, in turn, will make the product’s analysis more accurate, director of education Dr. Mike Stone and chief medical officer Dr. John Martin wrote in an email. Martin has been corresponding with emergency room physicians in China, Italy, Spain and the United Kingdom as the pandemic has progressed, he said.

“It’s an all-hands-on-deck approach right now,” the email said.

Just as important as treating infected persons, however, is making sure they don’t infect more people.

Boston-based startup Biofourmis offers an AI-powered health analytics platform called Biovitals, which uses patient monitoring to predict negative health outcomes before they happen. Bioform had been working with the University of Hong Kong on an at-home heart monitoring solution for two years when they received a call from the government of the region asking if the solution could be repurposed for at-home COVID-19 monitoring.

That’s because healthcare facilities are among the least safe places for sick people during a pandemic. In a February 7 study of 138 coronavirus patients in Wuhan, China, 41 percent were suspected to have caught the virus at a hospital. By keeping carriers and potential carriers at home, healthcare workers and vulnerable hospital patients are shielded from some exposure.

Bioform received that call in mid-February. Its solution rolled out two weeks ago in Hong Kong.

Here’s how it works: Patients who are positive or at risk for COVID-19 are equipped with a biosensor to wear on one of their arms, and then they’re sent home. The sensor collects 20 different physiological signals from its wearer, including temperature, heart rate and respiration rate. Then, Biofourmis’ platform uses AI to analyze the signals and determine if a physician needs to be pinged. Over time, the machine learning model will start to understand the physiological signature of the virus, so it ideally can be detected earlier and treated more effectively.

“We’re also collecting data right now on medication, imaging, clinical data and therapies, and we can use AI to potentially learn more about this disease, because we know very little about the disease right now,” Biofourmis CEO Kuldeep Singh Rajput told Built In. “Having AI guide us and tell us exactly what signature COVID-19 has and how it progresses will help physicians manage patients better, but also will help companies to come up with new solutions.”

Bioform’ predictive platform will roll out in three more countries with high COVID-19 infection rates in the next week, Rajput said. He did not disclose which hospital systems will participate.

Telemedicine, which Suki is supporting, and at-home care, which Biofourmis is enabling, could be instrumental in preventing hospital systems from becoming overwhelmed by confirmed or suspected COVID-19 patients.

But people suffering from coronavirus aren’t the only ones getting sick. Patients with other illnesses or chronic conditions — like heart disease, which accounts for one in every four deaths in the United States each year — will have a harder time getting seen by medical professionals and receiving the care they need.

That’s why health tech startup HeartFlow isn’t adjusting its offerings at all.

HeartFlow uses AI to analyze CT images of patients’ hearts. Physicians upload the scans to HeartFlow’s cloud, and then the company’s algorithms and trained analysts create a 3D model of the heart and its arteries. With the help of another layer of physics simulations, HeartFlow provides physicians information about how blockages impact blood flow.

Usually, insights like those require an invasive procedure called an angiogram. And invasive procedures require attending physicians and hospital beds — two things in short supply during a pandemic.

“A lot of hospitals are canceling elective procedures and things that aren’t emergencies to try to save on supplies or personal protective equipment, as well as just time and space in the hospital,” said Tim Fonte, HeartFlow’s VP of customer success. “They’re doing things as far-reaching as converting physicians’ offices into intensive care units temporarily.”

By letting algorithms do what angiograms normally would, HeartFlow is helping hospitals divert more resources toward COVID-19 response. Its analysts need special equipment, so they will continue working on-site in the Bay Area and Austin, albeit in smaller, isolated teams. The startup has a working group of about five people addressing customer concerns and determining the best path forward in light of the outbreak, but it’s largely business as usual, Fonte said.

“There wasn’t a fundamental need to change what we’re doing now,” he said. “Hospitals have to put their time into other things right now, but it doesn’t mean these patients with coronary disease who need help are just going to go away.”

Some companies leveraging AI to help aren’t in the health tech space. In fact, they’re not even creating their own algorithms.

CRITICALSTART is a Texas-based cybersecurity startup. Its director of professional services, Quentin Rhoads, likes being the best at things — or at least close to the best, he said.

“I’m a pretty competitive individual is pretty much everything I do,” he said. “I don’t ever want to feel like I fall behind. I guess I’ve always been like that.”

Perhaps that’s why when Twitter user @TinkerSec sent him a message saying one of CRITICALSTART’s competitors was donating part of its computing power to help researchers simulate the protein structures of COVID-19, Rhoads signed his company up the same day.

The project was Folding@Home, an effort by researchers at Washington University in St. Louis School of Medicine to crowdsource the computing power needed to run extremely complex simulations of the atoms in viruses.

A virus is coated in protein, which consists of folded-up amino acids, which consist of atoms. Existing experimental methods provide a snapshot of a virus’ atoms, but no insight into how they move and interact. Simulations are a better way to hunt for a virus’ weaknesses, but running each simulation requires an enormous number of calculations — running them on a single computer would take hundreds of years.

That’s where CRITICALSTART’s password-cracking server, dubbed Cthulhu, comes into play. Cthulhu is a combination of hardware and software that uses eight Nvidia Titan V graphics cards — created for deep learning and AI research — to make 27.8 billion password guesses per second. Its automatically generated password-candidate lists contain quadrillions of unique entries.

With Cthulhu on the job, CRITICALSTART joined more than 240,000 teams across the world donating powerful computing rigs, or even personal laptops, to the task. In the week leading up to March 18, 400,000 people downloaded Folding@Home, director Dr. Greg Bowman said on Twitter, and the project now has 470 petaFLOPS of power available to it — more than two times the peak power of the Summit supercomputer. (Summit is the world’s fastest computer. So far, it’s found 77 potential coronavirus therapies by running simulations.)

A week after starting with Folding@Home, Rhoads is keeping close tabs on his company’s ranking.

“Right now we’re in the top 2 percent of contributors, which is pretty insane,” Rhoads said. “I mean, we’re still ranked like 5,000th globally, but still.” (Their rank had risen to 3,406th at the time of this writing.)

The CRITICALSTART team has paused the simulations to run penetration tests a few times, Rhoads said, but largely, the GPUs have been dedicated to generating data about the virus. In uncertain times, it feels good to do something helpful — and the team rankings don’t hurt either.

“This gives our team something to do that’s constructive,” Rhoads said. “We’re trying to convince our other competitors to get involved as well. It gives it a little gamification and lets us not just contribute to a good cause, but also get bragging rights.”

Despite AI’s usefulness for researchers, healthcare workers and corporate types, it has its limitations. Namely, its reliance on past data makes it an imperfect tool for responding to a novel threat. When it comes to COVID-19, AI can’t tell us what will happen next — and hasn’t really told us what’s happening right now.

The machine learning specialist tapped by the Centers for Disease Control and Prevention to model current infections, for instance, chose not to use machine learning, Vox reported. Instead, he’s using a method called “wisdom of crowds,” in which normal people report how they think the pandemic is progressing, and researchers compile the answers to create a model.

“The first question everyone is going to have is, ‘How can we prevent this from happening again?’” said Gabriel Musso, chief science officer at New York City-based BioSymetrics. “I think that will get a lot of deserved attention.”

BioSymetrics is an AI-enabled platform for early-stage drug discovery. While he couldn’t share details, Musso said his company has multiple clients using machine learning for COVID-19-related drug discovery or triage projects.

And while machine learning models may not be able to prevent the next global virus, he said, that doesn’t mean they can’t make us better prepared.

Novelty detection is an area of machine learning in which a model learns to identify signals or data that weren’t part of its training. A model trained on a healthy person’s signals may be able to detect early signs of disease, for example. The more the model understands which signals lead to disease, the earlier it can detect warning signs. Someday, the same could be true of pandemics.

“As a society, we need to be able to understand what we’re able to predict. To that end, there’s no reason machine learning can’t be applied effectively,” Musso said. “That’s the ultimate hope for machine learning. Once you have that understanding, there’s no reason you can’t apply similar patterns for threats that can’t be identified.”

A vaccine, a physiological signature, a voice assistant, a plan — they all require data, and lots of it. As data from disparate countries with disparate practices rolls in, experts will rush to find some systemic meaning.

Hopefully, AI will augment those efforts to make us healthier and safer. And maybe next time, it will help us be ready.

“We can use the data generated through COVID to make a better argument in favor of the costs of taking preventative measures to prevent things from spreading across nations,” Musso said. “And perhaps coordinate a response that’s anticipatory.”


COVID-19 coronavirus reports change daily and even hourly. The public health emergency has already swept the whole world: the virus threatens people's lives, affects business and interferes with travel.
How the COVID-19 coronavirus will affect our daily life and work is still unclear because this disease is spreading all over the world for the first time, but there is an assumption that artificial intelligence (AI) will help fight the virus and its economic impact.
A report by the World Health Organization last month declared that AI and big data are a vital solution to tackle the virus. This article will explore some machine learning-based methods people use to detect or combat coronavirus.

Chatbots answer questions related to coronavirus
One of these chatbots - Bespoke - was created in Japan in 2011 after a strong earthquake. Today you can find the latest news on the outbreak of coronavirus, disease statistics around the world, information on prevention and symptoms, as well as the latest developments in the field of transport services.
In the United States, they have developed a chatbot with artificial intelligence that identifies flu symptoms. To do this, send data on temperature and pulse, as well as an audio recording of cough. Now this chatbot is asking clarifying questions related to the coronavirus. For example, have you recently traveled to China or other outbreak hubs?
You are aware of the fact of how the coronavirus damaged economies and trading in the world. A lot of European markets crashed, and even forex markets were affected. Of course, severe disruptions caused by COVID-19 have not missed the latter, but it did not hinder top forex brokers from adopting an innovation featuring chatbot. The chatbot which we have mentioned in the previous case is similar. It offers people the news about the coronavirus, how to protect and tackle it. Not only brokers help people find useful information, but they also think it will help them to attract more customers after the pandemic is over.

Artificial Intelligence can detect, track, and the model outbreak of disease
Canadian startup BlueDot has developed one of the most successful disease risk prediction systems. Their artificial intelligence scans about 100 thousand articles in 65 languages ​​daily. Therefore, it was the first to detect an outbreak of coronavirus in China back in December 2019.
Johns Hopkins University has developed a program that collects real-time information on coronavirus infections worldwide.
Artificial intelligence can create mathematical models that help describe the evolution of a disease — its peak and decline. A similar model was used during the outbreak of coronavirus in Italy.

Artificial intelligence helps find a cure for coronavirus
To create an effective vaccine, you need to understand the structure and nature of the new coronavirus thoroughly. The Google DeepMind division has used its latest artificial intelligence algorithms to study proteins that may be associated with COVID-19. The company published its research in the public domain. DeepMind says their computational predictions of protein structures have not been tested experimentally, but they hope that they will help the scientific community understand how coronavirus works.
BenevolentAI uses artificial intelligence systems to create cures for the most severe diseases. A few weeks after the outbreak of a new coronavirus, they tuned their system so that it selects existing drugs that could help.
Several large technology companies, such as Tencent, DiDi, and Huawei, provide researchers with their cloud computing resources and supercomputers. The speed with which these systems can perform calculations and model solutions will help much more quickly develop a cure or vaccine for a new coronavirus.
The Stanford University project Folding@home offers anyone who wants to help the scientific community in the fight against coronavirus. To do this, you need to install a special program on your computer and connect to a distributed network for resource-intensive scientific calculations. While you are not working at a computer, it will calculate precisely how protein chains in the coronavirus cells interact with each other. By correctly modeling the structure of the virus, scientists will be able to find a cure for it quickly.

Detection of fever in people in public places
To detect coronavirus, AI uses cameras equipped with thermal sensors.
The Singapore hospital and government medical facilities are real-time, checking the temperature by launching the KroniKare system, which runs on a smartphone with a temperature sensor.
The artificial intelligence system developed by Baidu, a Chinese technology company, is equipped with an infrared sensor and artificial intelligence to determine people's body temperature; it is now used at the Qinghe Railway Station in Beijing.
Baidu technology makes it possible to determine forehead temperatures in 200 people in 1 minute with an accuracy of 0.5ºС by combining computer vision and infrared radiation. The system warns authorities if it detects a person with a temperature above 37.3 degrees Celsius since elevated temperature is a harbinger of coronavirus. Baidu products are used to monitor body temperature at Beijing South Railway Station and line 4 of the Beijing Metro.
Last month, the Shenzhen Micromulticopter announced the launch of more than 100 unmanned aerial vehicles in several Chinese cities. Drones can not only determine the temperature but also spray disinfectants and patrol public places.

Now we can understand how artificial intelligence helps people detect and fight against this annoying coronavirus. While there is still a long way for the virus to be contained, AI does a great job to restrict the spread of it.


How artificial intelligence is taking on COVID-19?

As the COVID-19 coronavirus outbreak continues to spread across the globe, companies and researchers are looking to use artificial intelligence as a way of addressing the challenges of the virus. Here are just some of the projects using AI to address the coronavirus outbreak.

Using AI to find drugs that target the virus

A number of research projects are using AI to identify drugs that were developed to fight other diseases but which could now be repurposed to take on coronavirus. By studying the molecular setup of existing drugs with AI, companies want to identify which ones might disrupt the way COVID-19 works.
BenevolentAI, a London-based drug-discovery company, began turning its attention towards the coronavirus problem in late January. The company's AI-powered knowledge graph can digest large volumes of scientific literature and biomedical research to find links between the genetic and biological properties of diseases and the composition and action of drugs.

The company had previously been focused on chronic disease, rather than infections, but was able to retool the system to work on COVID-19 by feeding it the latest research on the virus. "Because of the amount of data that's being produced about COVID-19 and the capabilities we have in being able to machine-read large amounts of documents at scale, we were able to adapt [the knowledge graph] so to take into account the kinds of concepts that are more important in biology, as well as the latest information about COVID-19 itself," says Olly Oechsle, lead software engineer at BenevolentAI.

While a large body of biomedical research has built up around chronic diseases over decades, COVID-19 only has a few months' worth of studies attached to it. But researchers can use the information that they have to track down other viruses with similar elements, see how they function, and then work out which drugs could be used to inhibit the virus.

"The infection process of COVID-19 was identified relatively early on. It was found that the virus binds to a particular protein on the surface of cells called ACE2. And what we could with do with our knowledge graph is to look at the processes surrounding that entry of the virus and its replication, rather than anything specific in COVID-19 itself. That allows us to look back a lot more at the literature that concerns different coronaviruses, including SARS, etc. and all of the kinds of biology that goes on in that process of viruses being taken in cells," Oechsle says.

The system suggested a number of compounds that could potentially have an effect on COVID-19 including, most promisingly, a drug called Baricitinib. The drug is already licensed to treat rheumatoid arthritis. The properties of Baricitinib mean that it could potentially slow down the process of the virus is taken up into cells and reduce its ability to infect lung cells.

More research and human trials will be needed to see whether the drug has the effects AI predicts. BenevolentAI has announced that Ely Lilly and the US National Institute for Allergies and Infectious Diseases (NIAID) will begin investigating Baricitinib's safety and effectiveness in treating COVID-19 as part of clinical trials from this month. The results of the trials are expected within the next two months.

Shedding light on the structure of COVID-19

DeepMind, the AI arm of Google's parent company Alphabet, is using data on genomes to predict organisms' protein structure, potentially shedding light on which drugs could work against COVID-19.

DeepMind has released a deep-learning library called AlphaFold, which uses neural networks to predict how the proteins that make up an organism curve or crinkle, based on their genome. Protein structures determine the shape of receptors in an organism's cells. Once you know what shape the receptor is, it becomes possible to work out which drugs could bind to them and disrupt vital processes within the cells: in the case of COVID-19, disrupting how it binds to human cells or slowing the rate it reproduces, for example.

After training up AlphaFold on large genomic datasets, which demonstrate the links between an organism's genome and how its proteins are shaped, DeepMind set AlphaFold to work on COVID-19's genome.

"We emphasize that these structure predictions have not been experimentally verified, but hope 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," DeepMind said. Or, to put it another way, DeepMind hasn't tested out AlphaFold's predictions outside of a computer, but it's putting the results out there in case researchers can use them to develop treatments for COVID-19.

Detecting the outbreak and spread of new diseases

Artificial-intelligence systems were thought to be among the first to detect that the coronavirus outbreak, back when it was still localized to the Chinese city of Wuhan, could become a full-on global pandemic.

It's thought that AI-driven HealthMap, which is affiliated with the Boston Children's Hospital, picked up the growing cluster of unexplained pneumonia cases shortly before human researchers, although it only ranked the outbreak's seriousness as 'medium'.

"We identified the earliest signs of the outbreak by mining in Chinese language and local news media -- WeChat, Weibo -- to highlight the fact that you could use these tools to basically uncover what's happening in a population," John Brownstein, professor of Harvard Medical School and chief innovation officer at Boston Children's Hospital, told the Stanford Institute for Human-Centered Artificial Intelligence's COVID-19 and AI virtual conference.

Human epidemiologists at ProMed, an infectious-disease-reporting group, published their own alert just half an hour after HealthMap, and Brownstein also acknowledged the importance of human virologists in studying the spread of the outbreak.

"What we quickly realized was that as much it's easy to scrape the web to create a really detailed line list of cases around the world, you need an army of people, it can't just be done through machine learning and web scraping," he said. HealthMap also drew on the expertise of researchers from universities across the world, using "official and unofficial sources" to feed into the line list.

The data generated by HealthMap has been made public, to be combed through by scientists and researchers looking for links between the disease and certain populations, as well as containment measures. The data has already been combined with data on human movements, gleaned from Baidu, to see how population mobility and control measures affected the spread of the virus in China.

HealthMap has continued to track the spread of coronavirus throughout the outbreak, visualizing its spread across the world by time and location.

Spotting signs of a COVID-19 infection in medical images

Canadian startup DarwinAI has developed a neural network that can screen X-rays for signs of COVID-19 infection. While using swabs from patients is the default for testing for coronavirus, analyzing chest X-rays could offer an alternative to hospitals that don't have enough staff or testing kits to process all their patients quickly.

Darwin AI released COVID-Net as an open-source system, and "the response has just been overwhelming", says DarwinAI CEO Sheldon Fernandez. More datasets of X-rays were contributed to train the system, which has now learned from over 17,000 images, while researchers from Indonesia, Turkey, India and other countries are all now working on COVID-19. "Once you put it out there, you have 100 eyes on it very quickly, and they'll very quickly give you some low-hanging fruit on ways to make it better," Fernandez said.

The company is now working on turning COVID-Net from a technical implementation to a system that can be used by healthcare workers. It's also now developing a neural network for risk-stratifying patients that have contracted COVID-19 as a way of separating those with the virus who might be better suited to recovering at home in self-isolation, and those who would be better coming into hospital.

Monitoring how the virus and lockdown is affecting mental health

Johannes Eichstaedt, assistant professor in Stanford University's department of psychology, has been examining Twitter posts to estimate how COVID-19, and the changes that it's brought to the way we live our lives, is affecting our mental health.

Using AI-driven text analysis, Eichstaedt queried over two million tweets hashtagged with COVID-related terms during February and March, and combined it with other datasets on relevant factors including the number of cases, deaths, demographics and more, to illuminate the virus' effects on mental health.

The analysis showed that much of the COVID-19-related chat in urban areas was centered on adapting to living with, and preventing the spread of, the infection. Rural areas discussed adapting far less, which the psychologist attributed to the relative prevalence of the disease in urban areas compared to rural, meaning those in the country have had less exposure to the disease and its consequences.

There are also differences in how the young and old are discussing COVID-19. "In older counties across the US, there's talk about Trump and the economic impact, whereas, in young counties, it's much more problem-focused coping; the one language cluster that stands out there is that in counties that are younger, people talk about washing their hands," Eichstaedt said.

"We really need to measure the wellbeing impact of COVID-19, and we very quickly need to think about scalable mental healthcare and now is the time to mobilize resources to make that happen," Eichstaedt told the Stanford virtual conference.

Forecasting how coronavirus cases and deaths will spread across cities – and why

Google-owned machine-learning community Kaggle is setting a number of COVID-19-related challenges to its members, including forecasting the number of cases and fatalities by the city as a way of identifying exactly why some places are hit worse than others.

"The goal here isn't to build another epidemiological model… there are lots of good epidemiological models out there. Actually, the reason we have launched this challenge is to encourage our community to play with the data and try and pick apart the factors that are driving the difference in transmission rates across cities," Kaggle's CEO Anthony Goldbloom told the Stanford conference.

Currently, the community is working on a dataset of infections in 163 countries from two months of this year to develop models and interrogate the data for factors that predict spread.

Most of the community's models have been producing feature-importance plots to show which elements may be contributing to the differences in cases and fatalities. So far, said Goldbloom, latitude and longitude are showing up as having a bearing on COVID-19 spread. The next generation of machine-learning-driven feature-importance plots will tease out the real reasons for geographical variances.

"It's not the country that is the reason that transmission rates are different in different countries; rather, it's the policies in that country, or it's the cultural norms around hugging and kissing, or it's the temperature. We expect that as people iterate on their models, they'll bring in more granular datasets and we'll start to see these variable-importance plots becoming much more interesting and starting to pick apart the most important factors driving differences in transmission rates across different cities. This is one to watch," Goldbloom added.


1. Artificial intelligence can help address coronavirus - if applied in a creative way.
2. It is up to us to identify new and innovative ways to leverage what AI can do.
3. Examples include identifying patterns in coronavirus-related research and helping with diagnostics.

Artificial intelligence (AI) has the potential to help us tackle the pressing issues raised by the COVID-19 pandemic. It is not the technology itself, though, that will make the difference but rather the knowledge and creativity of the humans who use it.

Indeed, the COVID-19 crisis will likely expose some of the key shortfalls of AI. Machine learning, the current form of AI, works by identifying patterns in historical training data. When used wisely, AI has the potential to exceed humans not only through speed but also by detecting patterns in that training data that humans have overlooked.

However, AI systems need a lot of data, with relevant examples in that data, in order to find these patterns. Machine learning also implicitly assumes that conditions today are the same as the conditions represented in the training data. In other words, AI systems implicitly assume that what has worked in the past will still work in the future.


Imaging COVID-19 AI initiative is a multicenter European project to enhance computed tomography (CT) in the diagnosis of COVID-19 by using artificial intelligence. The project group will create a deep learning model for automated detection and classification of COVID-19 on CT scans, and for assessing disease severity in patients by quantification of lung involvement.

Many different hospitals and institutions across Europe will collaborate to rapidly develop an artificial intelligence solution in this time-sensitive research project. The AI model will be made freely available to all participants for clinical validation.


Abbott Laboratories is unveiling a coronavirus test that can tell if someone is infected in as little as five minutes, and is so small and portable it can be used in almost any health-care setting.

The medical-device maker plans to supply 50,000 tests a day starting April 1, said John Frels, vice president of research and development at Abbott Diagnostics. The molecular test looks for fragments of the coronavirus genome, which can quickly be detected when present at high levels. A thorough search to definitively rule out an infection can take up to 13 minutes, he said.

Abbott has received emergency use authorization from the U.S. Food and Drug Administration “for use by authorized laboratories and patient care settings,” the company said on Friday.

The U.S. has struggled to supply enough tests to detect the virus, even as the outbreak threatens to overwhelm hospitals in New York, California, Washington and other regions. After initially restricting testing to high-risk people, and problems with a test designed by the Centers for Disease Control and Prevention, U.S. regulators have rushed out diagnostics made by the world’s leading commercial-testing companies.

relates to Abbott Launches 5-Minute Virus Test for Use Almost Anywhere

“This is really going to provide a tremendous opportunity for front-line caregivers, those having to diagnose a lot of infections, to close the gap with our testing,” Frels said. “A clinic will be able to turn that result around quickly, while the patient is waiting.”

The technology builds on Illinois-based Abbott’s ID Now platform, the most common point-of-care test currently available in the U.S., with more than 18,000 units spread across the country. It is widely used to detect influenza, strep throat and respiratory syncytial virus, a common bug that causes cold-like symptoms.

The test starts with taking a swab from the nose or the back of the throat, then mixing it with a chemical solution that breaks open the virus and releases its RNA. The mixture is inserted into an ID Now system, a small box weighing just under 7 pounds that has the technology to identify and amplify select sequences of the coronavirus genome and ignore contamination from other viruses.

The equipment can be set up almost anywhere, but the company is working with its customers and the Trump administration to ensure the first cartridges used to perform the tests are sent to where they are most needed. They are targeting hospital emergency rooms, urgent-care clinics and doctors’ offices.

Last week, Abbott’s m2000 RealTime system got U.S. Food and Drug Administration approval for use in hospitals and molecular laboratories to diagnose the infection. That system can churn through more tests on a daily basis, up to 1 million a week, but it takes longer to get the results. Abbott plans to provide at least 5 million tests a month between the two systems.

Other companies are also rolling out faster-testing systems. Henry Schein Inc. on Thursday said its point-of-care antibody test, which looks for evidence that a person’s immune system has already fought off the infection, was available. The blood test can be given at the point of care and delivers results in about 15 minutes, though it can’t be used to definitively diagnose a current infection.


করোনাভাইরাসে আক্রান্ত ব্যক্তি ও উপদ্রুত এলাকা চিহ্নিত করতে সব গ্রাহকের মোবাইল ফোনে পাঁচটি করে প্রশ্ন পাঠানো হচ্ছে। সেই প্রশ্নের উত্তরের ভিত্তিতে আক্রান্ত ব্যক্তি ও এলাকার ডিজিটাল ম্যাপ তৈরি করবে সরকার। এতে করে কোন এলাকায় কে রোগী, তা সহজেই চিহ্নিত করা যাবে। গত রোববার থেকে সীমিত আকারে এসএমএম পাঠানো শুরু হয়েছে বলে জানা গেছে।

জানতে চাইলে টেলিযোগাযোগমন্ত্রী মোস্তাফা জব্বার প্রথম আলোকে বলেন, ‘পুরো বাংলাদেশের ডিজিটাল ম্যাপ আমাদের হাতে আছে। এই কাজ সেই ম্যাপ ধরেই করা হচ্ছে। ম্যাপের সঙ্গে সব তথ্য যুক্ত করার পরপর কেউ ঝুঁকিপূর্ণ এলাকার থেকে বাইরে গেলেও আমরা জানতে পারব। তিনি বলেন, এই কাজের সঙ্গে এটুআই, ন্যাশনাল টেলিকমিউনিকেশন মনিটরিং সেন্টার (এনটিএমসি), স্বাস্থ্য মন্ত্রণালয়, স্বরাষ্ট্র মন্ত্রণালয় এবং মোবাইল অপারেটরদের সংযুক্ত করা হয়েছে।’

এনটিএমসির একজন কর্মকর্তা জানান, যে পাঁচটি প্রশ্ন সব গ্রাহকের কাছে পাঠানো হবে, সেগুলো হলো বয়স কত, জ্বর, কাশি ও শ্বাসকষ্ট আছে কি না, সম্প্রতি বিদেশ থেকে ফেরা কারও সংস্পর্শে এসেছেন কি না, করোনায় আক্রান্ত কারও সংস্পর্শে এসেছেন কি না এবং দীর্ঘমেয়াদি কোনো অসুখে ভুগছেন কি না।

গ্রাহকেরা এসব প্রশ্নের উত্তর এসএমএস আকারে পাঠাতে পারবেন, চাইলে ফোনও করতে পারবেন। নিজের মোবাইল ফোন থেকেও *৩৩৩২# ডায়াল করে কোনো চার্জ ছাড়াই তথ্য জানাতে পারবেন। সবই হবে টোলফ্রি। ইন্টারনেট ব্যবহারকারীরা এই ঠিকানাতে ঢুকে তথ্য দিতে পারবেন। এর বাইরেও বিকাশ, জিপি, রবি, বাংলালিংক ও উবারের অ্যাপের মাধ্যমে সহজেই তথ্য জানাতে পারবেন। তথ্য জানানোর জন্য কাউকে ঘণ্টার পর ঘণ্টা অপেক্ষা করতে হবে না। সঙ্গে সঙ্গে জানাতে পারবেন। দিনে লাখ লাখ দেওয়া যাবে।

সংশ্লিষ্ট কর্মকর্তারা জানান, প্রতি ছয় ঘণ্টা পরপর মোবাইল অপারেটররা এই তথ্য এনটিএমসির কাছে হস্তান্তর করবে। তারা সেই তথ্যের ভিত্তিতে ডিজিটাল ম্যাপ তৈরি করবে। এই ম্যাপ হবে ৯৫ থেকে ৯৮ শতাংশই বিশ্বাসযোগ্য। কারণ, ফোন গ্রাহকের সেটের শনাক্তকরণ নম্বর ও অবস্থান ধরে ম্যাপ করা হবে। এতে একই তথ্য দুবার আসবে না। মোবাইল ফোন কোম্পানি রবি এ কাজ প্রথম শুরু করেছে। পরে সব মোবাইল কোম্পানিকে এর সঙ্গে যুক্ত করা হয়েছে।

সরকারি সূত্র জানায়, মোবাইল ফোন কোম্পানিগুলোর হিসাবে সরকারি ছুটি বা বন্ধ ঘোষণার পর ঢাকা থেকে ১ কোটি ১০ লাখ গ্রামে চলে গেছে। এদের সঙ্গে বৃদ্ধ ও শিশুও রয়েছে। এসব লোকদের মধ্যে কেউ করোনাভাইরাস বহন করলে তা সহজেই সর্বত্র ছড়িয়ে যেতে পারে। এই ম্যাপের মাধ্যমে সে তথ্যও জানা যাবে। ম্যাপ তৈরির পর চিহ্নিত এলাকা ধরে ব্যবস্থা নেবে সরকার।

মন্ত্রী মোস্তাফা জব্বার বলেন, চীন ও দক্ষিণ কোরিয়া করোনা এলাকা চিহ্নিত করতে ডিজিটাল ম্যাপ ব্যবহার করে সুফল পেয়েছে। তারা ঘরে বসেই জানতে পেরেছে কোথায় কত রোগী হচ্ছে, কমছে না বাড়ছে। বাংলাদেশেরও ডিজিটাল ম্যাপ তৈরি ও তথ্য বিন্যাসের সক্ষমতা আছে। ডিজিটাল বাংলাদেশের সরকার এখন সেই পথেই হাঁটছে।


Pages: [1] 2 3