Two data scientists say they’ve created AI algorithms that can do in a week what biological researchers might otherwise spend years trying to pull off in a laboratory: discover antibody-based treatments that have a fighting chance to beat back COVID-19.

In fact, studies have shown it takes an average of five years and half a billion dollars to find and fine-tune antibodies in a lab, Andrew Satz and Brett Averso, both execs of a 12-member startup called EVQLV, explain.

Speaking with their alma mater, Columbia University’s Data Science Institute, Satz and Averso say their machine-learning algorithms can help by cutting the chances of costly experimental failures in the lab.

“We fail in the computer as much as possible to reduce the possibility of downstream failure in the laboratory,” Satz tells the institute’s news division. “[T]hat shaves a significant amount of time from laborious and time-consuming work.”

EVQLV is working on the advancement with Immunoprecise Antibodies (IPA), a bioscience research company concentrating on discovering therapeutic antibodies.

The collaboration “will accelerate the effort to develop therapeutic candidates against COVID-19,” according to the news report. “EVQLV will identify and screen hundreds of millions of potential antibody treatments in only a few days—far beyond the capacity of any laboratory.”

With the algorithmic screening complete, IPA will produce and test the most promising antibody candidates, the school reports.

“Speeding up the first stage of the process—antibody discovery—goes a long way toward expediting the discovery of a treatment for COVID-19.”

Some look like people in robot costumes. Some look like microwave ovens on wheels. All helped healthcare workers in Wuhan, China, avoid contracting COVID-19 while caring for hospitalized patients who had the illness.

The machines are the 14 robots that all but led operations at a field hospital in the city that is the Ground Zero of the raging global pandemic.

CNBC has the story in words and videos.

One quick clip shows the technology, developed by CloudMinds of Beijing, checking peoples’ temperature with infrared thermometry. When someone enters the hospital with an elevated body temperature and other signs of fever, the device alerts medical staff.

The robots range in cost from $17,000 to $72,000 apiece.

A model at the high end works with an AI platform that syncs with smart bracelets and rings worn by patients. At the height of Wuhan’s coronavirus crisis, it was “able to monitor patient vital signs, allowing doctors and nurses outside the facility to monitor all patient vital information remotely on one interface,” CloudMinds CEO Bill Huang tells CNBC.

Read the item and view the videos:

Tampa General Hospital in Florida has admitted three patients with COVID-19. Halfway around the world, Sheba Medical Center in Israel has seen 40. Both expect exponential increases—and both are using new AI applications to respond.  

Specifically, Tampa General is installing an algorithmic system to instantaneously identify fever in visitors. It works with facial recognition software.

Meanwhile, Sheba is monitoring COVID-positive patients with an AI-powered sensor placed under their mattresses. Continuously analyzing patterns in these patients’ heart activity, respiration and body movements, the sensor alerts staff when someone seems headed for respiratory failure or sepsis.

The Wall Street Journal posted coverage of the installations March 20.

Tampa General’s system uses cameras positioned at visitor entrances to pick up on not only thermal data but also sweating and facial discoloration, the paper reports.

The objective is to screen visitors for fever and block those who are feverish, John Couris, president and CEO, tells reporter Jared Council.

Couris says the system is “part of an outbreak-response plan to reduce normal foot traffic at Tampa General by three-quarters,” Council writes. Couris emphasizes that the goal is to “keep people that don’t really need to be in the hospital out of the hospital.”

Both systems were developed locally to the provider institutions—Tampa General’s AI-powered visitor screening by Orlando-based Care.ai and Sheba’s under-mattress monitor by Israeli medical-devices company EarlySense.

WSJ reporter Council also quotes Gregg Pessin, an industry analyst from Gartner. Noting that both the technologies in the article are new, Pessin says the most effective AI applications are likely to be those installed before the pandemic.

“The [AI technologies] that have proven themselves with other infectious diseases,” Pessin says, “we can have higher expectations of them.”

Read the whole thing:

The coronavirus crisis continues to unite heretofore unaffiliated technology powerhouses at the forefront of AI and other forms of IT innovation in healthcare. The trend continued March 26 with the launch of a multifaceted, far-flung and very well-funded institute.

Its initial aim: pitting the best AI can bring to the fight against COVID-19.

Called the C3.ai Digital Transformation Institute, or C3.ai DTI for short, the effort gets its first name from the AI software company headquartered in Redwood City, Calif.

C3.ai’s partners in the work include Microsoft, the University of California, Berkeley, Princeton University, the University of Chicago, the Massachusetts Institute of Technology, Carnegie Mellon University, the University of Illinois at Urbana-Champaign (UIUC) and the latter’s National Center for Supercomputing Applications.

The C3.ai DTI will have as its mission “accelerating the application of artificial intelligence to speed the pace of digital transformation in business, government and society,” according to the March 26 announcement. It will be jointly managed by UC Berkeley and UIUC.

The initial project is a call for research proposals for advancing ways to slow or stop COVID-19 and future pandemics using AI. Subsequent calls for research proposals are to follow on a biannual basis.

Examples of sought proposals include those that apply machine learning and other AI methods to mitigate the spread of the COVID-19 pandemic, design or repurpose drug design and improve societal resilience in response to the spread of the COVID-19 pandemic.

The institute plans to offer researchers as many as 26 cash awards per year, each ranging from $100,000 to $500,000.

It’s also allotting $750,000 annually to compensate visiting professors and researchers who support its participating scholars, as well as providing free access to Microsoft’s Azure cloud and C3 AI Suite resources and several other supports and perks.

Overall, C3.ai plans to offer nearly $57.3 million in cash contributions over the first five years of the DTI’s operation.

The compute resources from C3.ai and Microsoft will amount to an additional $310 million of in-kind contributions.

“We are collecting a massive amount of data about MERS, SARS and now COVID-19,” says Condoleezza Rice, former U.S. Secretary of State and a member of C3.ai’s board of directors. “We have a unique opportunity before us to apply the new sciences of AI and digital transformation to learn from these data how we can better manage these phenomena and avert the worst outcomes for humanity. I can think of no work more important and no response more cogent and timely than this important public-private partnership.”

The launch comes during the same week in which similarly aggressive and broad-based efforts to deploy supercomputing in the war against COVID-19 were announced by the White House and Amazon Web Services.

Mayo Clinic researchers have found that primary care providers welcome the concept of AI-based clinical decision support (CDS) while preferring not to use the technology—at least as configured for their tryout adoption—in day-to-day practice.

In a study slated to be published in the May edition of the International Journal of Medical Informatics, Santiago Romero-Brufau, MD, PhD, and colleagues describe their work anonymously surveying several dozen clinical staff in three primary-care clinics in Southwest Wisconsin.

Participants, whose number included nurses and social workers as well as physicians, completed surveys before and after implementation of an AI-based CDS system.

The CDS’s specific aim was to identify poor glycemic control in patients with diabetes. When the software flagged these patients, it alerted staff and offered recommendations for intervention.

Prior to the program’s installation, some 14 staff members said they felt unfavorably disposed toward the CDS. Only 11 viewed it in a positive light.

But after they’d used the system, a strong majority, 21 staff members, indicated they were favorably disposed. Only three said they didn’t like it.

And yet, despite the high ratings post-implementation, just 14% said they would recommend the AI-based CDS to peers.

Anecdotal feedback offered to the researchers showed the most appreciated aspect of the CDS was that it “promoted team [dialogue] about patient needs.”

The least appreciated aspect was the “inadequacy of the interventions” recommended by the CDS. These recommendations were widely perceived to be “poorly tailored, inappropriate or not useful,” the authors note.

In their discussion, the authors surmise that AI-based CDS tools perceived negatively by staff “may reduce staff excitement about AI technology, and hands-on experience with AI may lead to more realistic expectations about the technology’s capabilities.”

They urge AI developers to carefully distinguish between tasks well-suited for AI and those best left in the hands of humans.  

“AI may be poorly suited to assess nuanced aspects of care that involve personal and social factors and are not easily codified within the EHR,” Romero-Brufau et al. comment. “This reinforces that AI is unlikely to replace clinicians anytime in the foreseeable future. Yet, it may be useful as a tool used by trained clinicians, provided that it is carefully implemented in a way that is integrated within local workflows and provides relevant recommendations to augment the abilities of clinical practitioners.”

Researchers at the University of Massachusetts, Amherst, have developed a portable device that combines sensors with AI-based analysis to estimate how many people within a crowd seem to have a respiratory virus such as the seasonal flu or COVID-19.

The team’s idea is to initially place the devices in medical waiting areas, from where it would help prepare staff for caseload ebbs and flows. Later it might be set in larger public spaces, helping to monitor epidemiological trends at the population level.

The device, which the inventors are calling FluSense, processes data from thermal images of people in groups and from audio captures of such sounds as coughing, sneezing and, presumably, groaning with discomfort.

According to the study, running in the March edition of the Proceedings of the Association for Computing Machinery on Interactive, Mobile, Wearable and Ubiquitous Technologies, senior author Tauhidur Rahman, PhD, and team fed their platform more than 350,000 thermal images and 21 million non-speech audio samples from hospital waiting areas at UMass’s University Health Services clinic.

The researchers found the setup could predict daily patient counts with a high level of accuracy.

Further, comparing predictions from the devices against lab-confirmed flu cases, they found their sensor-based features “strongly correlated with laboratory-confirmed influenza trends.”

The device stores no speech, sound or image data that could be used to identify individuals. Its deep neural network draws boundaries around thermal images representing group members, while its audio analyzer distinguishes between speech and non-speech sounds associated with respiratory illness.

The study’s lead author, PhD candidate Forsad Al Hossain, tells the university’s news division FluSense showcases the power of AI combined with edge computing done at or near the source of the data.

“We are trying to bring machine-learning systems to the edge,” Al Hossain says. “All the processing happens right here. These systems are becoming cheaper and more powerful.”

UMass epidemiologist Andrew Lover, PhD, MPH, says the study proves the concept that specific coughing sounds correspond with flu-related illness. “Now we want to validate it beyond this specific hospital setting,” he adds, “and show that we can generalize across locations.”

Click here to access the study and here to read the full UMass-Amherst news item.

Researchers are finalizing a new AI-powered smartphone app for assessing a user’s risk of being infected with the new coronavirus. Once complete, the app will be made free to the public.

More than 3,300 people around the world have died from COVID-19 so far, according to the latest statistics, and nearly 100,000 patients have been infected with the disease.  

Arni S.R. Srinivasa Rao, PhD, and Jose A. Vazquez, MD, both of the Medical College of Georgia in Augusta, led the development of this new technology. The researchers shared their findings in Infection Control & Hospital Epidemiology.

“We wanted to help identify people who are at high risk for coronavirus, help expedite their access to screening and to medical care and reduce spread of this infectious disease,” Rao said in a prepared statement.

“We are trying to decrease the exposure of people who are sick to people who are not sick,” Vazquez added.

The app surveys users, asking them for key demographic information and exploring their recent travel histories. Questions also cover symptoms commonly associated with COVID-19. An AI algorithm then kicks in, telling the user their level of risk and alerting a nearby healthcare facility if necessary.

The app—expected to be live in a matter of weeks—will be made available to the public on the august.edu domain. The researchers also hope to make it available in common app stores.

The Healthcare Information and Management Systems Society (HIMSS) has officially canceled its 2020 annual meeting in Orlando, Florida, due to continued concerns over the new coronavirus.

This marks the first time in 58 years the conference has been canceled. The event, which was scheduled to take place March 9-13, typically draws more than 40,000 health IT professionals from all over the world.

HIMSS officials said recent reports from the World Health Organization (WHO) and Centers for Disease Control and Prevention (CDC)—and additional experts in this area—were taken into account when reaching this decision.

“In coordination with an external advisory panel of medical professionals to support evidence-based decision making, it is clear that it would be an unacceptable risk to bring so many thousands of people together in Orlando next week,” according to a statement from Karen D. Groppe, senior director of strategic communications for HIMSS. “The advisory panel recognized that industry understanding of the potential reach of the virus has changed significantly in the last 24 hours, which has made it impossible to accurately assess risk.”

This is not the first healthcare conference to be affected by COVID-19. The European Society of Radiology, for instance, announced it would delay its annual meeting, originally planned for March 11-15 in Vienna. The American Physical Society also canceled its own meeting, scheduled to take place in Denver March 2-6.

Meanwhile, the American College of Cardiology (ACC) still plans to hold its annual meeting, ACC 2020, March 28-30 in Chicago.

“The ACC continues to closely monitor health and safety updates and recommendations issued by the WHO and CDC, as well as state and local health organizations,” Timothy W. Attebery, CEO of the ACC, said in a statement.

The newly incorporated American Board of Artificial Intelligence in Medicine (ABAIM) is soon to begin credentialing healthcare workers in AI, machine learning and deep learning.

The group announced its intentions March 9, noting that it was only recently incorporated as a not-for-profit entity.

ABAIM’s main activity will be awarding board certification to individuals who pass an exam demonstrating a firm grasp of advanced concepts related to AI and its iterations used in healthcare.  

The certification also will validate the ability of those so certified to analyze the benefits and pitfalls of these technologies in real-world scenarios.

The ABAIM says its ultimate goal is to “enable healthcare professionals to participate in development, assessment, selection and implementation of AI, machine learning and deep learning tools for their benefit and that of the institutions they serve today and in the future.”

Two physicians are serving as the board’s chairs and driving the initiative: Orest Boyko, MD, PhD, a psychology research professor at the University of Southern California; and Anthony Chang, MD, of the Sharon Disney Lund Medical Intelligence and Innovation Institute (MI3) at Children’s Hospital of Orange County in California.

Artificial Intelligence and its related technologies are “increasingly important to healthcare as a whole,” Boyko said.

Chang added that ABAIM has a modular curriculum that will enable a wide range of healthcare professionals—as well as patients, data scientists and IT personnel—to become knowledgeable in the application of AI, ML and DL tools and technologies.

A new AI app is hitting the market that could predict sickness before a person even appears sick.

Achu Health, a health and wellness platform launching its SickScan app for iPhone, Apple Watch, Fitbit Versa and Ionic on March 31, tracks the ongoing outbreaks, trends and densities of cold and flu reports in the areas of its users, providing a real-time global health outlook.

The app works through machine learning algorithms that use data from the Apple Watch and matches it with personal health data patterns that can then predict oncoming sickness like cold or flu. These predictions can happen all before the person even starts feeling symptoms. Namely, it asks three daily questions to build a personal benchmark of the user based on how they feel. The app then guides users to improvement “at an achievable pace” with goals and personalized insights about their state of health.

Knowing a potential for sickness from the common cold or flu before symptoms appear can help users take proactive steps to prevent illness altogether or lessen the severity of illness.

“What is really cool about Achu Health is that it is the first app of its kind to highlight sickness patterns ahead of time, actually enabling users to take proactive steps to try to avoid sickness,” Tony Peticca, CEO of Achu, said in a statement. “Healthcare officials are asking people to be cautious, monitor symptoms, practice good hygiene, and lead an overall healthier lifestyle. Achu provides the tools to achieve all of this.”

The app also offers personalized, actionable goals to build and reinforce health lifestyle habits, according to the press release.

Achu Health uses Apple’s Core ML and HealthKit platforms to protect user information and perform calculations on-device.

The app’s launch comes at a time when the new coronavirus, COVID-19, has been declared a global pandemic, and serious action are being put into place to prevent further outbreak.