Tag: Lyle Ungar

Posted on

ASSET Center Inaugural Seed Grants Will Fund Trustworthy AI Research in Healthcare

by Devorah Fischler

Illustration credit: Melissa Pappas

Penn Engineering’s newly established ASSET Center aims to make AI-enabled systems more “safe, explainable and trustworthy” by studying the fundamentals of the artificial neural networks that organize and interpret data to solve problems.

ASSET’s first funding collaboration is with Penn’s Perelman School of Medicine (PSOM) and the Penn Institute for Biomedical Informatics (IBI). Together, they have launched a series of seed grants that will fund research at the intersection of AI and healthcare.

Teams featuring faculty members from Penn Engineering, Penn Medicine and the Wharton School applied for these grants, to be funded annually at $100,000. A committee consisting of faculty from both Penn Engineering and PSOM evaluated 18 applications and  judged the proposals based on clinical relevance, AI foundations and potential for impact.

Artificial intelligence and machine learning promise to revolutionize nearly every field, sifting through massive amounts of data to find insights that humans would miss, making faster and more accurate decisions and predictions as a result.

Applying those insights to healthcare could yield life-saving benefits. For example, AI-enabled systems could analyze medical imaging for hard-to-spot tumors, collate multiple streams of disparate patient information for faster diagnoses or more accurately predict the course of disease.

Given the stakes, however, understanding exactly how these technologies arrive at their conclusions is critical. Doctors, nurses and other healthcare providers won’t use such technologies if they don’t trust that their internal logic is sound.

“We are developing techniques that will allow AI-based decision systems to provide both quantifiable guarantees and explanations of their predictions,” says Rajeev Alur, Zisman Family Professor in Computer and Information Science and Director of the ASSET Center. “Transparency and accuracy are key.”

“Development of explainable and trustworthy AI is critical for adoption in the practice of medicine,” adds Marylyn Ritchie, Professor of Genetics and Director of the Penn Institute for Biomedical Informatics. “We are thrilled about this partnership between ASSET and IBI to fund these innovative and exciting projects.”

 Seven projects were selected in the inaugural class, including projects from Dani S. Bassett, J. Peter Skirkanich Professor in the Departments of Bioengineering, Electrical and Systems Engineering, Physics & Astronomy, Neurology, and Psychiatry, and several members of the Penn Bioengineering Graduate Group: Despina Kontos, Matthew J. Wilson Professor of Research Radiology II, Department of Radiology, Penn Medicine and Lyle Ungar, Professor, Department of Computer and Information Science, Penn Engineering; Spyridon Bakas, Assistant Professor, Departments of Pathology and Laboratory Medicine and Radiology, Penn Medicine; and Walter R. Witschey, Associate Professor, Department of Radiology, Penn Medicine.

Optimizing clinical monitoring for delivery room resuscitation using novel interpretable AI

Elizabeth Foglia, Associate Professor, Department of Pediatrics, Penn Medicine and the Children’s Hospital of Philadelphia

Dani S. Bassett, J. Peter Skirkanich Professor, Departments of Bioengineering and Electrical and Systems Engineering, Penn Engineering

 This project will apply a novel interpretable machine learning approach, known as the Distributed Information Bottleneck, to solve pressing problems in identifying and displaying critical information during time-sensitive clinical encounters. This project will develop a framework for the optimal integration of information from multiple physiologic measures that are continuously monitored during delivery room resuscitation. The team’s immediate goal is to detect and display key target respiratory parameters during delivery room resuscitation to prevent acute and chronic lung injury for preterm infants. Because this approach is generalizable to any setting in which complex relations between information-rich variables are predictive of health outcomes, the project will lay the groundwork for future applications to other clinical scenarios.

Read the full list of projects and abstracts in Penn Engineering Today.

Posted on

Bioengineering Contributes to “New COVID-19 Testing Technology at Penn”

César de la Fuente, Ph.D., a Presidential Assistant Professor in Psychiatry, Microbiology, and Bioengineering, is leading a team to develop an electrode that can be easily printed at low cost to provide COVID-19 test results from your smart phone.

A recent Penn Medicine blog post surveys the efforts across Penn and the Perelman School of Medicine to develop novel says to detect SARS-CoV-2 and features several Department of Bioengineering faculty and Graduate Group members, including César de la Fuente, Presidential Assistant Professor in Psychiatry, Microbiology, and Bioengineering; Arupa Ganguly, Professor in Genetics; A.T. Charlie Johnson, Rebecca W. Bushnell Professor in Physics and Astronomy; Lyle Ungar, Professor in Computer and Information Science; and Ping Wang, Associate Professor in Pathology and Laboratory Medicine.

Read “We’ll Need More than Vaccines to Vanquish the Virus: New COVID-19 Testing Technology at Penn” by Melissa Moody in Penn Medicine News.

Posted on

An ‘Electronic Nose’ to Sniff Out COVID-19

by Erica K. Brockmeier

Postdoc Scott Zhang at work in the Johnson lab. (Photo: Eric Sucar, University Communications)

Even as COVID-19 vaccines are being rolled out across the country, the numerous challenges posed by the pandemic won’t all be solved immediately. Because herd immunity will take some time to reach and the vaccine has not yet been approved for some groups, such as children under 16 years of age, the coming months will see a continued need for tools to rapidly track the disease using real-time community monitoring.

A team of Penn researchers is working on a new “electronic nose” that could help track the spread of COVID-19. Led by physicist Charlie Johnson, the project, which was recently awarded a $2 million grant from the NIH, aims to develop rapid and scalable handheld devices that could spot people with COVID-19 based on the disease’s unique odor profile.

Dogs and devices that can detect diseases

Long before “coronavirus” entered into the vernacular, Johnson was collaborating with Cynthia Otto, director of the Penn Vet Working Dog Center, and Monell Chemical Senses Center’s George Preti to diagnose diseases using odor. Diseases are known to alter a number of physical processes, including body odors, and the goal of the collaboration was to develop new ways to detect the volatile organic compounds (VOCs) that were unique to ovarian cancer.

The next step is to scale down the current device, and the researchers are aiming to develop a prototype for testing on patients within the next year.

Since 2012, the researchers have been developing new ways to diagnose early-stage ovarian cancer. Otto trained dogs to recognize blood plasma samples from patients with ovarian cancer using their acute sense of smell. Preti, who passed away last March, was looking for the specific VOCs that gave ovarian cancer a unique odor. Johnson developed a sensor array, an electronic version of the dog’s nose, made of carbon nanotubes interwoven with single-stranded DNA. This device binds to VOCs and can determine samples that came from patients with ovarian cancer.

Last spring, as the pandemic’s threat became increasingly apparent, Johnson and Otto shifted their efforts to see if they could train their disease-detecting devices and dogs to spot patients with COVID-19.

Continue reading at Penn Today.

N.B.: A.T. Charlie Johnson, Rebecca W. Bushnell Professor of Physics and Astronomy at the Penn School of Arts & Sciences, and Lyle Ungar, Professor in Computer and Information Science at Penn Engineering and Psychology at the School of Arts & Sciences, are both members of the Penn Bioengineering Graduate Group.

Posted on

Lyle Ungar: ‘Philadelphia Needs More Contact Tracers’

Lyle Ungar, Ph.D. (Photo: Eric Sucar)

In May, Lyle Ungar, Professor of Computer and Information Science and Angela Duckworth, Rosa Lee and Egbert Chang Professor in Penn Arts & Sciences and the Wharton School, contributed to a New York Times op-ed on how to slow the COVID-19 pandemic through a culture of mask-wearing.

As infections continue to rise, Ungar and Duckworth are following up with another op-ed. Writing in the Philadelphia Inquirer, they outline the need to rapidly ramp-up the city and state’s contact tracing capacity:

Guidelines from health officials suggest Pennsylvania needs about 4,000 contact tracers, including 2,000 for the Philadelphia metro area. Our state has been operating with fewer than 200.

Continue reading Ungar and Duckworth’s op-ed at the Philadelphia Inquirer.

Originally posted on the Penn Engineering blog. Media contact Evan Lerner.

Lyle Ungar is a Professor of Computer and Information Science (CIS) and a member of the Penn Bioengineering Graduate Group. Read more stories about the coronavirus pandemic written by Lyle Ungar here.

Posted on

Lyle Ungar on Normalizing Face Masks

As scientists continue to battle the novel coronavirus, public health officials maintain that wearing a face mask is a powerful way to curb the spread of the virus and keep communities safe. However, America has struggled to adopt this change, as compared to other countries that have made wearing a face mask an unremarkable aspect of their culture.

Lyle Ungar, Ph.D.

In an opinion piece for the New York Times, Lyle Ungar, Professor of Computer and Information Science, Angela Duckworth, Rosa Lee and Egbert Chang Professor in Penn Arts & Sciences and the Wharton School, and Ezekiel J. Emanuel, Professor of Medical Ethics and Health Policy in Penn’s Perelman School of Medicine, propose a new approach to increase consistent face mask use among Americans: make wearing a mask “easy,” “understood,” and “expected.”

In their article, Ungar, Duckworth, and Emanuel make reference to communities that provided face masks free of charge for residents and note the decrease in infection in these areas. In addition, they point out how uncertainty about the necessity of face masks in the U.S. has led to public confusion which inhibits trust and use of masks. Finally, the three researchers push for a shift in social norms to embrace wearing a face mask as standard in America for the near future.

Some of Ungar’s recent research is also focused on the pandemic, including a “COVID Twitter map,” created with colleagues at the World Well-Being Project and Penn Medicine’s Center for Digital Health. Their map helps show, in real time, how people across the country perceive the virus and how it is affecting their mental health.

Read more about Ungar, Duckworth, and Emanuel’s strategy for normalizing face masks in their opinion piece for the New York Times.

Originally posted on the Penn Engineering blog.

Lyle Ungar is a Professor of Computer and Information Science (CIS) and a member of the Penn Bioengineering Graduate Group.

Posted on

Language in Tweets Offers Insight Into Community-level Well-being

In a Q&A, researcher Lyle Ungar discusses why counties that frequently use words like ‘love’ aren’t necessarily happier, plus how techniques from this work led to a real-time COVID-19 wellness map.

By Michele W. Berger

Lyle Ungar, Ph.D. (Photo: Eric Sucar)

People in different areas across the United States reacted differently to the threat of COVID-19. Some imposed strict restrictions, closing down most businesses deemed nonessential; others remained partially open.

Such regional distinctions are relatively easy to quantify, with their effects generally understandable through the lens of economic health. What’s harder to grasp is the emotional satisfaction and happiness specific to each place, a notion ’s has been working on for more than five years.

In 2017, the group published the , a free, interactive tool that displays characteristics of well-being by county based on Census data and billions of tweets. Recently, WWBP partnered with ’s Center for Digital Health to create a , which reveals in real time how people across the country perceive COVID-19 and how it’s affecting their mental health.

That map falls squarely in line with a paper published this week in the by computer scientist , one of the principal investigators of the World Well-Being Project, and colleagues from Stanford University, Stony Brook University, the National University of Singapore, and the University of Melbourne.

By analyzing 1.5 billion tweets and controlling for common words like “love” or “good,” which frequently get used to connote a missing aspect of someone’s life rather than a part that’s fulfilled, the researchers found they could discern subjective well-being at the county level. “We have a long history of collecting people’s language and asking people who are happier or sadder what words they use on Facebook and on Twitter,” Ungar says. “Those are mostly individual-level models. Here, we’re looking at community-level models.”

In a conversation with Penn Today, Ungar describes the latest work, plus how it’s useful in the time of COVID-19 and social distancing.

Read Ungar’s Q&A at .

Dr. Lyle Ungar is a Professor of Computer and Information Science and a member of the Department of Bioengineering Graduate Group.

Posted on

Five Tips to Stay Positive and Healthy During Social Isolation

Though the coronavirus situation is changing daily, even hourly, by now the need for physical separation from those not in your household is clear. That doesn’t mean it’s easy, says Penn psychologist Melissa Hunt.

“We’re social animals,” says Hunt, associate director of clinical training in Penn’s Psychology Department. “We have an entire neuroendocrine system that responds to touch and social proximity with people we care about, that contributes to our sense of well-being and connection in the world. Losing out on that is really hard.”

It’s also not something we’ve really been asked to do before, says Lyle Ungar, a Penn computer scientist who is part of the World Well-Being Project, an initiative that uses social media language to measure psychological well-being and physical health. “This is an experiment on a scale that we’ve never seen in the United States,” he says.

Ungar and Hunt offer some suggestions to stay positive and healthy in the face of this new social isolation.

1. Maintain a connection with the people you love, even if it can’t be a physical one. 

“Social distance does not mean no social contact,” Ungar says. Psychologically, face-to-face conversations are best, but right now they’re not likely possible. Instead, Ungar suggests video calls. “They’re second best in terms of emotional bonding,” he says. “Phone calls aren’t as good as video chats, and texting is even worse. But of course, being totally isolated is the worst.”

Read the full five tips at Penn Today. Media contact Michele W. Berger.

Melissa G. Hunt is the associate director of clinical training in the Department of Psychology in the School of Arts and Sciences at the University of Pennsylvania. 

Lyle Ungar is a professor in the departments of Bioengineering and Computer and Information Science in the School of Engineering and Applied Science, in the Graduate Group in Genomics and Computational Biology in the Perelman School of Medicine, in the Department of Operations, Information, and Decisions in the Wharton School, and in the Department of Psychology in the School of Arts and Sciences.