Machine Learning

Public Health

College of Public Health

Social Determinants of Health

Campus News

In This Story

Melissa J. Perry, Sc.D., MHS, MBA

Robert M. Weiler, PhD, MPH

91��’s AI in Public Health Summit examined what artificial intelligence (AI) could mean for health equity, education, and the future workforce.

The Future of Public Health in an AI-Enabled World with Dean Melissa Perry and Easan Selvan, National Director, Academic Medicine and Public Health, Microsoft. Photo by Heather Carroll/CPH

For a field built to prevent and respond to disruptions, public health now faces a defining new challenge: harnessing the rapidly evolving power of artificial intelligence.

“There are moments in every profession when it becomes clear that change is not simply coming, that it has already arrived,” said Robert Weiler, senior associate dean for academic affairs at the George Mason College of Public Health.

That urgency carried through George Mason’s inaugural AI in Public Health Summit, where conversations centered on what generative AI, machine learning, and large language models could mean for the future of research, education, and practice.

“Today’s meeting is not about AI,” said College of Public Health Dean Melissa Perry. “It’s about the future of public health.” The challenge, she argued, is not simply grasping AI, but preparing future public health professionals to leverage it in ways that benefit humanity.

To achieve that goal, the College of Public Health convened a brain trust of academics, practitioners, industry leaders, and students from across the country. Helping anchor the discussion was the Association of Schools and Programs of Public Health (ASPPH), whose AI task force is helping shape national conversations around responsible AI adoption in higher education and practice. According to ASPPH representatives, George Mason is “leading in this space” among its 150 member institutions.

Several themes emerged across the day:

We must lead or risk being left behind.

Keeping Public Health at the Center of AI: Reflections on the Association of Schools and Programs of Public Health Task Force Report. Photo by Heather Carroll/CPH

At this point, the debate has shifted from whether AI belongs in public health to how to use it responsibly and effectively.

“There’s no escaping it,” said Eduardo Ruiz, chief information officer for ASPPH, pointing to rapid adoption across health care systems, public health agencies, and higher education.

Arman Latif, chief information officer at the Virginia Department of Health, framed AI as “less of a tool, and more of a shift in mindset” for public health. While ethical, environmental, equity, and philosophical concerns abound, he argued that the field can't ignore a technology with such potential to improve operations and strengthen how agencies serve the public. “To not do it, in itself, is unethical,” he suggested.

In a field focused on prevention and “upstream thinking,” speakers pointed to the promise of AI to anticipate problems instead of reacting to them: forecasting outbreaks, detecting overdose trends earlier, identifying food insecurity patterns, and uncovering insights buried in massive datasets.

AI can assist, but humans still decide.

AI in Public Health Summit hosted by the College of Public Health at FUSE at Mason Square. Photo by Mary Cunningham/CPH

The summit’s optimism around AI came with a consistent caveat: the technology may support public health work, but it will never replace the people making decisions and serving communities.

Jamie Atchison, senior director of innovation and strategy at ASPPH, pointed to one of her group’s core recommendations: keep AI human-centered, using it as a tool for decision-makers rather than a replacement for human judgment.

In disease surveillance, for example, AI may help detect patterns and flag emerging outbreaks, but people still need to interpret findings and take action. AI may also help tailor public health messaging to specific populations, but humans remain responsible for judgment, nuance, and building trust.

“AI is a non-moral technology,” said Easan Selvan, national director of academic medicine and public health at Microsoft. “Whether or not we decide to use it for good … is incumbent upon” people and institutions, he said.

AI is a new social determinant of health.

Preparing the Public Health Workforce for an AI-Enabled Future: Practitioners' Perspectives panel with representatives from ICF, Virginia Department of Health, Fairfax County Health Department, and Association of State and Territory Health Officials. Photo by Heather Carroll/CPH

If public health gets AI right, speakers argued, the technology could help narrow longstanding health inequities. Get it wrong, and those gaps could deepen.

“The risks [are] that AI can be an inequity multiplier if we’re not careful, but in fact that is up to us,” Perry said.

AI is already influencing many drivers of health, from information access to employment and health services. “We’re really thinking of AI as a determinant of health,” Ruiz said.

Speakers repeatedly returned to one concern: AI systems reflect the data behind them. So, if that data excludes or underrepresents specific populations, the resulting tools risk reinforcing existing disparities.

AI could also improve equity, from identifying vulnerable populations earlier to helping smaller health departments and community organizations access tools and data once limited to better-funded institutions.

Classrooms are adapting in real time.

Banning AI outright in the classroom has become unrealistic, George Mason faculty and students emphasized during the summit’s student panel.

“People are going to be using it either way,” said biology major Anika Tahsin Siddiqui, arguing that faculty should set clearer expectations and encourage open conversation around AI use to reduce stigma.

Students described using AI to learn coding languages, organize notes, create visualizations and presentations, and study for exams. But they pushed back against AI as a substitute for learning itself.

Bridge-builders, translators, and critical thinkers are in demand.

Student Panel: Teach Us What We Need to Know: Student Voices on AI Skills for Public Health Practice. Photo by Heather Carroll/CPH

While AI literacy is quickly becoming nonnegotiable in public health roles, panelists repeatedly argued that deep technical mastery is not the end goal. Instead, they described a growing demand for “bridge professionals” who can move between worlds: understanding community needs, public health practice, and data systems well enough to connect them.

“The translator is really key,” said Tabatha Offutt-Powell, vice president for public health data modernization and informatics at the Association of State and Territorial Health Officials.

“Those who are early to understand, early to use, early to adapt will be the best prepared,” Ruiz said.

Stay tuned to the College of Public Health for deeper insights from specific panels, as well as recordings of the sessions.

Groundbreaking study reveals hidden complexity in human genetics

tdonnel — Mon, 12 Jan 2026 18:32:03 +0000

Groundbreaking study reveals hidden complexity in human genetics tdonnel Mon, 01/12/2026 - 13:32

In This Story

Amarda Shehu

Sometimes, in genetics, two wrongs do make a right. A research team recently showed that two harmful genetic variants, when occurring together in a gene, can restore function—proving a decades-old hypothesis originally proposed by Nobel laureate Francis Crick. Their study, published in the Proceedings of the National Academy of Sciences (PNAS), not only experimentally validated this theory but also introduced a powerful artificial intelligence (AI)-driven approach to genetic interpretation led by 91�� researchers.

The project began when Aimée Dudley, a geneticist at the Pacific Northwest Research Institute (PNRI), approached 91�� Chief AI Officer Amarda Shehu after following her lab’s work on frontier AI models for predicting the functional impact of genetic variation. That conversation sparked a collaboration that married PNRI’s experimental expertise with George Mason’s computational innovation to discover some surprising ways variant combinations can shape human health.

The problem

Every year one in three Americans is diagnosed with a genetic disorder. Symptoms manifest in infancy for about 70% of individuals. Sadly, 35% die before the age of 5. Advancements in clinical genomics offer hope to better understand and possibly treat these disorders.

“High-throughput genomic screening has been a wonderful feat for humanity,” said Shehu, “but one of its side effects is that it has produced massive amounts of data, outpacing our ability to interpret what that data means for health and disease.”

Research in the Shehu lab has for years focused on building frontier AI models to advance genetic interpretation, but all data available link only isolated, single variants to measured functional activity. Because each person's genome contains billions of base pairs, with about five million variants existing between two individuals’ genomes, looking at one variant at a time rather than combinations of variants could only reveal so much.

“It looked like we had hit a wall,” Shehu said, “that is, until Dr. Dudley contacted my lab more than a year ago.”

On the left, a 3D landscape derived from variant–variant measurements shows distinct functional regions emerging from pairwise interactions. On the right, these regions map onto a multimeric protein structure, where variants in separate spatial zones can be sequestered into different active sites, allowing functional recovery. This visualization captures the structural logic underlying positive epistasis and illustrates how AI-enabled analysis links genetic variation to protein function, a key, groundbreaking result Dudley and Shehu's labs published in the Proceedings of the National Academy of Sciences. Image provided.

The proof

Dudley’s lab was convinced that the key was to account for variant combinations in a gene, also called epistasis. They measured functional effects of variant combinations in the DNA of a key enzyme, argininosuccinate lyase (ASL), a lack of which results in urea cycle disorder, a rare but devastating condition.

The researchers tested thousands of variant combinations that resulted in no enzyme activity when on their own and found that a significant portion of them had high levels of enzyme activity when in combination with each other. In other words, two defective variants, when combined, can recover function.

“This was the most puzzling thing that I could not believe when Dr. Dudley showed it to me. Sometimes in biology, zero plus zero equals 100%,” said Shehu.

Shehu said that Crick, who shared the Nobel Prize in Physiology or Medicine 1962 with James Dewey Watson and Maurice Wilkins for their discoveries concerning the molecular structure of DNA, had hypothesized this could happen.

“Crick had a fancy word for it—variant sequestration,” said Shehu, “But until Dr. Dudley, no one had demonstrated it.”

The progress

Once Dudley’s lab confirmed the phenomenon experimentally, George Mason researchers turned to AI to see if it could predict similar effects across other genes. Using the ASL data from Dudley’s lab, George Mason computer science PhD student Anowarul Kabir developed a machine learning model to predict the effects of variant combinations. Then, he applied the model to a structurally similar but evolutionarily distinct protein, fumarase (FH). The algorithm achieved 99.6 percent accuracy in predicting regained function within ASL and 91 percent accuracy in FH.

“The really cool thing about this,” said Shehu, “is that the model learned both sequence and structural patterns and was able to transfer its knowledge to another gene.”

This breakthrough suggests that with experimental data from a few genes, AI can help scale variant effect prediction to a broad set of genes. The PNAS publication estimates that as many as 4% of the genes in the human genome could have the same types of effects seen for ASL and FH.

The paradigm shift

This breakthrough marks a paradigm shift in clinical genomics for precision medicine. By considering variant combinations rather than isolated, single variants, clinicians can deliver faster, more accurate diagnoses and life-saving interventions for families facing rare diseases. They can also prioritize therapeutic treatments based on specific epistatic profiles of patients or clinical trial participants.

“Clinical genomics has been stuck in a rut for decades. We’ve shown that you need to look at combinations of variants to fully understand their impact,” said Shehu. “Our AI model expands coverage from one gene to another, accelerating interpretation and bringing us closer to true precision medicine.”

Topics

DNA

Machine Learning in Health Care

Commonwealth Cyber Initiative (CCI)

Chef’s KISS: Statistics PhD candidate creates new recipe for complex spatial data analysis

tdonnel — Thu, 06 Mar 2025 20:40:50 +0000

Chef’s KISS: Statistics PhD candidate creates new recipe for complex spatial data analysis tdonnel Thu, 03/06/2025 - 15:40

In This Story

Ben Seiyon Lee

Jin Hyung Lee, a PhD candidate in the Department of Statistics, in collaboration with his advisor, Assistant Professor Ben Seiyon Lee, has developed novel statistical methodology for analyzing large-scale complex data that can be up to 3,600 times faster than the current standard. He will receive the Korean International Statistical Society (KISS) 2024 Outstanding Student Paper Award for his work and present about it at the American Statistical Association’s Joint Statistical Meetings (JSM) 2025 in Nashville, Tennessee.

The primary application of Lee’s methodology is in the analysis of high-resolution satellite image data, which is inherently complex and high-dimensional. A major challenge lies in predicting values at unobserved locations within the satellite imagery. While traditional spatial modeling methods are computationally intensive and time-consuming, Lee's novel approach offers a solution that is significantly faster. This development has significant implications for various fields, such as atmospheric sciences, ecology, public health, and medical imaging.

Jin Hyung Lee, photo provided

Lee’s research focuses on the application of variational inference to massive spatial datasets using a unique machine learning algorithm. Variational inference is a method used to approximate complex probability distributions when true inference is not possible, making it a powerful method for modeling complex spatial datasets. The proposed approach significantly improves the computational efficiency of spatial data analysis, achieving speeds up to three orders of magnitude faster than existing methods while maintaining comparable accuracy.

Lee's method can be used to predict weather patterns in remote and rapidly changing environments like the Gulf Coast, southern California, and polar regions like Alaska or Antarctica. The ability to process high-dimensional data quickly and accurately is crucial for making timely and informed decisions in these regions, especially when they are at risk of geophysical hazards such as hurricanes, wildfires, or sea ice loss. Additionally, the methodology has potential applications in infectious disease modeling and public health data analysis, where rapid and accurate predictions are essential for effective intervention and policymaking.

Lee's research is part of his broader dissertation work, which focuses on developing and applying variational inference techniques to various statistical models. His goal is to simplify these methods, making them more accessible to non-experts and applicable to a wide range of data types. By doing so, Lee aims to bridge the gap between advanced statistical methodologies and practical applications, enabling more efficient and effective data analysis across different fields.

At the JSM 2025, Lee will have the opportunity to present his research to a large audience of statisticians from around the world. The conference, which attracts over 5,000 participants annually, provides a platform for sharing cutting-edge research, networking with peers, and exploring new developments in the field of statistics. Lee’s presentation will be part of a session hosted by KISS, where he and other award recipients will showcase their work and receive their awards.

Receiving the KISS Outstanding Student Paper Award is a significant milestone in Lee’s academic journey. It not only recognizes his contributions to the field but also provides him with valuable exposure and opportunities for future collaboration. As Lee continues to advance his research, his innovative methodologies and their applications are poised to make a lasting impact on the field of statistics and beyond.

Topics

Department of Statistics

Computational statistics

Keeping data safe by keeping it separate

tdonnel — Tue, 25 Feb 2025 15:35:36 +0000

Keeping data safe by keeping it separate tdonnel Tue, 02/25/2025 - 10:35

Developing a robust cybersecurity system demands a lot of data, but keeping all that data in a single location introduces the risk of a data breach. Luckily, 91�� researcher Zhuangdi Zhu in the Department of Cyber Security Engineering specializes in federated learning, a method of decentralized machine learning that allows multiple entities to collaboratively train a machine learning model without sharing their raw data.

Zhu is using this expertise to assist Wajih Ul Hassan of the University of Virginia develop scalable host-based intrusion detection systems (HIDS). Together, Zhu and Hassan are leveraging artificial intelligence (AI) to enhance a given host’s cybersecurity while ensuring data privacy.

HIDS monitor and analyze the activities within a single host or device. These systems use data, such as system logs, web browsing logs, and process logs, to detect irregularities that may indicate a security threat. For example, Zhu noted, a HIDS might detect malicious software that prompts a browser to download a harmful PDF file. By identifying such irregularities, the HIDS can prevent potential security breaches. Central management of these logs through managed security service providers (MSSPs) on cloud servers, however, could potentially breach user privacy. Enter: federated learning.

Zhuangdi Zhu, photo provided

In a federated learning system, each entity trains a local model on its own data and only shares the model updates with a central server. Local models are trained on individual datasets, and their findings are sent to a central server, Zhu explained. The server then aggregates these parameters to create a global model, which is subsequently sent back to the local models. This iterative process continues until a robust and accurate model is developed. Federated learning thus ensures sensitive data remains within the local models, addressing privacy concerns and complying with data regulations.

The project, funded by the Commonwealth Cyber Initiative, is set to span one year, starting in the summer of 2025. In addition to developing a federated learning framework for HIDS, the team plans to create an open-source dataset for intrusion detection, which will serve as a valuable resource for future research and development in this field.

Zhu's work on decentralized machine learning not only addresses critical privacy concerns but also paves the way for more secure and efficient threat detection systems. Her work on this project represents a significant step forward in the ongoing effort to protect digital environments from evolving cyber threats.

In This Story

Zhuangdi Zhu

Learn more about George Mason's Department of Cyber Security Engineering

Topics

Cybersecurity

Physics PhD student is using machine learning techniques to unlock the key to predicting solar flares

Katarina Benson — Mon, 27 Jan 2025 14:44:24 +0000

Physics PhD student is using machine learning techniques to unlock the key to predicting solar flares Katarina Benson Mon, 01/27/2025 - 09:44

João Felipe Sousa Pereira’s research on solar flares could one day help us safeguard astronauts and technology in space and even prevent widespread blackouts here on Earth. Pereira, a second-year Physics PhD student at 91��, is studying solar physics with the goal of uncovering the precise triggers of solar flares.

João Felipe Sousa Pereira. Photo by Evan Cantwell/Office of University Branding

Pereira said solar flare prediction is key because really intense solar flares are often associated with coronal mass ejections (CMEs), which in turn can cause geomagnetic storms, carry radiation, and significantly contribute to space weather.

“CMEs, geomagnetic storms, and solar radiation can affect our satellites if we are unprepared. These events can also knock out our GPS or power grids on rare occasions,” he said. “What we really want is to figure out what is causing solar flares. We have some suspicions, but maybe machine learning techniques can find something we didn’t.”

There are already some prediction models in place now, but Pereira’s research is trying to push past the current “bottleneck” in the research. His work is not only trying to confirm previous techniques but also testing out a new one.

Pereira is the recipient of a Graduate Inclusion and Access scholarship, which works to enhance the diversity of the graduate student community at George Mason by providing scholarships for first-generation doctoral students who have been historically underrepresented within their doctoral field of study. The scholarship provides funding and an opportunities to become involved in the graduate community through special events each semester.

“The grade requirements [for the scholarship] are a little higher than those of my fellow grad students, but I think the hard work is rewarding and will help me stay on track to finish within the five years.”

João Felipe Sousa Pereira outside the Mason Observatory. Photo by Evan Cantwell/Office of University Branding

Pereira came to George Mason after completing his undergraduate degree in physics and astronomy at University of Maryland (UMD), College Park. He initially became interested in space weather his freshman year at UMD. “I had an introductory electricity and magnetism course. It seemed interesting to me to learn about solar wind, the types of phenomena that occur in space, and how the physics of it all actually impacts us on Earth.”

In his junior and senior years, Pereira worked on space weather research with his then-advisor Surjalal Sharma and became interested in continuing that research in his graduate studies. He then visited George Mason, where he met with his current advisor Jie Zhang of the Department of Physics and Astronomy. “[Zhang] helped me set up the possibilities for what can be done in this field, and he had the idea for the project that I'm working on now,” Pereira said.

On the same visit, Pereira had the opportunity to meet with graduate students who let him know that the PhD program wasn’t easy, but he would have the support he needed. He was able to see the graduate student culture with his own eyes, which helped him feel like he could belong at George Mason.

Pereira offers advice to other students considering PhD programs. “You should talk to as many people as possible—that can help guide your decision process. Some people have good experiences, some people have bad experiences, and they’re all valid. Everyone’s on their own path.”

“Pereira’s passion to research and commitment to his doctoral program are inspiring,” said Laurence Bray, senior associate provost for graduate education. “He represents the Mason Nation at heart by designing his own path to success with strength and resilience.”

Pereira’s enthusiasm for his research continues. “The reason I do physics is because I like figuring out how things work. And it's not necessarily easy, but in the end, when you have that ‘aha moment,’ it really is rewarding,” he said.

Learn more about Research at George Mason

Topics

College of Science

Graduate Inclusion and Access Scholarship GIA

Students

doctoral students

Using robotics to introduce AI and machine learning concepts into the elementary classroom

ckearney — Thu, 23 Jan 2025 17:52:02 +0000

Using robotics to introduce AI and machine learning concepts into the elementary classroom ckearney Thu, 01/23/2025 - 12:52

91�� researcher Erdogan Kaya is part of an interdisciplinary research team that is planning to introduce elementary students to the foundational concepts of artificial intelligence (AI) and machine learning using educational robotics.

George Mason professor Erdogan Kaya with some of the educational robots his team will be using with elementary school students. Photo provided

Kaya, an assistant professor in George Mason’s School of Education, and his collaborators—Hasan Deniz of University of Nevada, Las Vegas; Ezgi Yesilyurt of Weber State University; and Refika Turgut of University of South Carolina—have been awarded a $1 million grant from the National Science Foundation (NSF) “Computer Science for All” program for their project, “Cultivating Artificial Intelligence Literacy through Linguistically Inclusive Integrated Elementary Curriculum via Educational Robotics.”

“Over the years, I have seen firsthand how robotics can captivate and inspire students, making complex STEM concepts accessible and more engaging,” said Kaya. “Students gain insight into how AI systems work and develop a deeper understanding of the power of AI, which promotes foundational AI literacy.”

Approximately 600 elementary students in grades 4 and 5 from schools serving underrepresented populations in Clark County, Nevada, will participate in this study. The goal of this project is to provide the students with hands-on learning opportunities that will allow them to develop an understanding of AI and its application in science and technology.

The study will also offer professional development to 25 in-service educators to equip them with the foundational knowledge of AI and machine learning needed to teach an AI-integrated STEM curriculum.

Kaya emphasized that it is essential for young learners to acquire a level of AI literacy that includes an understanding of how AI algorithms work, how AI applications are developed, and how they can be used responsibly and creatively. He hopes that by being exposed to AI and machine learning at an early age, students will develop skills that may lead them to pursue careers in STEM.

“This project is about opening doors to AI literacy for young students, especially those from multilingual backgrounds who may not see themselves represented in tech fields,” said Kaya, who grew up in Turkiye and began learning English in middle school.

After working with multilingual learners in Title I schools in Arizona, Kaya discovered that his perspective as someone who has navigated education in multiple languages gave him insight into serving this population of students effectively.

“By integrating AI and robotics early on, we are providing a foundation in STEM that not only builds skills but instills a belief in students that they can be part of AI-intensive fields,” he said.

Educational tools, including Birdbrain Technologies’ Hummingbird Robotics®, Teachable Machine, and Snap!, a visual block-based programming environment, will be used in this study. Students will be tasked with designing automated solutions to real-world challenges that exist in their home communities, such as how to make smart homes more energy-efficient or how to develop farming robots capable of harvesting strawberries. Kaya said that projects like these will allow the students to apply AI concepts in ways that they will find more culturally relevant and meaningful.

The study will also promote the responsible and ethical use of AI by asking students to engage in critical thinking regarding the broader societal impact of AI and how bias can affect AI algorithm outputs.

Teachers using the AI-integrated curricular resources developed under this project will be able to incorporate them into their existing curricula.

“Our curriculum is designed to be flexible and integrative. By combining AI, engineering, language arts, and science into integrated lessons, teachers can address multiple subjects within a single lesson, making the most of limited classroom time,” said Kaya.

The importance of teaching the principles of AI and machine learning at an early age continues to gain traction in K-12 computer science education. Kaya notes that organizations such as the International Society for Technology in Education and Computer Science Teachers Association (CSTA) are responding with programs such as Teach AI. In addition, CSTA is updating its standards, scheduled for release in 2026, to incorporate machine learning and AI.

At the state level, Virginia’s recent updates to the Computer Science Standards of Learning (SOLs) include requirements for machine learning, further underscoring the need to prepare students in this field.

It is these changes in the field of computer science education that influenced Kaya’s decision to pursue a second master’s degree—this one in machine learning—at George Mason. “Even though I have a CS background, I recognized that machine learning and AI are becoming crucial parts of CS education,” he said. “To better serve the needs of future teachers and K-12 students, I decided to further my own education in this rapidly evolving field.”

With this project, Kaya said the goal is to equip teachers to bring AI and robotics into their classrooms with confidence, even if they do not have a technical background. “By providing practical training and readily available materials, we hope to create a ripple effect where teachers inspire their students and make AI education a reality in their classrooms,” Kaya said.

Make a difference with the School of Education

Topics

College of Education and Human Development

National Science Foundation

K-12 Partnerships

Strategic Direction

Mason Momentum

Aisha Behr leverages dual roles in industry and academia to advance deep learning

tdonnel — Wed, 08 Jan 2025 15:17:30 +0000

Aisha Behr leverages dual roles in industry and academia to advance deep learning tdonnel Wed, 01/08/2025 - 10:17

With degrees from 91�� in civil engineering, systems engineering, and earth systems and geoinformation sciences, alumna Aisha Behr’s path to becoming a leader in artificial intelligence (AI) and machine learning is as diverse as it is inspiring. Now a director for the AI and machine learning business units at CGI, Behr also serves as an adjunct professor in George Mason’s Department of Information Sciences and Technology (IST), teaching applied information technology (AIT) classes in machine learning and deep learning.

Behr started her career in government contracting, where she first encountered the burgeoning field of data science.

Her work required her to apply data science techniques to geospatial analysis, sparking a deep interest in the subject. While working full-time, Behr pursued a PhD in earth systems and geoinformation sciences at George Mason. Her dissertation, which aimed to improve the SVD algorithm with spatial statistics, highlighted her innovative approach to integrating machine learning with spatial data.

Aisha Behr. Photo provided

While balancing her professional career with her academic pursuits, Behr found a new calling in teaching, starting as an adjunct after completing her PhD in 2020. Her industry experience proves invaluable in the classroom, allowing her to offer students a unique perspective on the practical applications of their studies.

"I wanted to make sure that students had a really good process and experience through the whole course," said Behr. By providing code templates and practical assignments, she ensures that students can confidently apply what they learn in the AI and machine learning field.

Behr's teaching philosophy is centered around making complex concepts accessible and engaging. She developed the courses AIT 636 Interpretable Machine Learning and AIT 746 Applied Deep Learning to emphasize hands-on learning.

“Dr. Behr has been an exemplary adjunct in the IST department, playing a critical role in developing our new applied AI technologies concentration for the master’s in AIT program, as well as several graduate courses,” said Ioulia Rytikova, an IST professor and the director of the master’s program in AIT.

Behr is excited about the potential of generative AI and other emerging technologies. She will continue integrating such advancements into her teaching, possibly through guest lectures and hands-on labs.

"I want our students to be able to have exposure to these very, very new technologies," she emphasized, noting that she likes to demonstrate to students how keeping up with technology can give them a competitive edge in their careers.

"I enjoy learning new concepts,” said Behr. “Being able to show a student that you can learn and then accelerate your career is why I like it so much."

Behr’s journey is a powerful example of how passion, adaptability, and a commitment to education can lead to a fulfilling and impactful career. Her dedication to bridging industry and academia ensures that her students are well-prepared to navigate and excel in the ever-evolving field of AI and machine learning.

Learn more about Information Sciences and Technology at George Mason

In This Story

Ioulia Rytikova

Topics

information sciences and technology

applied information technology graduate programs

Katherine Scafide, PhD, RN, FAAN, FAAFS

Adjunct Faculty

Alumni

Determining quality in forensic injury imaging - 91�� secures NIH AIM-AHEAD funding to advance equity in AI-driven injury detection

dhawkin — Fri, 22 Nov 2024 18:21:21 +0000

Determining quality in forensic injury imaging - 91�� secures NIH AIM-AHEAD funding to advance equity in AI-driven injury detection dhawkin Fri, 11/22/2024 - 13:21

In This Story

Janusz Wojtusiak, PhD

David Lattanzi

91�� has been awarded funding from the National Institutes of Health (NIH) through its Artificial Intelligence/Machine Learning Consortium to Advance Health Equity and Researcher Diversity (AIM-AHEAD) program.

This initiative encourages more people from historically underrepresented groups in researching and developing of artificial intelligence (AI) and machine learning (ML) models. AIM-AHEAD aims to leverage the growing volume of data generated through electronic health records (EHR) and other biomedical research to address health disparities and inequities.

Janusz Wojtusiak. Photo by the Office of University Branding

The newly funded project, led by Janusz Wojtusiak, builds upon the Equitable and Accessible Software for Injury Detection (EAS-ID) initiative aimed at building artificial intelligence tools for collecting, assessing and analyzing injury data. The new funding specifically addresses the problem of measuring equity and quality of imaging documentation.

In addition to Wojtusiak, an interdisciplinary research team comprising Katherine Scafide and David Lattanzi is joined by Health Informatics Assistant Professor Eman Elashkar, Research Assistant Professor Jesse Kirkpatrick, who is also the acting director of the Institute for Philosophy and Public Policy, and Amin Nayebi Nodoushan, a postdoctoral researcher at Mason.

Their research focuses on using AI methods combined with Alternate Light Sources (ALS) to improve bruise detection, addressing visibility issues for individuals with darker skin tones who often encounter challenges in accurately assessing injuries sustained from violence.

Current literature highlights that skin color significantly influences the accuracy of AI-based tools in healthcare. Studies have documented disparities in the performance of medical devices, such as pulse oximeters and smartwatches, which frequently yield inaccurate readings for individuals with darker skin. These discrepancies can lead to delays in critical medical interventions, exacerbating existing health disparities.

The proposed research will focus specifically on bruises, the most common type of soft tissue injury experienced by victims of intimate partner violence (IPV). Statistics indicate that approximately one in three people in the U.S. have experienced IPV, with racial minorities reporting disproportionately higher rates. Survivors with darker skin tones have noted that their bruises are often invisible, resulting in significant delays in seeking necessary medical care.

Katherine Scafide is part of the multidisciplinary team working to advance equity in AI-driven injury detection. Photo by Emma Anderson.

Leveraging the innovative use of ALS, the George Mason research team has demonstrated marked improvement in bruise visibility across diverse skin tones. The team aims to develop methods that ensure that AI-based tools provide equitable and unbiased detection and characterization of injuries. This will involve creating combined technical-ethical metrics to assess the performance of these tools across different skin tones. Engaging diverse stakeholders, including clinicians, forensic nurses, and community representatives, will be essential in the development process to align with ethical practices in AI.

The research team’s two primary aims are to develop metrics that assess equity in AI tools and apply these metrics to improve bruise detection models. They have already collected a substantial dataset of bruise images taken under various lighting conditions, which will be utilized to enhance the AI models’ performance. The interdisciplinary nature of the research team, comprising informaticians, engineers, clinicians, and ethicists, ensures a comprehensive approach to tackling these complex issues.

In alignment with AIM-AHEAD’s goals, this research initiative promises to contribute significantly to addressing health inequities and enhancing the capabilities of AI in healthcare. By focusing on the specific needs of underrepresented communities, the George Mason research team is paving the way for more equitable health care solutions, ultimately aiming to improve the accuracy and efficacy of injury assessments across diverse populations.

This project is led by George Mason’s College of Public Health in collaboration with the College of Engineering and Computing. More information on the project can be found at bruise.gmu.edu.

Topics

Bruise Visibility

Machine Learning in Health Care

New research utilizes machine learning to address social isolation among alzheimer’s caregivers

mthomp7 — Thu, 10 Oct 2024 17:22:37 +0000

New research utilizes machine learning to address social isolation among alzheimer’s caregivers mthomp7 Thu, 10/10/2024 - 13:22

A new study from the College of Public Health at 91��, led by Professor Janusz Wojtusiak and Health Services Research doctoral candidate Ghaida Alsadah, explores the use of machine learning to predict social isolation among caregivers of individuals with Alzheimer’s disease and related disorders.

This research, which has been selected for funding by the Commonwealth of Virginia's Alzheimer's and Related Diseases Research Award Fund (ARDRAF), marks a significant advance in leveraging artificial intelligence (AI) to address a critical public health issue.

Professor Janusz Wojtusiak uses machine learning to predict social isolation among caregivers of individuals with Alzheimer’s disease and related disorders.

Alsadah has played a pivotal role in this study, contributing her expertise as a doctoral candidate to develop and refine machine learning models. These models analyze data from the Health and Retirement Study (HRS), National Health and Aging Trends Study (NHATS), and Behavioral Risk Factor Surveillance System (BRFSS) to identify and predict social isolation trajectories among caregivers. The study’s key finding is that AI-driven methods offer a novel approach to detecting social isolation, potentially leading to targeted interventions.

“This research is groundbreaking in its application of machine learning to predict social isolation among caregivers, an area previously underexplored,” said Wojtusiak. “The potential to develop AI-based interventions could significantly enhance the well-being of caregivers who often face profound social and emotional challenges.”

The study aims to construct predictive models for social isolation, adapt them for Medicare claims data, and simulate their application across large populations. The goal is to create a framework for AI-based interventions to address loneliness among caregivers effectively.

The innovation of this work lies in its use of machine learning to analyze and predict social isolation—a new approach with the potential to transform current understanding and interventions. Wojtusiak and Alsadah’s research is set to significantly impact health informatics and caregiver support. “Predicting Social Isolation Among Alzheimer’s Caregivers Using Machine Learning” will be published in an upcoming issue of a leading health informatics journal, emphasizing the importance of innovative approaches to complex public health challenges.

Additional contributors include College of Public Health alumna Mary Louise Pomeroy, a postdoctoral research fellow at Johns Hopkins University, who provided valuable expertise on social isolation and relevant datasets.

Learn more about the College of Public Health

In This Story

Janusz Wojtusiak, PhD

Topics

College of Public Health

Strategic Direction

MSHI Student Profile

Two George Mason faculty appointed to Virginia AI task force

Nathan Kahl — Sat, 27 Jul 2024 13:23:33 +0000

Two George Mason faculty appointed to Virginia AI task force Nathan Kahl Sat, 07/27/2024 - 09:23

In This Story

Amarda Shehu

Padmanabhan Seshaiyer

Amarda Shehu, a professor of computer science and associate dean in the College of Engineering and Computing, and Padhu Seshaiyer, a professor of mathematical sciences and the former associate dean for academic affairs for the College of Science, were named to the State Council of Higher Education for Virginia (SCHEV) EO30 task force, prompted by Executive Order (EO) 30 by Virginia Governor Glenn Youngkin.

Both Shehu and Seshaiyer acknowledge that this is a timely and important initiative by SCHEV, and they are excited that 91�� is an integral part of this process, supporting SCHEV, and by extension, institutes of education across the commonwealth.

Shehu's research is on AI and machine learning. Photo by the Office of University Branding

The EO states that it “recognizes the dual nature—both the opportunities and risks—of this developing technology in education. K-12 schools and postsecondary institutions must embrace innovation, experimentation, and new educational opportunities for students as well as ensure appropriate guardrails and necessary constraints exist to safeguard individual data privacy and mitigate discriminatory outcomes.”

SCHEV leaders chose Shehu and Seshaiyer for the task force because of their longstanding work and leadership in artificial intelligence (AI), STEM, and education; both admit there is a lot to consider around AI, and they are glad that Virginia is putting forth this effort.

Shehu said a broad conception of AI is necessary. “We need to think a little bit more holistically regarding the different opportunities and potential risks with regards to integrating AI in education. What kind of guidelines should we have for universities and for community colleges, not just for educators, but also for all the different organizations that they work with across Virginia.”

Seshaiyer explained that the task force has broad representation. “While we talk about promoting innovation and economic growth, there's also this whole aspect of ethical boundaries and considerations in AI development and deployment," he said. "It requires government, industry, and academia coming together to understand AI research, workforce development, and responsible AI.”

Shehu said the task force’s work and function are evolving. “A lot of the meetings I imagine will be thought experiments and the members feeding off one another based on our expertise. Some of us may be more positioned toward exciting applications, while some will want to caution, ‘Hey, hold on a second—you can't really do acquisition like this because you have to go through so many regulatory processes.’”

Shehu said they had been asked to consider and build on examples and guidelines from states, countries, and regions to be forward-thinking in their approach. One approach would be for the task force to categorize AI applications that are definitely a no, some that are yes, and some that still exist in a gray area.

Seshaiyer has encouraged students to experiment with AI in assignments. Photo provided

“For instance, AI assessing your emotions and your reactions and anything like that used for surveillance—that's a ‘no’ unless in situations of national security,” she said. “Consider personalized learning settings that are popping up where you might see clear value for an AI agent that sits and monitors you to read facial features so it can figure out if I'm confused or if I'm understanding. But for the task force, that’s a no, because that is surveillance. Please keep in mind we are thinking about children and students, a highly vulnerable population.”

Seshaiyer said, “For higher ed we have K-12 on one side, and workforce on the other side, so we are theoretically coming up with all sorts of academic ideas about AI and its implications. We test it on a nice cookbook problem, while the workforce side is looking at it from a business perspective, and K-12 is of course thinking of the learning implications. This is an example of having the tension in understanding AI implications by different stakeholders between impact, thoughtfulness, and speed.”

Those dealing with children have multiple considerations, he added. “So, the question for the principal or the Chief Information Technology Officer of the school system is, ‘How do I navigate this space? Which software is feasible, appropriate and at the right price point? Is it safe to use and are there any backdoors in terms of data privacy?’ There are these really practical questions for which they don't have answers because nothing is formally written, but they also don't quite know how to evaluate AI and its implications even if there are answers of how to actually evaluate it.”

The recommendations and guidance provided will impact rank-and-file faculty members, but also must be understood by deans, presidents, and provosts in higher ed, the faculty members said.

Seshaiyer said, “This could have impact across the curriculum. Should I change the content or the way I teach a class? Do I need to go back because maybe I was doing it all wrong or I thought I was doing it right? So, if I were to put my money into the recommendations, it would be training, training, training,”

The task force members are currently working on creating a draft of emergent themes on opportunities, issues, and executive order responsibilities. They have not yet been told what their timeframe is or the expected length of service.

Topics

SCHEV

Faculty and Staff News