Today, a plethora of technologies, from image recognition tools to chatbots, are powered by machine learning. A key component to the technique’s success is data—and lots of it. For doctors and hospitals who hope to use machine learning to improve healthcare, that need for copious data presents a problem: medical data is protected by privacy laws and often exists in incomplete or diverse forms—from doctor’s notes to medical scans—that make it difficult for machine learning models to use it effectively.

“Using data better to aid medical decisions is a grand challenge of the 21st century,” says Sanjay Purushotham, an assistant professor in information systems at UMBC. “We need innovations in existing techniques to take full advantage of artificial intelligence in healthcare.”

Together with his students, Purushotham is tackling that challenge. He recently received a prestigious NSF CAREER award to support his team’s efforts to develop new ways to train health-focused machine learning models. 

Purushotham has been contributing his expertise in computer science to collaborations with doctors and hospitals for almost ten years. The NSF CAREER award will help Purushotham further that research in a new direction, and ultimately, his team hopes their work will improve medical treatments and reduce costs, benefiting patients around the world.

The need for data-driven healthcare

Sanjay Purushotham (Marlayna Demond ’11/UMBC)

When you visit the doctor, you may be asked about your general health, your family medical history, and your current symptoms. The doctor may order a series of tests and scans. All of this data could yield valuable insights into your health and the best course of medical treatment.

Bringing the data together in ways that make it accessible and illuminating is an ongoing challenge in health care. Synthesizing and presenting health information in new ways could improve individual medical care. Computer systems could ensure busy doctors see the most relevant information at the right time, aiding their decision making. It could also prove valuable for addressing public health challenges, such as the spread of infectious diseases.

“During the COVID pandemic, the health community realized the importance of having access to good data,” says Purushotham. Better data could help public officials make better decisions about when to take precautions, such as closing schools. It could also help individuals better understand the risks when choosing to partake in activities like attending large social gatherings or traveling.

Over the next five years, the award will support Purushotham and his students as they investigate ways to advance a technique called federated learning, which could allow hospitals and doctors to jointly build and evaluate a machine learning model without sharing sensitive medical data.

A new way to collaborate

Most machine learning models are trained centrally, on vast quantities of data that are often scrapped from the internet. However, a lot of data exists that cannot be sent to a central processing facility, for cost or privacy reasons. The term ‘federated learning’ was coined in 2016 to describe a decentralized machine learning technique that could train on data that never leaves users’ mobile phones. Instead, individual devices would take turns downloading the model, training it on their own data, and then sending the updated model parameters back to a central location.

Students Sultan Ahmed (left) and Zahid Hassan Tushar (center) work in the lab with Sanjay Purushotham (right). (Marlayna Demond ’11/UMBC)

The general approach could be beneficial in many industries, from finance to manufacturing. In health care, federated learning has clear appeal because privacy laws strictly limit how health data can be shared.

For example, federated learning could allow hospitals to train a joint model on their medical data, such as CT scans, without sharing the scans with each other. The jointly trained model  might reveal new ways to detect disease.

Yet, many hurdles remain to successfully deploying the technique, including the non-uniformity and limited nature of some patient data, the varying computational resources available to different medical practitioners, and the threat of bad actors seeking access to private information.

Advancing federated learning

In the coming years, Purushotham and his team will pursue three main avenues of research to address the obstacles of deploying federated learning in healthcare. The project will develop new algorithms, methodologies, and software to make data-driven federated learning for healthcare more robust and trustworthy.

The first focus of the team will be to develop new ways to handle the diversity of health data. The  team will then study potential methods of attacks on the federated learning systems, and develop defenses against such attacks. The researchers will also investigate ways that the system can “un-learn” in situations where users request the influence of their data be removed from the model. In all cases, the researchers will focus on developing fair and interpretable algorithms. Finally, the researchers will study ways to generate synthetic health data, which can be used to augment or replace real data to improve the AI models.

The scope of the work is ambitious, but Purushotham is confident in his team.

“I have great students and collaborators,” he says. “I’m really excited to make federated learning in healthcare work.”

Sanjay Purushotham (third from left) with members of his research team (from left to right): Shaswati Shah, Catherine Ordun, Sultan Ahmed, Md Mahmudur Rahman, and Zahid Hassan Tushar. (Marlayna Demond ’11/UMBC)

Thank you for your patience as we continue to improve our campus!

Administrative Assistant Position:

Title: Administrative Assistant

Part Time | $18 an hr.

Meet Anna Jones, a first-generation psychology major on the pre-med track at UMBC. What started as a “nudge” by one of her professors wound up leading Anna to becoming a peer tutor with UMBC’s SI (supplemental instruction) PASS (peer-assisted study sessions) program—an experience that has changed her life and defined her experience as a Retriever. We can’t wait to hear all about it!

Q: What brought you to UMBC in the first place?

A: Hello! I am a psychology B.S. major with a minor in biological sciences on the pre-med track. I transferred to UMBC after my first year of college and fell in love with what UMBC had to offer.
I came from a very small honors college and wanted to be a part of a more diverse, larger, student body. At UMBC, I quickly learned that I was surrounded by goal-oriented, like-minded, and well-rounded students, and I was met by supportive professors who connected me to my higher self through opportunity and encouragement.

Q: What’s the one thing you’d want someone to know about the support you found here?

A: Academic support is within arms-length here. Resources are offered tailored to anyone’s needs as a student and it is not challenging to access.

Q: Tell us about someone in the community who has inspired you or supported you, and how they did it.

A: I’ve been inspired by a countless number of individuals here on campus. The highlighted person(s) would be my physics professor Dr. Lili Cui, my SI PASS supervisor Deborah Webb, the ASC (Academic Success Center) director Dr. Delana Gregg (Ph.D. ’19, language, literacy, and culture), and simply all of my peers in the SI PASS organization for the past three semesters. Dr. Lili was the professor I worked alongside as I supported her course through being an SI Pass leader. Dr. Lili has uplifted me by giving me honest academic advice and suggesting opportunities to further my leadership skills. She saw the leadership in me before I recognized it within myself.

Deb Webb and Dr. Gregg supported me extensively by being present through all of my success as an SI PASS leader. Deb Webb has provided me with skill building tasks and granted me access to resources that have been helpful to both my personal and academic self and career. Through her coordination of SI PASS, she has supported me through mentorship, organization, and communication. Dr. Gregg also supported me through words of encouragement and helping me become a part of a network that made it possible for me to help other students and faculty beyond our campus.

Jones, second from right, stands next to Delana Gregg, third from right, and other members of the SI PASS team.

Q: Tell us about what you love about being a peer mentor and SI PASS tutor.

A: I wanted to give back to my community but didn’t know how, so I became an SI PASS leader and mentor. Through these roles, I was able to achieve my wish to not only give back, but connect with many elements this campus had to offer. I admire UMBC’s priority of peer education and wanted to extend that principle to others through my role as a student.

SI PASS is a free support resource for traditionally difficult courses which tend to be STEM or language related. SI PASS leaders are responsible for hosting regularly-scheduled study sessions throughout the week to help facilitate active learning among students enrolled in their designated course. We engage students in various learning strategies to support students in knowing what to learn and how to learn it.

As an SI PASS mentor, I serve as a role model to assigned new leaders, provide guidance on specific administrative and SI PASS skills such as completing planning sheets and logging data, offer support (motivational/emotional), and assist new leaders with setting goals and identifying resources.

What I love about being an SI PASS leader and mentor is the ability to give back to my community at such a large school. It helps me connect with my peers and professors in ways that I never imagined possible. I feel like a thread, sewing different bits of the campus together. I am grateful for the new skills I’ve developed through my experience and the meaningful connections I’ve made and have helped other students make during my time here.

Q: Since you’ve been a part of the UMBC community, how have you found support of your WHY?

A: I was suggested to be an SI PASS Leader by my former physics professor Dr. Lili Cui. This referral started as a nudge in the right direction but later turned into a life-changing experience for me. Becoming a part of this organization led to me presenting at my very first conference for the MDCLCA (Maryland College Learning Center Association) organization, which then led me to becoming a student representative. My professor, my supervisor, and my peer educators all aid equally in my evolution as a student. They have all done nothing but encourage me to be my best self, providing challenges for me to overcome and grow through.

Q: What would you tell other transfer students about what it’s like becoming a part of the UMBC community?

A: Being a transfer student as such a large university (compared to my previous school) can be very intimidating. It may require some elbow grease to build up the courage to become more involved on campus but you will come to find that the inclusivity of this community eases the tension. Becoming involved is easier than you may think and there’s countless options of helpful resources to point you in the right direction.

* * * * *

UMBC’s greatest strength is its people. When people meet Retrievers and hear about the passion they bring, the relationships they create, the ways they support each other, and the commitment they have to inclusive excellence, they truly get a sense of our community. That’s what “Meet a Retriever” is all about.

Learn more about how UMBC can help you achieve your goals.