Introduction to Professor Sanjay Purushotham and His Lab at University of Maryland, Baltimore County

1. Could you briefly introduce yourself (and your University/Lab)?

Sanjay Purushotham is a tenure-track assistant professor in the Department of Information Systems at the University of Maryland, Baltimore County (UMBC). He obtained his M.S and Ph.D. in Electrical Engineering from the University of Southern California (USC)
under Prof. C.-C. Jay Kuo in the Media Communications Lab. Before joining UMBC, he was a Postdoctoral Scholar Research Associate in the Department of Computer Science and the Integrated Media Systems Center (IMSC) at USC, where he was mentored by Prof. Yan Liu and Prof. Cyrus Shahabi. His research interests include machine learning, deep learning, computer vision, and its applications to healthcare & bioinformatics, oncology, and multimedia data analysis. He has produced more than 35 publications, and he has won the best paper and best poster awards at many international venues including SIGSPATIAL, 2nd ICAIH, 34th Annual European Annual Urology Congress, and Socal ML Symposium. His research has been supported by the National Science Foundation (NSF) and the National Aeronautics and Space Administration (NASA).

Dr. Purushotham lab’s research mission is to develop efficient machine learning algorithms and systems to solve the most pressing societal challenges, such as engineering better medicines and harnessing data revolution. This mission involves convergence research and is in alignment with the NSF’s 10 Big Ideas. In particular, he is developing machine learning and deep learning algorithms and systems for personalized intelligent healthcare, mathematical oncology, and climate informatics.

2. What have been your most significant research contributions up to now?

Dr. Purushotham’s recent research contributions include developing state-of-the-art deep learning-based analytical frameworks to analyze heterogeneous health data from electronic health records.  His team has developed explainable deep learning models – to predict clinical outcomes of critical care patients from intensive care unit (ICU) data, to discover biomarkers and their interactions from biomedical data, to perform survival analysis of cancer patients, and to monitor patient’s well-being through wearable mobile health technology. Our team has also developed various machine learning models for robust outcome predictions in robotic surgery and traumatic brain injury.

3. What problems in your research field deserve more attention (or what problems will you like to solve) in the next few years, and why?

Developing responsible artificial intelligence (AI) models for healthcare is a significant problem that deserves attention soon as AI models are pervading the healthcare industry. Responsible AI includes fair, transparent, and trustworthy machine learning models that can help clinicians and stakeholders to make informed decisions to improve patient care and the quality of life.

4. What advice would you like to give to the young generation of researchers/engineers?

Be clear of your short-term and long-term goals—importantly, focus and work towards your long-term vision. Solve high-impactful problems by questioning the status quo. Have good mentors and sponsors, and be a mentor to others.