Mehak Gupta, Ph.D.

Mehak Gupta Headshot

Mehak Gupta, Ph.D.

Assistant Professor of Computer Science

Office Location: Caruth Hall 467

Send Email

 

Education

  • Ph.D, Computer Science, University of Delaware
  • M.S., Software Engineering, Thapar University, India
  • B.S., Computer Engineering, Punjabi University, India

Biography

Dr. Gupta is an Assistant Professor in the Department of Computer Science in the Bobby B. Lyle School of Engineering, SMU Lyle. Dr. Gupta has developed a number of prediction models that use medical data (Electronic Health Record data) to predict future risk of developing diseases such as obesity and heart failure.

Dr. Gupta’s main research interests are in deep learning and prediction modeling, for applications in healthcare. During her graduate studies, she collaborated with local hospitals and other non-profit organizations (Delaware Data Innovation Lab). Dr. Gupta’s dissertation, entitled “Deep Learning Predictive Modelling for Electronic Health Record” has garnered a significant impact on childhood obesity prediction and provides the basis to develop clinical decision support for obesity prediction in pediatric primary settings.

Honors and Awards

  • Frank A. Pehrson Graduate Student Award for Outstanding Computer Science Research
  • Dissertation Fellowship
  • Data Science Fellowship
  • Distinguished Graduate Student Award

 


Research

  • Deep Learning
  • Supervised and Semi-supervised machine learning
  • Structured and Unstructured medical data
  • Predictive modeling
  • Natural Language Processing

Recent Publications

  • Mehak Gupta, Thao-Ly T Phan, H Timothy Bunnell, and Rahmatollah Beheshti. “Obesity prediction with ehr data: A deep learning approach with interpretable elements”. ACM Transactions on Computing for Healthcare (HEALTH), 3(3):1–19, 2022 (View)
  • Mehak Gupta, Brennan Gallamoza, Nicolas Cutrona, Pranjal Dhakal, Raphael Poulain, and Rahmatollah Beheshti. “An Extensive Data Processing Pipeline for MIMIC-IV”. In Proceedings of the 2nd Machine Learning for Health symposium, volume 193 of Proceedings of Machine Learning Research, pages 311–325. PMLR. 2022 (View)
  • Raphael Poulain, Mehak Gupta, and Rahmatollah Beheshti. “Few-Shot Learning with Semi-Supervised Transformers for Electronic Health Records.”. Machine Learning for Healthcare Conference, pages 1–21, 2022. (View)
  • Gupta, M., Poulain, R., T. Phan, T.-L., Bunnell, H. T. and Beheshti, R. “Flexible-window Predictions on Electronic Health Records”. In Proceedings of the AAAI Conference on Artificial Intelligence, 36(11):12510-12516. (IAAI-Track) (View)
  • Gupta, M., T. Phan, T.-L., Bunnell, H. T. and Beheshti, R. “Concurrent Imputation and Prediction on EHR data using Bi-Directional GANs”. In Proceedings of the 12th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics. (View)

Personal website