Peter Szolovits

Peter Szolovits is a Professor of Computer Science and Engineering and Professor of Health Sciences and Technology in MIT’s Department of Electrical Engineering and Computer Science and an associate faculty member at the Institute of Medical Engineering and Science (IMES) and Harvard-MIT Division of Health Sciences and Technology. Szolovits also heads the Clinical Decision-Making Group within MIT’s Computer Science and Artificial Intelligence Laboratory. His research centers on applying AI methods to medical decision making, extracting meaningful data from clinical narratives, and designing information systems for health care institutions and patients. Szolovits has worked on problems of diagnosis, therapy planning, execution and monitoring for various medical conditions, computational aspects of genetic counseling, controlled sharing of health information, privacy in medical records, and integration of clinical and genomic data for translational medicine. His interests in AI include knowledge representation, qualitative reasoning, probabilistic inference, and machine learning. 

Selected Publications

• Mahajan, D., Lehman, E., Liang, J., Szolovits, P., Raghavan, P., Chang, C., Iyengar, A. (2022). Towards Generalizable Methods for Automating Risk Score Calculation. ACL Biomedical Natural Language Processing Workshop (BioNLP).
• Lehman, E., Liang, J., Raghavan, P., Szolovits, P., Lialin, V., Legaspi, K., Sy, A. J. R., Pile, P. T. S., Alberto, N. R. I ., Ragasa, R. R. R., Alberto, I. R. I., Alfonso, P. G. I., Taliño, M., Moukheiber, D., Wallace, B., Rumshisky, A., Celi, L. A. (2022). Learning to Ask Like a Physician. NAACL.
• Raghavan, P., Mahajan, D., Liang, J., Chandra, R., Szolovits, P. (2021). emrKBQA: A Clinical Knowledge-Base Question Answering Dataset. ACL Biomedical Natural Language Processing Workshop (BioNLP).
• Jin, D., Jin, Z., Zhou, J. T., Szolovits, P. (2020). Unsupervised Domain Adaptation for Neural Machine Translation with Iterative Back Translation. International Joint Conferences on Artificial Intelligence (IJCAI).
• Jin, D., Jin, Z., Zhou, J. T., Szolovits, P. (2020). Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment. The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI).

Media

• February 7, 2020: MIT News, Hey Alexa! Sorry I fooled you …
• May 3, 2019: MIT News, School of Engineering first quarter 2019 awards.
• June 6, 2018: MIT News, An unexpected ambition borne from MIT experience.
• August 21, 2017: MIT News, Using machine learning to improve patient care.