Shruthi Chari

I am a recent PhD in Computer Science from Rensselaer Polytechnic Institute (RPI). I was advised by Professor Deborah L. McGuinness and Professor Oshani Seneviratne. I will soon start as a Machine Learning (ML) Scientist at Bristol Myers Squibb and I am excited to work among an interdiscplinary team of scientists to apply trustworthy ML techniques to further drug discovery.
My research interests lie in the area of clinical Natural Language Processing (NLP) and Explainable Artificial Intelligence (XAI). Specifically, I apply semantics, ML, and natural language processing techniques to further the fields of human-centered explainable AI and healthcare informatics.

Previously, I received my B.S. in Computer Science at PES Institute of Technology and M.S. in Computer Science at Rensselaer Polytechnic Institute.

Email  /  Industry CV  /  Academic CV

Google Scholar  /  Twitter  /  LinkedIn  /  GitHub

• Invited to give job talks on my PhD thesis research at the Dept. of AI and Informatics, Mayo Clinic; Center for Devices and Radiological Health (CDRH), FDA and the Small Molecule and Drug Discovery Team at BMS.
• 8/2023: Started to contribute to the explainability focus of the IARPA HIATUS project.
• 4/2023: Passed my Candidacy Presentation as part of my PhD program requirements. Committee: Prof. Deborah L. McGuinness, Co-Advisor: Prof. Oshani Seneviratne, Members: Prof. James A. Hendler, Dr. Prithwish Chakraborty and Dr. Pablo Meyer.
• 7/2023: Our work on Explanation Ontology V 2.0 appeared on Semantic Web J.
• 2/2023: Our work on Contextualizing Model Explanations using Medical Guidelines appeared on Artificial Intelligence in Medicine J.
• 8/2021: Completed my externship at the Center for Computational Health, IBM Research, and was hosted by Dr. Prithwish Chakraborty.
• 8/2021: We were one of the top best paper award winners at the Joint KDD 2021 Health Day and 2021 KDD Workshop on Applied Data Science for Healthcare for our work on Leveraging Clinical Context for User-Centered Explainability: A Diabetes Use Case
• 11/2020: Awarded the best resource track paper for, Explanation Ontology: A Model of Explanations for User-Centered AI, at ISWC 2020.
• 3/2020: Our book chapters on Foundations of and Directions for Explainable Knowledge-Enabled Systems are available as published by IOS Press as a part of the Knowledge Graphs for eXplainable Artificial Intelligence: Foundations, Applications and Challenges book.
• 9/2019: Started my PhD in Computer Science at RPI.
• 8/2019: Completed my internship at IBM Research, Yorktown Heights and hosted by Dr. Ching-Hua Chen.
• 3/2019: Defended my Masters thesis on Semantic Modeling of Cohort Descriptions, advised by Prof. Deborah L. McGuinness and Committee Members: Prof. Kristin Bennett, Prof. James A. Hendler and Dr. Amar K. Das.

We introduce version 2.0 of the Explanation Ontology with better support for state of the art explainer methods and more explanation types, we now support the modeling of 15 explanation types.

We introduce an end-end method to contextualize model predictions and explanations in a comorbodity risk prediction setting by implementing a question-answering pipeline to extract relevant sentences from medical guidelines.

We introduce our Explanation Ontology (EO), a resource to represent system-, user- and interface- dependencies of explanations. We are able to represent nine different explanation types within the EO.

We suggest directions in terms of research areas that will be important for AI explainability. We also introduce a definition for explanations that accounts for imporant dimensions such as context, user intent and knowledge.

We introduce an extraction and compositon pipeline for cohort description tables from clinical trial PDFs. The tables are converted into Study Cohort Ontology (SCO) structured knowledge graphs using our multi-step extraction pipeline.

Source code credit to Dr. Jon Barron