NCI Data Jamboree (Project Abstract Submission): Submission #2

Presenter Information
---------------------
First Name: Megha
Middle Initial: B.
Last Name: Srivastava
Degree(s): B.S./M.S. in Computer Science
Position/Title/Career Status: PhD Student in Computer Science
Organization: Stanford University
Organization Address:
Stanford

Email: megha@cs.stanford.edu

Additional Authors
------------------
List of Additional Authors:
{Empty}


Abstract Information
--------------------
Abstract Category: Employing statistical, computational, and informatics tools, algorithms, and methods to integrate or analyze data
Abstract Keywords: machine learning, AI-readiness, distribution shift, causal inference, confounding variables, language models, LLMs
Abstract Title: Project Seeker 
Abstract:
I am a PhD student in Computer Science, with significant experience in machine learning, large language modeling, and human-AI interaction. I have recently been transition my research towards applications of AI in medicine, healthcare, and drug discovery, and hope to understand what challenges exist on the dataset-level, and what are ideal datasets that can help push different problems forward. One research area I am particularly interested in is challenges of distribution shift -- e.g. mismatch between the training dataset and test time inference, and how to tackle that. I am particularly curious about methods for identifying potential confounding variables that are unmeasured in the current dataset. My hope is to join a project that can help improve the quality and availability of oncology datasets for machine learning research.