AI for Healthcare

My research pursuits focus on the application of AI to improve healthcare. This entails developing predictive models for the analysis and interpretation of biomedical data. I am particularly interested in developing innovative AI solutions for precision medicine, especially by leveraging multimodal data. My work spans deep learning, graph representation learning, large language models and natural language processing.

About Me

Hi, I am Shaika Chowdhury (সাইকা চৌধুরী). Welcome to my personal website! I am currently a Research Associate at Mayo Clinic's AI and Informatics department. Prior to this, I worked as a Postdoctoral Researcher/Fellow with research focus on the applications of AI in precision medicine using real-world healthcare data. I received my PhD in Computer Science from the University of Illinois Chicago in 2021. During my PhD, I also interned at IQVIA, Siemens Healthineers and Target.

Latest

Paper titled "Probing Fine-grained and Coarse-grained Embeddings with Large Language Models for Patient-Trial Matching using Siamese Neural Network" is accepted to the AMIA 2025 Annual Symposium as a poster!
My joint work titled "Advancing Efficacy Prediction for EHR-based Emulated Trials in Repurposing Heart Failure Therapies" has been accepted to the npj Digital Medicine 2025!
Paper I co-authored titled "Synoptic Reporting by Summarizing Cancer Pathology Reports using Large Language Models" is accepted to npj Health Systems 2025!
My paper titled "Stratifying heart failure patients with graph neural network and transformer using Electronic Health Records to optimize drug response prediction" is accepted to the Journal of the American Medical Informatics Association 2024!
I presented my work titled "Evaluation of GPT-3 for Anti-Cancer Drug Sensitivity Prediction" at the AMIA Informatics Summit 2024.
I presented my work titled "Drug Response Prediction and Phenomapping for Personalized Healthcare Management using EHR: A Graph-based Deep Learning Approach" at the AMIA Clinical Informatics Conference 2024.
My paper titled "Evaluating Drug Effectiveness for Antihypertensives in Heart Failure Prognosis: Leveraging Composite Clinical Endpoints and Biomarkers from Electronic Health Records" is accepted to the 14th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics 2023, which I also presented at the conference!
Paper I co-authored titled "BETA: a comprehensive benchmark for computational drug-target prediction" is accepted to Briefings in Bioinformatics 2022!