Clinical Data
Clinical data research focuses on extracting meaningful insights and predictions from diverse patient information, including structured records (e.g., demographics, diagnoses) and unstructured data (e.g., clinical notes, images). Current research emphasizes developing and refining machine learning models, such as deep learning networks (including convolutional and recurrent architectures) and transformer-based language models, to improve diagnostic accuracy, predict patient outcomes (e.g., mortality, readmission), and personalize treatment strategies. This work is crucial for advancing healthcare by enabling more effective disease management, facilitating data-driven decision-making, and ultimately improving patient care.
Papers
A Counterfactual Fair Model for Longitudinal Electronic Health Records via Deconfounder
Zheng Liu, Xiaohan Li, Philip Yu
Patient Clustering via Integrated Profiling of Clinical and Digital Data
Dongjin Choi, Andy Xiang, Ozgur Ozturk, Deep Shrestha, Barry Drake, Hamid Haidarian, Faizan Javed, Haesun Park