About

Welcome! I’m Xiangyu, also known as Sean. I recently earned my PhD in Data Science from the New Jersey Institute of Technology, under the guidance of Professor Yi Chen. My doctoral research focused on developing end-to-end machine learning pipelines for the healthcare industry, with a dissertation centered on using AI techniques to improve the effectiveness and efficiency of patient engagement.

In the summer of 2022, I interned as a Data Scientist at Amazon’s Supply Chain Optimization Technologies (SCOT). Previously, in the summer of 2021, I served as an AI Research Associate at the Center for Health Information & Decision Systems (CHIDS) at the University of Maryland.

I hold a Master of Science in Marketing Intelligence (STEM-designated) from Fordham University’s Gabelli School of Business and a Bachelor of Science in Business Administration from the New York Institute of Technology.

I’m currently seeking a full-time DS/MLE/Applied Scientist position.

Experience

Data Scientist Intern, Amazon (May 2022 - September 2022)
AI Research Associate, CHIDS, University of Maryland (June 2021 - August 2021)
Data Category Manager, Standard Media Index (October 2015 - August 2018)

Research Experience

Research Assistant, New Jersey Institute of Technology
- Led a project to develop a knowledge graph enhanced thread recommender system for online health forums
- Led a project to increase the likelihood of having patients answer a phone call from the healthcare provider through machine learning and deep learning techniques, including a graph-based call time prediction model and a hybrid patient reachability prediction model
- Led the design of a novel hybrid NLP approach and the development of a prototype system for extracting cancer biomarkers from free-text pathology reports
- Developed a hierarchical time-aware neural network for personalized risk prediction of adverse drug events using claims data
- Contributed to the implementation of an advanced deep learning model for extracting patient conditions from clinical notes

Teaching Experience

Instructor, New Jersey Institute of Technology
- Instructor of MIS 363 Project Management for Managers (Summer 2020)
- Instructor of MIS 445 Decision Support Tool and Technology for Managers (Spring 2020)
Teaching Assistant, New Jersey Institute of Technology
- Technical Support (primarily Microsoft Project) of MIS 363 Project Management for Managers (Spring 2021, Fall 2021, Spring 2022, Fall 2022, Spring 2023, Fall 2023, Spring 2024)
- Teaching Assistant of MIS 385 Database Systems for Managers (Fall 2019)
- Lab Assistant at NJIT Business Analytics Lab (Spring 2019)

Publications

Weiting Gao, Xiangyu Gao, Yi Chen, Compositional and Hierarchical Semantic Learning Model for Hospital Readmission Prediction, 2024 33rd ACM International Conference on Information and Knowledge Management (CIKM), 2024 [code]
Weiting Gao, Xiangyu Gao, Wenjin Chen, David J Foran, Yi Chen, BioReX: Biomarker Information Extraction Inspired by Aspect-Based Sentiment Analysis, 2024 Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), 2024 [code]
Jinhe Shi, Xiangyu Gao, William C Kinsman, Chenyu Ha, Guodong Gordon Gao, Yi Chen, DI++: A Deep Learning System for Patient Condition Identification in Clinical Notes, Artificial Intelligence in Medicine, 2022
Jinhe Shi, Xiangyu Gao, Chenyu Ha, Yage Wang, Guodong Gao, Yi Chen, Patient ADE Risk Prediction through Hierarchical Time-Aware Neural Network Using Claim Codes, 2020 IEEE International Conference on Big Data (Big Data), 2020
Xiangyu Gao, Jinhe Shi, Wenjin Chen, Nancy Sazo, Huiqi Chu, Evita Sadimin, David J Foran, Yi Chen, CBEx: A Hybrid Approach for Cancer Biomarker Extraction, 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2020

Working Papers

Xiangyu Gao, Jinhe Shi, Junjie Luo, Guodong (Gordon) Gao, and Yi Chen, Patient Reachability Prediction Through a Hybrid Deep Learning Model
Xiangyu Gao, Jinhe Shi, Guodong (Gordon) Gao, and Yi Chen, Personalized Phone Call Time Prediction Using Graph Embedding

Currently Reading