My name is Shengpu Tang (唐笙普), and I am a PhD candidate in the division of computer science & engineering at the University of Michigan. I'm a member of the Machine Learning for Data-Driven Decisions (MLD3) research group led by Jenna Wiens, under the Michigan AI Lab.
My research focuses on developing and applying machine learning methods to help solve important problems related to healthcare. While motivated by specific use cases (such as risk stratification and dynamic treatment recommendation for various diseases and medical conditions), my work aims to identify interesting technical challenges and propose novel solutions that are broadly relevant to fundamental AI/ML research. My past contributions span the technical areas of reinforcement learning, deep learning, time-series and sequential data modeling, transfer learning, fairness, and I hope to apply my knowledge and expertise to interdisciplinary problems in healthcare and beyond.
PS: I have many genius friends and this LINK will redirect you to one of them.
- Reinforcement Learning
- Machine Learning
- Healthcare
-
PhD in Computer Science, 2023 (expected)
University of Michigan, Ann Arbor
-
MSE in Computer Science, 2020
University of Michigan, Ann Arbor
-
BSE in Computer Science, 2018
University of Michigan, Ann Arbor
Recent News
- Dec 2022: 🎉 I'll be presenting my latest work Leveraging Factored Action Spaces for Efficient Offline RL in Healthcare at NeurIPS 2022 in New Orleans, LA!
- Dec 2022: 🎉 I am co-organizing the ML4H 2022 Symposium, co-located with NeurIPS 2022 in New Orleans, LA!
- Jul-Aug 2022: Finally attended my first in-person conferences during PhD, ICML 2022 in Baltimore, MD and MLHC 2022 in Durham, NC!
- May-Aug 2022: I worked with Microsoft's Azure Cognitive Services team as a Research Intern.
- February 2022: Our paper on M-CURES, an open-source machine learning model predicting deterioration of hospitalized COVID-19 patients has been accepted to one of the world's leading medical journals, The BMJ!
- December 2021: Our paper on respecting autonomy & enabling diversity for medical databanks that drive precision health and clinical AI - is published in Health Affairs!
- December 2021: Co-organizing a new workshop - Research2Clinics -- Bridging the Gap: From Machine Learning Research to Clinical Practice - at NeurIPS 2021. Thank you to everyone who contributed and attended!
- August 2021: Invited to give a talk on RL with Set-Valued Policy: A Framework for Clinician-in-the-Loop Decision Making at the PathCheck Global Health Innovators Talk Series! You can find the recording of the seminar here.
- July-August 2021: I'll be presenting my work on Practical Considerations for Offline RL Model Selection at both MLHC 2021 and RL4RealLife @ ICML 2021! Watch the spotlight talk here.
- December 2020: Won a free registration to NeurIPS 2020 as one of the top reviewers! Excited to see everyone there :)
- July 2020: I'll be presenting my latest work on RL with Set-Valued Policy at ICML 2021! Check out the spotlight video here.
Media Coverage
- February 22, 2022: AI Triage -- Digital Health Wire newsletter.
- February 22, 2022: How to train a clinical AI to predict bad health outcomes -- STAT Health Tech.
- February 17, 2022: Open-source patient model tops industry standard -- University of Michigan News.
- December 7, 2021: How bias can creep into medical databanks that drive precision health and clinical AI -- Michigan Health Lab.
- June 22, 2021: A hospital algorithm designed to predict a deadly condition misses most cases -- The Verge.
- April 21, 2021: In scramble to respond to Covid-19, hospitals turned to models with high risk of bias -- MedCityNews.
- March 30, 2021: From collaboration to validation: How a team of engineers, clinicians, programmers, and administrators evaluated one of the most widely implemented predictive models -- Precision Health at UM.
- January 22, 2021: Epic Deterioration Index May Identify High- and Low-Risk COVID-19 Patients -- Clinical Advisor.
- October 12, 2020: New framework helps streamline EHR data extraction -- Healthcare IT News.
- May 12, 2020: Faster than COVID: a computer model that predicts the disease’s next move -- The Mighican Engineer News Center.
- April 15, 2020: Computer scientists employ AI to help address COVID-19 challenges -- Michigan AI Lab.
Visitors
Publications
Leveraing Factored Action Spaces for Efficient Offline Reinforcement Learning in Healthcare
Early Identification of Patients Admitted to Hospital for COVID-19 at Risk of Clinical Deterioration: Model Development and Multisite External Validation Study
Respecting Autonomy and Enabling Diversity: The Effect of Eligibility and Enrollment on Research Data Demographics
Model Selection for Offline Reinforcement Learning: Practical Considerations for Healthcare Settings
Predicting Postoperative Opioid Use with Machine Learning and Insurance Claims in Opioid-Naïve Patients
Democratizing EHR Analyses with FIDDLE - A Flexible Data-Driven Preprocessing Pipeline for Structured Clinical Data
Clinician-in-the-loop Decision Making: Reinforcement Learning with Near-Optimal Set-Valued Policies
Evaluating a Widely Implemented Proprietary Deterioration Index Model Among Hospitalized COVID-19 Patients
Predicting Acute Graft-versus-Host Disease Using Machine Learning and Longitudinal Vital Sign Data from Electronic Health Records
Relaxed Parameter Sharing: Effectively Modeling Time-Varying Relationships in Clinical Time-Series
A BioHackathon on the challenges of aging: Rapid need-finding and solution modeling in a student-led event
Activities
short films, games, etc.
Set Sail
Campus Movie Fest 2019
Set Sail (part 2)
Campus Movie Fest 2019
FreshWalk
EECS 598 - Advanced Data Mining
pandas
Contributed bug fixes
Legend of Zelda NES remastered
EECS 494 Game
Zelda Windy_World
EECS 494 Game
FlappyBird coop
EECS 494 Game
Flash-mob Oct.1 @ UM diag
Celebrating National Day of China, 2015