Machine Learning for Data-Driven Decisions (MLD3)
We are a part of the AI Lab within the Division of Computer Science and Engineering. We work at the interface of artificial intelligence (AI), machine learning (ML), and healthcare.
Welcome to the Machine Learning for Data-Driven Decisions Group at the University of Michigan! Our current research portfolio focuses on major public health problems – including infectious disease, Alzheimer’s disease, and diabetes, respiratory failure, among others. We develop and state-of-the-art AI and machine learning methods to analyze large health datasets. Our work spans several aspects of AI including time-series analysis, reinforcement learning, computer vision, causal inference, and human-computer interaction. We aim to develop the computational methods needed to help organize, process, and transform data into actionable knowledge with the ultimate goal of improving health. You can contact the group by emailing Dr. Jenna Wiens at wiensj@umich.edu. |
- Comment published in Nature Medicine
Congratulations to Meera Krishnamoorthy on her comment “Off-label use of artificial intelligence models in healthcare” published in Nature Medicine!
- Dr. Jenna Wiens on JAMA Podcast with JAMA Editor in Chief Dr. Kirsten Bibbins-Domino
Jenna Wiens, PhD was recently interviewed by JAMA Editor in Chief Kirsten Bibbins-Domino, PhD, MD, MAS, to discuss clinician-AI collaboration for more effective deployment of AI in health. Check it out here!
- Paper Accepted to NEJM AI
Congratulations to Fahad Kamran and Donna Tjandra on their recently accepted paper “Evaluation of Sepsis Prediction Models before Onset of Treatment” to NEJM AI!
- Paper Accepted to AISTATS 2024
Congrats Fahad Kamran on his paper “Learning to Rank for Optimal Treatment Allocation Under Resource Constraints” accepted at AISTATS 2024!
- Paper Published in JAMA
Congratulations to Sarah Jabbour on her JAMA publication: Measuring the Impact of AI in the Diagnosis of Hospitalized Patients: A Randomized Clinical Vignette Survey Study!
AI and Clinical Practice with Jenna Wiens
Dr. Jenna Wiens • JAMA 2024
AI for Clinical Diagnostic Decision Making: Can Explanations be a Backstop Against Biased AI? | MiCHAMP Seminar Series
Sarah Jabbour • MiCHAMP 2024
Disparate Censorship & Undertesting: A Source of Label Bias in Clinical Machine Learning
Trenton Chang • MLHC 2022
PhD student perspectives in CSE: Sarah Jabbour
Sarah Jabbour • 2023
From Diagnosis to Treatment – Augmenting Clinical Decision Making with Artificial Intelligence • Temerty Speaker Series
Dr. Jenna Wiens • May 11, 2021
Reinforcement Learning with Set-Valued Policies • PathCheck Global Health Innovators Seminar
Shengpu Tang • August 12, 2021
Model Selection for Offline Reinforcement Learning: Practical Considerations for Healthcare Settings | MLHC 2021
Shengpu Tang
Mind the Performance Gap: Examining Dataset Shift During Prospective Validation | MLHC 2021
Erkin Otles
Deep Learning Applied to Chest X-Rays: Exploiting and Preventing Shortcuts | MLHC 2020
Sarah Jabbour
Deep Reinforcement Learning for Closed-Loop Blood Glucose Control | MLHC 2020
Ian Fox
Clinician-in-the-loop RL with Set-Valued Policies | ICML 2020
Shengpu Tang | More details on icml.cc
Deep Residual Time-Series Forecasting: Application to Blood Glucose Prediction
Presented at 2020 KDH Blood Glucose Level Prediction Challenge
MCURES
a COVID predictive model developed specifically for the Michigan Medicine population: the Michigan COVID-19 Utilization and Risk Evaluation System, or MCURES.
Friday Night AI: AI and COVID-19
Erkin Otles speaks about M-CURES, a machine learning model developed by people from our lab. M-CURES can help clinicians tell which COVID-19 patients are most likely to deteriorate.
How can machine learning impact healthcare?
Prof. Jenna Wiens uses machine learning to make sense of the immense amount of patient data generated by modern hospitals. This can help alleviate physician shortages, physician burnout, and the prevalence of medical errors.
Stanford Medicine Big Data | Precision Health 2018
Dr. Jenna Wiens