The workshop will be held December 10 in New Orleans. Times are listed in CST.
Time | Title |
8:30-8:45 | Opening Remarks |
8:45-9:15 | Keynote 1: Elaine Nsoesie |
| Session 1: Global Health and Health Equity |
9:15-9:35 | Speaker: Emma Pierson |
9:35-9:55 | Speaker: Milind Tambe |
9:55-10:15 | Speaker: Charles Delahunt |
10:15-11:00 | Panel Q&A: Global Health and Health Equity with Elaine Nsoesie, Emma Pierson, Milind Tambe, and Charles Delahunt |
11:00-11:20 |
Lightning Talks
- Learning Temporal Higher-order Patterns to Detect Anomalous Brain Activity
- SANSformers: Self-Supervised Forecasting in Electronic Health Records with Attention-Free Models
- Leveraging Transformers to Improve Breast Cancer Classification and Risk Assessment with Multi-modal and Longitudinal Data
- Deep Multimodal Fusion for Surgical Feedback Classification
- Using Reinforcement Learning for Multi-Objective Cluster-Level Optimization of Non-Pharmaceutical Interventions for Infectious Disease
- On the Importance of Step-wise Embeddings for Heterogeneous Clinical Time-Series
- Interpretable Mechanistic Representations for Meal-level Glycemic Control in the Wild
- Causal prediction models for medication safety monitoring: The diagnosis of vancomycin-induced acute kidney injury
|
11:20-12:05 | Poster Session 1 + Demos + Coffee Break presented by Genentech |
12:05-13:20 | Break for Lunch |
13:20-13:50 | Keynote 2: Marinka Zitnik |
| Session 2: Generative AI & LLMs |
13:50-14:10 | Speaker: Monica Agrawal |
14:10-14:30 | Speaker: Stefan Harrer |
14:30-14:50 | Speaker: Tao Tu |
14:50-15:35 | Panel Q&A: Generative AI & LLMs with Marinka Zitnik, Monica Agrawal, Stefan Harrer, and Tao Tu |
15:35-15:55 |
Lightning Talks
- MedAlign: A Clinician-Generated Dataset for Instruction Following with Electronic Medical Records
- Med-Flamingo: a Multimodal Medical Few-shot Learner
- Diffusion Models To Predict 3D Late Mechanical Activation From Sparse 2D Cardiac MRIs
- Learning Generalized Medical Image Representations through Image-Graph Contrastive Pretraining
- Coarse race data conceals disparities in clinical risk score performance
- When accurate prediction models become harmful self-fulfilling prophecies
- Utilizing the GPT-3.5 Artificial Intelligence Model to provide clinical recommendations in the Emergency Department
- Modeling Complex Disease Trajectories using Deep Generative Models with Semi-Supervised Latent Processes
|
15:55-16:00 | Announcement of Winners |
16:00-16:45 | Poster Session 2 + Demos + Coffee Break |
16:45-18:00 | Research Roundtables |
18:00-18:10 | Closing Remarks |
18:10-21:00 | Evening Social @ Napoleon House
(500 Chartres St, New Orleans, LA 70130)
|