Internship project: Generative AI for safe data-driven innovation

Opportunity

Electronic medical records (EMR) could support digital health applications that improve patient outcomes, if innovators can access the data to develop algorithms. Synthetic EMR data could improve privacy and stand in for real data when building proofs of concept, assuming similar performance can be achieved.

During this project, the intern will access real healthcare data from a large general hospital. They will extract the inputs required for a published machine learning model for predicting patient outcomes, e.g., deterioration. This can be used both to train a synthetic data generation model and to benchmark outcome prediction. The project will contribute to our understanding of the utility of synthetic health data for teaching and innovation.

Project Objectives

• Replicate a published machine learning model for predicting patient deterioration
• Benchmark the replicated machine learning model against synthetic and real clinical data
• Develop recommendations for applying a machine learning model to a synthetic data set