Cookies on this website

We use cookies to ensure that we give you the best experience on our website. If you click 'Accept all cookies' we'll assume that you are happy to receive all cookies and you won't see this message again. If you click 'Reject all non-essential cookies' only necessary cookies providing core functionality such as security, network management, and accessibility will be enabled. Click 'Find out more' for information on how to change your cookie settings.

This talk by Dr Shishir Rao explores how artificial intelligence (AI) on routinely collected electronic health records (EHR) data can transform healthcare research. The talk will focus on development and application of Transformer-based models for handling rich, multitype EHR, leveraging AI for prediction for early intervention, accelerating disease understanding, and conducting well-adjusted causal inference on large-scale EHR. Furthermore, the presentation will address critical challenges in the space of AI and healthcare: determining appropriate AI applications, ensuring trustworthiness, mitigating algorithmic bias, and validating clinical utility.

Dr Shishir Rao is a senior research scientist in the Deep Medicine research group led by Professor Kazem Rahimi focusing on developing and applying AI tools for understanding chronic diseases using multimodal healthcare data. Rao co-leads multiple AI projects in the research group focusing on perinatal risk assessment, musculoskeletal conditions, and heart failure. His research emphasises Transformer-based architectures for electronic health records (EHR) analysis, having pioneered the BEHRT model—the first Transformer for multimodal EHR. He also develops frameworks for causal inference with a focus on bridging advanced computational methods with practical clinical applications. He currently serves as AI methodological advisor for Heart, the BMJ family cardiology journal.

14:00 – 15:00 | Teams | followed by refreshments in the atrium

Find out more