Copenhagen Bioscience Conference presentation
Why medicine is creating exciting new frontiers for machine learning
Medicine stands apart from other areas where machine learning can be applied. While we have seen advances in other fields with lots of data, it is not the volume of data that makes medicine so hard, it is the challenges arising from extracting actionable information from the complexity of the data. It is these challenges that make medicine the most exciting area for anyone who is really interested in the frontiers of machine learning – giving us real-world problems where the solutions are ones that are societally important and which potentially impact on us all. Think Covid 19!
In this talk I will show how machine learning is transforming medicine and how medicine is driving new advances in machine learning, including new methodologies in automated machine learning, interpretable and explainable machine learning, dynamic forecasting, and causal inference.
Location and local date/time
This event will take place online on May 4 at 19:15 CEST ( 18:15 BST).
About the event
The philosophy that all humans are essentially the same has provided key assumptions in driving medical breakthroughs. This guiding principle is now challenged by evidence demonstrating that variation from the mean is not simply noise but predictive. Precision medicine explains this by asserting that individuals belong to one or more overlapping groups determined by ancestry and environment.
This conference will drive the conversation forward by focusing on patient centrality in the context of omics, digital medicine, and artificial intelligence. An unmet need in medical research is the link between molecular and genetic data (OMICs) with clinical characteristics for modelling outcomes like treatment response, survival, and risk of adverse events. This seems a simple task, however in reality it has proven to be harder than expected to manage. A major shift in thinking about how we might tackle these challenges is required from multiple domains.
Scientific development of this goal will be facilitated by two back-to-back strategies. First, the conference whitepaper will ground discussion and the opinions of attendees in a peer-reviewed process; second, we will run a hackathon prior to the conference and focused on difficult immunological and clinical data sets provided by organizers.