Thursday 17 June 2021, 12.30 - 1.30pm
This session will provide a clear understanding of key Machine Learning (ML) concepts, methods and techniques by showcasing applications for supporting clinical practice, clinical research and healthcare service delivery.
Using these case studies, we will explore design considerations according to application context (e.g. diagnosis and treatment selection), we will discuss how to approach the implementation of suitable ML methods (e.g. decision trees and neural networks), and finally we will study appropriate application evaluation strategies.
Dionisio Acosta-Mena (BSc, PhD), taught the Machine Learning in Healthcare and Biomedicine module in the Health Data Science Programme, Institute of Health Informatics, University College London. He has worked in several large scale projects looking into harnessing EHR data for clinical practice and research, most notably the EU-IMI EHR4CR project. His most recent publication explore data-driven temporal variability methods for automatic EHR data quality. He has expert knowledge and hands on experience in the design, implementation and evaluation of systems using artificial intelligence and machine learning methods to improve healthcare outcomes in areas such as breast cancer and brain tumours.
Currently he is a Senior Data Scientist at Cegedim RX, where he leads data science methodological and technical aspects of using the Cegedim THIN dataset.
We are very grateful to Dionisio and the team at Cegedim for sharing their time and expertise for the benefit of BHBIA members.
Click on the register for event button below. Please note you must be logged in as a member to book online.
If you belong to a BHBIA member company but don't yet have a log in please register now to join your company's membership.