HDR UK Applied Analytics Webinar: Reproducible machine learning of movement behaviours from wearable sensors - Aiden Doherty (01:03:07)

Wearable sensors such as wrist-worn activity trackers (accelerometers) have the potential to continuously, noninvasively, and painlessly measure important indicators of health status in peoples’ everyday lives. For example, UK Biobank has measured physical activity status in 103,712 participants who agreed to wear a wrist-worn device for seven days. These measurements are now actively used by health researchers worldwide to demonstrate associations between physical activity and CVD. Machine learning methods can help maximise the utility of these datasets. However, there is a broad concern around the lack of reproducibility of machine learning models in health data science. It is critical to carefully consider how to promote robust machine learning findings and reject irreproducible ones, to ensure credibility and trustworthiness. In this talk I will share progress on reproducible machine learning of wearable sensor data to support the early detection of disease and the identification of candidate therapeutics. (Aiden Doherty) 25/05/2021