Supporting self-management of COPD and asthma

Lead Research Organisation: University of Bristol
Department Name: Electrical and Electronic Engineering

Abstract

The objective of the project is to predict exacerbations in COPD and asthma using both supervised and unsupervised learning. Initially, the project will involve identifying what data needs to be collected and what data patients are comfortable having collected from them. Data will be collected at the individual patient level such as home monitoring sensors, activity data, cough frequency, symptom reporting and medication and from the population level such as citywide air quality, met office, traffic, pollen count, linked to primary care clinical records and secondary care admissions data and postcode. If possible, another objective is to clinically validate the effectiveness of the algorithm for predicting exacerbation.

Exacerbations are a period of symptom worsening that are difficult to predict and can cause a person's condition to worsen, to develop complications, require emergency care and can be fatal. There is a clinical need to effectively predict exacerbations in people with COPD and asthma so interventions can be applied early to prevent the severe consequences of exacerbation.

There are many novel aspects of this project including defining what data patients are comfortable having collected, combining patient-level and population-level data, implementing predictive algorithms to be used over long periods of time and prediction of an exacerbation.

The methodologies to be included in this project involve co-design, primary data collection, secondary data collection and training, validation and testing of a predictive algorithm using supervised and unsupervised learning.

Publications

10 25 50

Studentship Projects

Project Reference Relationship Related To Start End Student Name
EP/S023704/1 01/04/2019 30/09/2027
2275456 Studentship EP/S023704/1 23/09/2019 22/09/2023 Henry Glyde