Kevin Tsang

Project: Application of data-driven technologies for asthma self-management

Asthma is affecting around 5.4 million people in the UK. Currently, there is no cure for asthma. However existing treatments, such as inhalers, can be used to manage the condition better. The “optimal” self-management strategy should include a personalised asthma action plan supported by regular professional review and self-management education. 

Mobile-health applications (mHealth) have come to the forefront of self-management due to smartphones becoming ubiquitous. Where each device is packed with sensors, connected to the internet, and portable, which allows for non-intrusive monitoring. mHealth can play a role in promoting adherence to the self-management strategy by simplifying and reducing the number of recurring active input required by the patient; while providing passive monitoring throughout the day and appropriately timed alerts. 

The research aims to create a system for a personalised early predictor of asthma exacerbation, consisting of a mobile app, a server and the algorithm. We aim to develop an ML-based algorithm that is capable of learning as more data is collected, in addition to building upon existing research in using low-cost medical devices and wearable devices. This system will allow better self-management by preventing episodes through spotting early warning signs. 

About me

My research interests are machine learning, prediction models and mobile technologies.

Find out more about my research project

Project: AAMOS

Publications

Budiarto A, Tsang KCH, Wilson AM, Sheikh A, Shah SA. Machine Learning–Based Asthma Attack Prediction Models From Routinely Collected Electronic Health Records: Systematic Scoping Review. JMIR AI 2023;2:e46717. doi: 10.2196/46717

Tsang, K.C.H., Pinnock, H., Wilson, A.M., Salvi, D., Olsson, C.M., Shah, S.A. Compliance and Usability of an Asthma Home Monitoring System. In: Tsanas, A., Triantafyllidis, A. (eds) Pervasive Computing Technologies for Healthcare. PH 2022. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 488. Springer, Cham. doi:10.1007/978-3-031-34586-9_9

Tsang, K.C.H., Pinnock, H., Wilson, A.M., Salvi, D., Shah, S.A. Home monitoring with connected mobile devices for asthma attack prediction with machine learning. Sci Data 2023;10:370. doi:10.1038/s41597-023-02241-9 

Tsang KCH, Pinnock H, Wilson AM, Salvi D, Shah SA. AAMOS-00 Study: Predicting Asthma Attacks Using Connected Mobile Devices and Machine Learning, 2021-2022 [dataset]. University of Edinburgh, Edinburgh Medical School, Usher Institute. 2022. 

Tsang KCH, Pinnock H, Wilson AM, et al. Predicting asthma attacks using connected mobile devices and machine learning: the AAMOS-00 observational study protocol. BMJ Open 2022;12:e064166. doi: 10.1136/bmjopen-2022-064166

Tsang KCH, Pinnock H, Wilson AM, Shah SA. Application of Machine Learning Algorithms for Asthma Management with mHealth: A Clinical Review. J Asthma Allergy. 2022;15:855-873 https://doi.org/10.2147/JAA.S285742 

Salvi, D, Olsson CM, Ymeri G, Carrasco-López C, Tsang KCH , and Shah SA. 2021. Mobistudy: mobile-based, platform-independent, multi-dimensional data collection for clinical studies. In 11th International Conference on the Internet of Things (IoT ’21), November 8–12, 2021, St.Gallen, Switzerland. ACM, New York, NY, USA, 4 pages. doi.org/10.1145/3494322.3494363

Tsang KCH, Pinnock H, Wilson AM and Shah SA, Application of Machine Learning to Support Self-Management of Asthma with mHealth, 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 2020, pp. 5673-5677, doi: 10.1109/EMBC44109.2020.9175679.