Developing Mobile Technology using machine learning to monitor inhaler technique and medication adherence in asthma and COPD

Prof. John Hurst (primary)
UCL Respiratory: Centre for Inflammation and Tissue Repair
UCL, Division of Medicine
Dr Katharine Pike (secondary)
Respiratory, Critical Care and Anaesthesia Group
UCL

Abstract

Preventable asthma-related morbidity and mortality has not improved in 20 years.[1] The commonest reason for treatment failure is poor medication adherence, often caused by incorrect inhaler use. Up to 90% of people with asthma and a similar proportion with COPD use inhalers incorrectly.[2] Frequent technique checks improve clinical outcomes but are costly. We propose an App to help patients identify their inhalers and to check their technique. This will require an AI model using machine learning in a training cohort to learn different inhaler types, correct technique and common errors. This could be used by any patient with a smartphone.


References

1. Pavord ID , et al. After asthma: redefining airways diseases. The Lancet. 2017: 391;No. 10118
2. Lavorini F , et al. Effect of incorrect use of dry powder inhalers on management of patients with asthma and COPD. Respir Med 2008;102:593–604
3. Melani AS , et al. Inhaler mishandling remains common in real life and is associated with reduced disease control. Respiratory medicine. 2011;105(6):930-8
4. Klijn SL, et al . Effectiveness and success factors of educational inhaler technique interventions in asthma & COPD patients: a systematic review. NPJ primary care respiratory medicine. 2017;27(1):24
5. Press VG, et al. Effectiveness of Interventions to Teach Metered-Dose and Diskus Inhaler Techniques. A Randomized Trial. Annals of the American Thoracic Society. 2016;13(6):816-24


BBSRC Area
Genes, development and STEM* approaches to biology
Area of Biology
Physiology
Techniques & Approaches
Simulation / Modelling