The future of asthma care is digital

Introduction

Asthma treatment is complex with a heavy reliance on patient self-management, adherence to a prescribed action plan, active avoidance of triggers, and correct inhaler use.^1-3 Digital technology is rapidly transforming respiratory care, with the advent of electronic monitoring devices, mHealth apps, wearable devices, and the increasing use of telehealth designed to empower patients and overcome existing barriers to care.^4,5

There is little doubt that digital health solutions will continue to shape the future of respiratory care,⁶ driving personalised therapeutic approaches and playing a vital role in supporting clinician decision making!

Introducing big data and artificial intelligence

‘Big data’ together with artificial intelligence (AI), including machine learning algorithms, are poised to revolutionise both the diagnosis and management of asthma through the use of predictive analytics.⁷ By automating knowledge discovery from large, complex data sets (including electronic health records, physiologic data captured via remote telemonitoring and environmental information), machine learning algorithms can collect, interpret, and find trends and patterns in disparate data.⁷

How will artificial intelligence be used in respiratory care?

AI can be integrated in software or any number of devices and will play a role across the full spectrum of care. Potential applications include:

• At diagnosis, where automated interpretation of lung function tests and cough analysis using AI software have been shown to diagnose asthma to a high degree of accuracy (correct diagnosis in 82–97% of cases)^8,9
• In differential diagnosis to distinguish between asthma and COPD. The Asthma/COPD Differentiation Classification (AC/DC) tool is currently under development, and is able to use machine learning algorithms and over 411, 000 electronic health records to aid the physician in differentiating asthma from COPD with a high level of accuracy¹⁰
• For the analysis of breath sounds from electronic stethoscopes, smart speakers, or smartphones, to detect wheezes and crackles, or for the analysis of CT scans^6,11,12
• To predict an individual’s future risk of exacerbations¹³ or risk of hospital attendance (admission or ED visit) over the coming year^7,14,15
• To inform treatment decisions by linking genetic traits to phenotypes that can predict response, or non-response, to treatment

What else does the future hold?

For day-to-day asthma management, we can expect future generations of smart inhalers to warn users of potential environmental triggers or accurately predict an upcoming exacerbation, or even trigger personalised treatment pathways based on weather conditions.^6,7,16

And wearables, from stickers worn on the abdomen with sensors to monitor breathing patterns, to clothing sensors, smart watches, bracelets, rings and necklaces will enable patients to monitor and manage their condition in real-time and provide clinicians with vital medical data to support clinical decision making.^6,16

Future versions of the technology described above will likely focus on a stronger personalisation of these digital products and services, perhaps utilising the ever-evolving advances in AI and machine learning. It is now easy to imagine a near and exciting future in respiratory care, where patients and healthcare providers are able to rely on advanced digital health solutions to inform clinical decisions and provide an optimal, personalised approach to therapy.

Glossary

Big data

Definition: large data sets pooled from many sources

Artificial intelligence

Definition: computer systems able to perform tasks normally requiring human intelligence

Machine learning algorithms

Definition: computer algorithms that improve automatically through experience

References

1. Pritchard JN and Nicholls C. Emerging technologies for electronic monitoring of adherence, inhaler competence, and true adherence. J Aerosol Med Pulm Drug Deliv 2015;28:69–81.
2. Thomas M. Why aren’t we doing better in asthma: time for personalised medicine? NPJ Prim Care Respir Med 2015;25:15004
3. Horne R. Compliance, adherence, and concordance: implications for asthma treatment. Chest 2006;130:65S–72S.
4. Asthma UK. Connected asthma: how technology will transform care. Last accessed March 2020. Available from: https://www.asthma.org.uk/f29019fc/globalassets/get-involved/external-affairs-campaigns/publications/connected-asthma/connected-asthma---aug-2016.pdf.
5. Blakey JD, Bender BG, Dima AL, et al. Digital technologies and adherence in respiratory diseases: the road ahead. Eur Respir J 2018; 52: 1801147
6. The Medical Futurist. Breathtaking: The future of respiratory care and pulmonology. Available from: https://medicalfuturist.com/breathtaking-the-future-of-respiratory-care-and-pulmonology Last accessed: 11 June 2020
7. Messinger AI, Luo G, Deterding RR. The doctor will see you now: How machine learning and artificial intelligence can extend our understanding and treatment of asthma. J Allergy Clin Immunol 2020;145:476–478.
8. Topalovic M, Das N, Burgel P-R, et al. Artificial intelligence outperforms pulmonologists in the interpretation of pulmonary function tests. Eur Respir J 2019;53(4):1801660.
9. Porter P, Abeyratne U, Swarnkar V, et al. A prospective multicentre study testing the diagnostic accuracy of an automated cough sound centred analytic system for the identification of common respiratory disorders in children. Respiratory Research 2019;20:81.
10. Kaplan A, Cao H, FitzGerald JM, et al. Asthma/COPD Differentiation Classification (AC/DC): Machine learning to aid physicians in diagnosing asthma, COPD and asthma-COPD overlap (ACO). Poster presented at the American Thoracic Society Virtual Conference, August 05–10, 2020.
11. Arsene C. Alexa in healthcare: 17 real use cases you should know about. Available from: https://www.digitalauthority.me/resources/alexa-in-healthcare Last accessed: 11 June 2020.
12. Sanyel S. 4 ways in which AI is revolutionizing respiratory care. Available from: https://www.forbes.com/sites/shourjyasanyal/2018/11/26/4-ways-in-which-ai-is-revolutionizing-respiratory-care/#14498e5e318d Last accessed: 11 June 2020.
13. Janson C, Johansson G, Larsson K, et al. Use of machine learning to predict asthma exacerbations. Eur Respir Society Congress 2020.
14. Luo G, He S, Stone BL, et al. Developing a model to predict hospital encounters for asthma in asthmatic patients: secondary analysis. JMIR Med Inform 2020;8:e16080.
15. Finkelstein J, Wood J. Predicting asthma exacerbations using artificial intelligence. Stud Health Technol Inform 2013;190:56–58.
16. Reddy M. Digital transformation in healthcare in 2020: 7 key trends. Available from: https://www.digitalauthority.me/resources/state-of-digital-transformation-healthcare Last accessed: 11 June 2020.