Prediction of Short-acting Beta-agonist Usage in Patients with Asthma Using Temporal-convolutional Neural Networks

Overview

Journal JAMIA Open

Date 2023 Oct 30

PMID 37900973

Authors

Nicholas Hirons

Angier Allen

Noah Matsuyoshi

Jason Su

Leanne Kaye

Meredith A Barrett

Affiliations

Soon will be listed here.

Abstract

Objective: Changes in short-acting beta-agonist (SABA) use are an important signal of asthma control and risk of asthma exacerbations. Inhaler sensors passively capture SABA use and may provide longitudinal data to identify at-riskpatients. We evaluate the performance of several ML models in predicting daily SABA use for participants with asthma and determine relevant features for predictive accuracy.

Methods: Participants with self-reported asthma enrolled in a digital health platform (Propeller Health, WI), which included a smartphone application and inhaler sensors that collected the date and time of SABA use. Linear regression, random forests, and temporal convolutional networks (TCN) were applied to predict expected SABA puffs/person/day from SABA usage and environmental triggers. The models were compared with a simple baseline model using explained variance (), as well as using average precision (AP) and area under the receiving operator characteristic curve (ROC AUC) for predicting days with ≥1-10 puffs.

Results: Data included 1.2 million days of data from 13 202 participants. A TCN outperformed other models in predicting puff count ( = 0.562) and day-over-day change in puff count ( = 0.344). The TCN predicted days with ≥10 puffs with an ROC AUC score of 0.952 and an AP of 0.762 for predicting a day with ≥1 puffs. SABA use over the preceding 7 days had the highest feature importance, with a smaller but meaningful contribution from air pollutant features.

Conclusion: Predicted SABA use may serve as a valuable forward-looking signal to inform early clinical intervention and self-management. Further validation with known exacerbation events is needed.

References

Stanford R, Shah M, DSouza A, Dhamane A, Schatz M . Short-acting β-agonist use and its ability to predict future asthma-related outcomes. Ann Allergy Asthma Immunol. 2012; 109(6):403-7. DOI: 10.1016/j.anai.2012.08.014. View

Kaplan A, Mitchell P, Cave A, Gagnon R, Foran V, Ellis A . Effective Asthma Management: Is It Time to Let the AIR out of SABA?. J Clin Med. 2020; 9(4). PMC: 7230470. DOI: 10.3390/jcm9040921. View

Patel M, Pilcher J, Reddel H, Qi V, Mackey B, Tranquilino T . Predictors of severe exacerbations, poor asthma control, and β-agonist overuse for patients with asthma. J Allergy Clin Immunol Pract. 2014; 2(6):751-8. DOI: 10.1016/j.jaip.2014.06.001. View

Akinbami L, Moorman J, Liu X . Asthma prevalence, health care use, and mortality: United States, 2005-2009. Natl Health Stat Report. 2011; (32):1-14. View

Delamater P, Finley A, Banerjee S . An analysis of asthma hospitalizations, air pollution, and weather conditions in Los Angeles County, California. Sci Total Environ. 2012; 425:110-8. PMC: 4451222. DOI: 10.1016/j.scitotenv.2012.02.015. View

Anderson 3rd W, Gondalia R, Hoch H, Kaye L, Barrett M, Szefler S . Assessing asthma control: comparison of electronic-recorded short-acting beta-agonist rescue use and self-reported use utilizing the asthma control test. J Asthma. 2019; 58(2):271-275. DOI: 10.1080/02770903.2019.1687715. View

Jarrin R, Barrett M, Kaye L, Sayiner S, von Leer A, Johns J . Need for clarifying remote physiologic monitoring reimbursement during the COVID-19 pandemic: a respiratory disease case study. NPJ Digit Med. 2021; 4(1):50. PMC: 7954815. DOI: 10.1038/s41746-021-00421-8. View

Min X, Yu B, Wang F . Predictive Modeling of the Hospital Readmission Risk from Patients' Claims Data Using Machine Learning: A Case Study on COPD. Sci Rep. 2019; 9(1):2362. PMC: 6382784. DOI: 10.1038/s41598-019-39071-y. View

Merchant R, Inamdar R, Quade R . Effectiveness of Population Health Management Using the Propeller Health Asthma Platform: A Randomized Clinical Trial. J Allergy Clin Immunol Pract. 2016; 4(3):455-63. DOI: 10.1016/j.jaip.2015.11.022. View

10.

Pepper J, Barrett M, Su J, Merchant R, Henderson K, Van Sickle D . Geospatial-temporal analysis of the impact of ozone on asthma rescue inhaler use. Environ Int. 2019; 136:105331. DOI: 10.1016/j.envint.2019.105331. View

11.

Sheffield P, Zhou J, Shmool J, Clougherty J . Ambient ozone exposure and children's acute asthma in New York City: a case-crossover analysis. Environ Health. 2015; 14:25. PMC: 4373115. DOI: 10.1186/s12940-015-0010-2. View

12.

Pope 3rd C, Dockery D . Acute health effects of PM10 pollution on symptomatic and asymptomatic children. Am Rev Respir Dis. 1992; 145(5):1123-8. DOI: 10.1164/ajrccm/145.5.1123. View

13.

Luo G, He S, Stone B, Nkoy F, Johnson M . Developing a Model to Predict Hospital Encounters for Asthma in Asthmatic Patients: Secondary Analysis. JMIR Med Inform. 2020; 8(1):e16080. PMC: 7001050. DOI: 10.2196/16080. View

14.

Merchant R, Szefler S, Bender B, Tuffli M, Barrett M, Gondalia R . Impact of a digital health intervention on asthma resource utilization. World Allergy Organ J. 2018; 11(1):28. PMC: 6276132. DOI: 10.1186/s40413-018-0209-0. View

15.

Messinger A, Luo G, Deterding R . The doctor will see you now: How machine learning and artificial intelligence can extend our understanding and treatment of asthma. J Allergy Clin Immunol. 2019; 145(2):476-478. PMC: 7035143. DOI: 10.1016/j.jaci.2019.12.898. View

16.

Weinmayr G, Romeo E, De Sario M, Weiland S, Forastiere F . Short-term effects of PM10 and NO2 on respiratory health among children with asthma or asthma-like symptoms: a systematic review and meta-analysis. Environ Health Perspect. 2010; 118(4):449-57. PMC: 2854719. DOI: 10.1289/ehp.0900844. View

17.

Forno E, Celedon J . Asthma and ethnic minorities: socioeconomic status and beyond. Curr Opin Allergy Clin Immunol. 2009; 9(2):154-60. PMC: 3920741. DOI: 10.1097/aci.0b013e3283292207. View

18.

Barnett S, Nurmagambetov T . Costs of asthma in the United States: 2002-2007. J Allergy Clin Immunol. 2011; 127(1):145-52. DOI: 10.1016/j.jaci.2010.10.020. View

19.

Finkelstein J, Jeong I . Machine learning approaches to personalize early prediction of asthma exacerbations. Ann N Y Acad Sci. 2016; 1387(1):153-165. PMC: 5266630. DOI: 10.1111/nyas.13218. View

20.

Guarnieri M, Balmes J . Outdoor air pollution and asthma. Lancet. 2014; 383(9928):1581-92. PMC: 4465283. DOI: 10.1016/S0140-6736(14)60617-6. View