Application of Machine Learning Algorithms for Asthma Management with mHealth: A Clinical Review

Abstract

Background: Asthma is a variable long-term condition. Currently, there is no cure for asthma and the focus is, therefore, on longterm management. Mobile health (mHealth) is promising for chronic disease management but to be able to realize its potential, it needs to go beyond simply monitoring. mHealth therefore needs to leverage machine learning to provide tailored feedback with personalized algorithms. There is a need to understand the extent of machine learning that has been leveraged in the context of mHealth for asthma management. This review aims to fill this gap. Methods: We searched PubMed for peer-reviewed studies that applied machine learning to data derived from mHealth for asthma management in the last five years. We selected studies that included some human data other than routinely collected in primary care and used at least one machine learning algorithm. Results: Out of 90 studies, we identified 22 relevant studies that were then further reviewed. Broadly, existing research efforts can be categorized into three types: 1) technology development, 2) attack prediction, 3) patient clustering. Using data from a variety of devices (smartphones, smartwatches, peak flow meters, electronic noses, smart inhalers, and pulse oximeters), most applications used supervised learning algorithms (logistic regression, decision trees, and related algorithms) while a few used unsupervised learning algorithms. The vast majority used traditional machine learning techniques, but a few studies investigated the use of deep learning algorithms. Discussion: In the past five years, many studies have successfully applied machine learning to asthma mHealth data. However, most have been developed on small datasets with internal validation at best. Small sample sizes and lack of external validation limit the generalizability of these studies. Future research should collect data that are more representative of the wider asthma population and focus on validating the derived algorithms and technologies in a real-world setting.

Predicting asthma attacks using connected mobile devices and machine learning: the AAMOS-00 observational study protocol

“…There is no consensus on the optimal algorithm for classification as previous studies are not comparable. 11 Therefore, we have taken a broad approach to use five state-of-the-art algorithm classes including Bayesian networks, decision trees, iForest, logistic regression and support vector machines. 44 45 From the classifiers, a severe asthma attack predictor will be built on the device and questionnaire data, at a patient level and population level.…”

“…There is no consensus on the optimal algorithm for classification as previous studies are not comparable 11. Therefore, we have taken a broad approach to use five state-of-the-art algorithm classes including Bayesian networks, decision trees, iForest, logistic regression and support vector machines 44 45.…”

“…There has been an increasing number of mHealth studies to predict asthma attacks and develop passive monitoring to support asthma self-management,11 including the use of smart peak flow meters,12 night-time activity tracking,13 14 smart inhalers,15 smartphone-administrated questionnaires6 16 17 and weather data 18 19. However, the combined use of the monitoring devices available to asthma patients to develop asthma attack prediction models is largely unexplored.…”

Current state and prospects of artificial intelligence in allergy

“…146 AI can also leverage the capabilities of wearables and mHealth technologies to monitor disease outside clinical contexts. 147 A recent study tested a prototype application for real-time counting of coughs using a deep learning model on ambient sound recorded by mobile phone. 148 This yielded accurate and real-time cough count with a specificity of 92% and a specificity of 98%.…”

“…One example is KBot, an early prototype of a chatbot for asthma that utilizes contextual information (such as high pollen triggers) and NLP for dialogue processing 146 . AI can also leverage the capabilities of wearables and mHealth technologies to monitor disease outside clinical contexts 147 . A recent study tested a prototype application for real‐time counting of coughs using a deep learning model on ambient sound recorded by mobile phone 148 .…”