Predicting Asthma Attacks: Effects of Indoor PM Concentrations on Peak Expiratory Flow Rates of Asthmatic Children

Despite ample research on the association between indoor air pollution and allergic disease prevalence, public health and environmental policies still lack predictive evidence for developing a preventive guideline for patients or vulnerable populations mostly due to limitation of real-time big data and model predictability. Recent popularity of IoT and machine learning techniques could provide enabling technologies for collecting real-time big data and analyzing them for more accurate prediction of allergic disease risks for evidence-based intervention, but the effort is still in its infancy. This pilot study explored and evaluated the feasibility of a deep learning algorithm for predicting asthma risk. It is based on peak expiratory flow rates (PEFR) of 14 pediatric asthma patients visiting the Korea University Medical Center and indoor particulate matter PM10 and PM2.5 concentration data collected at their residence every 10 minutes using a PM monitoring device with a low-cost sensor between September 1, 2017 and August 31, 2018. We interpolated the PEFR results collected twice a day for each patient throughout the day so that it can be matched to the PM and other weather data. The PEFR results were classified into three categories such as ‘Green’ (normal), ‘Yellow’ (mild to moderate exacerbation) and ‘Red’ (severe exacerbation) with reference to their best peak flow value. Long Short-Term Memory (LSTM) model was trained using the first 10 months of the linked data and predicted asthma risk categories for the next 2 months during the study period. LSTM model is found to predict the asthma risk categories better than multinomial logistic (MNL) regression as it incorporates the cumulative effects of PM concentrations over time. Upon successful modifications of the algorithm based on a larger sample, this approach could potentially play a groundbreaking role for the scientific data-driven medical decision making.

[1]  Peak Expiratory Flow Rate as a Monitoring Tool in Asthma , 2017, The Indian Journal of Pediatrics.

[2]  Jong Wook Kim,et al.  Health Big Data Analytics: A Technology Survey , 2018, IEEE Access.

[3]  Gang Luo,et al.  Predicting asthma control deterioration in children , 2015, BMC Medical Informatics and Decision Making.

[4]  J. Choi,et al.  Nationwide pulmonary function test rates in South Korean asthma patients. , 2018, Journal of thoracic disease.

[5]  Changsoo Kim,et al.  Short-term Effects of Ambient Air Pollution on Emergency Department Visits for Asthma: An Assessment of Effect Modification by Prior Allergic Disease History , 2016, Journal of preventive medicine and public health = Yebang Uihakhoe chi.

[6]  Wha Me Park,et al.  Indoor air quality of daycare centers in Seoul, Korea , 2017 .

[7]  M. Mendell,et al.  Indoor Environmental Exposures and Exacerbation of Asthma: An Update to the 2000 Review by the Institute of Medicine , 2014, Environmental health perspectives.

[8]  S. Charleston-Villalobos,et al.  Respiratory acoustic thoracic imaging (RATHI): Assessing deterministic interpolation techniques , 2004, Medical and Biological Engineering and Computing.

[9]  Kwok Wai Tham,et al.  Indoor air quality and its effects on humans—A review of challenges and developments in the last 30 years , 2016 .

[10]  D. Mannino,et al.  Global burden of COPD: risk factors, prevalence, and future trends , 2007, The Lancet.

[11]  B. Fiese,et al.  Quality of Life in Children With Asthma: A Developmental Perspective. , 2015, Journal of pediatric psychology.

[12]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[13]  S. N. Geethalakshmi,et al.  Plant Leaf Segmentation Using Non Linear K means Clustering , 2012 .

[14]  J. Halonen,et al.  Urban air pollution, and asthma and COPD hospital emergency room visits , 2008, Thorax.

[15]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[16]  Robert X. Gao,et al.  Deep learning and its applications to machine health monitoring , 2019, Mechanical Systems and Signal Processing.

[17]  Tzu-Tsung Wong,et al.  Dependency Analysis of Accuracy Estimates in k-Fold Cross Validation , 2017, IEEE Transactions on Knowledge and Data Engineering.

[18]  T. H. Nguyen,et al.  Global, regional, and national deaths, prevalence, disability-adjusted life years, and years lived with disability for chronic obstructive pulmonary disease and asthma, 1990–2015: a systematic analysis for the Global Burden of Disease Study 2015 , 2017, The Lancet. Respiratory medicine.

[19]  J. Choung,et al.  GIS-based Association Between PM10 and Allergic Diseases in Seoul: Implications for Health and Environmental Policy , 2015, Allergy, asthma & immunology research.

[20]  Magnus Rattray,et al.  Distinguishing Asthma Phenotypes Using Machine Learning Approaches , 2015, Current Allergy and Asthma Reports.

[21]  Kuangyuan Zhang,et al.  Assessment of indoor air quality exposures and impacts on respiratory outcomes in River Rouge and Dearborn, Michigan. , 2017, Chemosphere.

[22]  David M. W. Powers,et al.  Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation , 2011, ArXiv.

[23]  Pattanapong Chantamit-o-pas,et al.  Long Short-Term Memory Recurrent Neural Network for Stroke Prediction , 2018, MLDM.

[24]  Ping Zhang,et al.  Risk Prediction with Electronic Health Records: A Deep Learning Approach , 2016, SDM.

[25]  Krishan L. Khatri,et al.  Early Detection of Peak Demand Days of Chronic Respiratory Diseases Emergency Department Visits Using Artificial Neural Networks , 2018, IEEE Journal of Biomedical and Health Informatics.

[26]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[27]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[28]  Valerie F. Reyna,et al.  Efficacy of a Web-Based Intelligent Tutoring System for Communicating Genetic Risk of Breast Cancer , 2015, Medical decision making : an international journal of the Society for Medical Decision Making.

[29]  L. Talabere.  Chapter 52 – Development, Implementation, and Evaluation of an Asthma Management Plan , 2008 .

[30]  M. Hetzel.  The pulmonary clock. , 1981, Thorax.

[31]  Guang-Zhong Yang,et al.  Deep Learning for Health Informatics , 2017, IEEE Journal of Biomedical and Health Informatics.

[32]  R. Deterding,et al.  Bringing Technology to Day-to-Day Asthma Management. , 2018, American journal of respiratory and critical care medicine.

[33]  Ireneous N. Soyiri,et al.  Evolving forecasting classifications and applications in health forecasting , 2012, International journal of general medicine.

[34]  S. Vesper,et al.  Indoor particulate matter and lung function in children. , 2019, The Science of the total environment.