Wearable Respiration Monitoring: Interpretable Inference With Context and Sensor Biomarkers

Breathing rate (BR), minute ventilation (VE), and other respiratory parameters are essential for real-time patient monitoring in many acute health conditions, such as asthma. The clinical standard for measuring respiration, namely Spirometry, is hardly suitable for continuous use. Wearables can track many physiological signals, like ECG and motion, yet not respiration. Deriving respiration from other modalities has become an area of active research. In this work, we infer respiratory parameters from wearable ECG and wrist motion signals. We propose a modular and generalizable classification-regression pipeline to utilize available context information, such as physical activity, in learning context-conditioned inference models. Morphological and power domain novel features from the wearable ECG are extracted to use with these models. Exploratory feature selection methods are incorporated in this pipeline to discover application-specific interpretable biomarkers. Using data from 15 subjects, we evaluate two implementations of the proposed pipeline: for inferring BR and VE. Each implementation compares generalized linear model, random forest, support vector machine, Gaussian process regression, and neighborhood component analysis as contextual regression models. Permutation, regularization, and relevance determination methods are used to rank the ECG features to identify robust ECG biomarkers across models and activities. This work demonstrates the potential of wearable sensors not only in continuous monitoring, but also in designing biomarker-driven preventive measures.

[1]  Azziza Bankole,et al.  Multiple-Instance Learning for Sparse Behavior Modeling from Wearables: Toward Dementia-Related Agitation Prediction , 2019, 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[2]  Claire M. Lochner,et al.  Monitoring of Vital Signs with Flexible and Wearable Medical Devices , 2016, Advanced materials.

[3]  John Lach,et al.  Inferring physical agitation in dementia using smartwatch and sequential behavior models , 2018, 2018 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI).

[4]  Gari D. Clifford,et al.  ECG Statistics , Noise , Artifacts , and Missing Data , 2006 .

[5]  Eric R. Ziegel,et al.  Generalized Linear Models , 2002, Technometrics.

[6]  L. Tarassenko,et al.  An assessment of algorithms to estimate respiratory rate from the electrocardiogram and photoplethysmogram , 2016, Physiological measurement.

[7]  George B. Moody,et al.  Derivation of Respiratory Signals from Multi-lead ECGs , 2008 .

[8]  R. Tibshirani Regression Shrinkage and Selection via the Lasso , 1996 .

[9]  David A. Clifton,et al.  Towards a Robust Estimation of Respiratory Rate from Pulse Oximeters , 2016 .

[10]  Steffen Leonhardt,et al.  Ambient and Unobtrusive Cardiorespiratory Monitoring Techniques , 2015, IEEE Reviews in Biomedical Engineering.

[11]  Gunnar Rätsch,et al.  Totally corrective boosting algorithms that maximize the margin , 2006, ICML.

[12]  D. Wakefield,et al.  Respiratory rate predicts cardiopulmonary arrest for internal medicine inpatients , 1993, Journal of General Internal Medicine.

[13]  Sergio Silvestri,et al.  Contact-Based Methods for Measuring Respiratory Rate , 2019, Sensors.

[14]  W. Mcdonnell,et al.  Ozone-induced respiratory symptoms: exposure-response models and association with lung function. , 1999, The European respiratory journal.

[15]  Ciara O'Brien,et al.  A comparison of algorithms for estimation of a respiratory signal from the surface electrocardiogram , 2007, Comput. Biol. Medicine.

[16]  Hiroshi Koizumi,et al.  Robust respiration rate estimation using adaptive Kalman filtering with textile ECG sensor and accelerometer , 2016, 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[17]  Pablo Laguna,et al.  A robust method for ECG-based estimation of the respiratory frequency during stress testing , 2006, IEEE Transactions on Biomedical Engineering.

[18]  Tonya L. Smith-Jackson,et al.  Motion Biomarkers for Early Detection of Dementia-Related Agitation , 2017, DigitalBioMarker@MobiSys.

[19]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[20]  Patrizia Vergallo,et al.  Empirical Mode Decomposition vs. Wavelet Decomposition for the Extraction of Respiratory Signal From Single-Channel ECG: A Comparison , 2013, IEEE Sensors Journal.

[21]  A. Nevill,et al.  Validity and reliability of cardiorespiratory measurements recorded by the LifeShirt during exercise tests , 2009, Respiratory Physiology & Neurobiology.

[22]  Gary B. Smith,et al.  The ability of the National Early Warning Score (NEWS) to discriminate patients at risk of early cardiac arrest, unanticipated intensive care unit admission, and death. , 2013, Resuscitation.

[23]  Geoffrey E. Hinton,et al.  Neighbourhood Components Analysis , 2004, NIPS.

[24]  Shigeho Tanaka,et al.  Estimation of daily inhalation rate in preschool children using a tri-axial accelerometer: a pilot study. , 2011, The Science of the total environment.

[25]  P. Krzesiński,et al.  Cardiorespiratory coupling in young healthy subjects , 2017, Physiological measurement.

[26]  U. Koehler,et al.  [Respiratory Rate - a Neglected Vital Sign]. , 2017, Deutsche medizinische Wochenschrift.

[27]  Chun Lin,et al.  Personal exposure monitoring of PM2.5 in indoor and outdoor microenvironments. , 2015, The Science of the total environment.

[28]  Dinesh John,et al.  Simple to complex modeling of breathing volume using a motion sensor. , 2013, The Science of the total environment.

[29]  Philip Langley,et al.  Principal Component Analysis as a Tool for Analyzing Beat-to-Beat Changes in ECG Features: Application to ECG-Derived Respiration , 2010, IEEE Transactions on Biomedical Engineering.

[30]  Yong Zhu,et al.  Low-Power Wearable Systems for Continuous Monitoring of Environment and Health for Chronic Respiratory Disease , 2016, IEEE Journal of Biomedical and Health Informatics.

[31]  Zoltán Benyó,et al.  A novel method for the detection of apnea and hypopnea events in respiration signals , 2002, IEEE Transactions on Biomedical Engineering.

[32]  John Lach,et al.  Non-Invasive Inference of Minute Ventilation Using Wearable ECG and Gaussian Process Regression , 2019, 2019 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI).

[33]  A. Sheel,et al.  Measurement of exercise ventilation by a portable respiratory inductive plethysmograph , 2006, Respiratory Physiology & Neurobiology.

[34]  Jordan Brayanov,et al.  Evaluation of a Novel Noninvasive Respiration Monitor Providing Continuous Measurement of Minute Ventilation in Ambulatory Subjects in a Variety of Clinical Scenarios , 2013, Anesthesia and analgesia.

[35]  B. V. K. Vijaya Kumar,et al.  Heartbeat Classification Using Morphological and Dynamic Features of ECG Signals , 2012, IEEE Transactions on Biomedical Engineering.

[36]  Carlos Guestrin,et al.  "Why Should I Trust You?": Explaining the Predictions of Any Classifier , 2016, ArXiv.

[37]  Yoram Singer,et al.  Improved Boosting Algorithms Using Confidence-rated Predictions , 1998, COLT' 98.

[38]  Justin R. Boyle,et al.  Automatic Detection of Respiration Rate From Ambulatory Single-Lead ECG , 2009, IEEE Transactions on Information Technology in Biomedicine.

[39]  S. Field,et al.  The effect of a peak flow-based action plan in the prevention of exacerbations of asthma. , 1997, Chest.

[40]  Valerio Persico,et al.  Big Data for Health , 2019, Encyclopedia of Big Data Technologies.

[41]  J. Hankinson,et al.  Standardisation of spirometry , 2005, European Respiratory Journal.

[42]  C. Sabel,et al.  Quantifying human exposure to air pollution--moving from static monitoring to spatio-temporally resolved personal exposure assessment. , 2013, The Science of the total environment.

[43]  Sabine Van Huffel,et al.  Application of Kernel Principal Component Analysis for Single-Lead-ECG-Derived Respiration , 2012, IEEE Transactions on Biomedical Engineering.

[44]  W L Haskell,et al.  Predicting Adult Pulmonary Ventilation Volume and Wearing Compliance by On-Board Accelerometry During Personal Level Exposure Assessments. , 2012, Atmospheric environment.

[45]  Carl E. Rasmussen,et al.  Sparse Spectrum Gaussian Process Regression , 2010, J. Mach. Learn. Res..

[46]  Yuhong Yang Aggregating regression procedures to improve performance , 2004 .

[47]  Patrice Quinton,et al.  Estimation of respiratory volume from thoracoabdominal breathing distances: comparison of two models of machine learning , 2017, European Journal of Applied Physiology.

[48]  H. Zou,et al.  Regularization and variable selection via the elastic net , 2005 .

[49]  I. Pavord,et al.  Monitoring asthma in children , 2015, European Respiratory Journal.

[50]  Paul Kligfield,et al.  Exercise Electrocardiogram Testing: Beyond the ST Segment , 2006, Circulation.

[51]  Wei Yang,et al.  Neighborhood Component Feature Selection for High-Dimensional Data , 2012, J. Comput..

[52]  Kendall F Morris,et al.  Cardiorespiratory coupling: common rhythms in cardiac, sympathetic, and respiratory activities. , 2014, Progress in brain research.

[53]  R. Saatchi,et al.  Respiration rate monitoring methods: A review , 2011, Pediatric pulmonology.

[54]  Eric T. Carlson,et al.  Development of three methods for extracting respiration from the surface ECG: a review. , 2014, Journal of electrocardiology.

[55]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[56]  Marjolein V. Smith,et al.  Prediction of lung function response for populations exposed to a wide range of ozone conditions , 2012, Inhalation toxicology.

[57]  Carl E. Rasmussen,et al.  A Unifying View of Sparse Approximate Gaussian Process Regression , 2005, J. Mach. Learn. Res..

[58]  Achim Zeileis,et al.  BMC Bioinformatics BioMed Central Methodology article Conditional variable importance for random forests , 2008 .

[59]  C.R. Merritt,et al.  Textile-Based Capacitive Sensors for Respiration Monitoring , 2009, IEEE Sensors Journal.

[60]  John Lach,et al.  Inferring Respiratory Minute Volume from Wrist Motion , 2019, 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[61]  Lionel Tarassenko,et al.  Data fusion for estimating respiratory rate from a single-lead ECG , 2013, Biomed. Signal Process. Control..