A practical approach to storage and retrieval of high-frequency physiological signals

This paper describes a novel time series storage solution specifically targeted at physiological waveforms and other associated clinical and medical device data. The system, called AtriumDB, is designed to serve as a data source for high performance computing systems and provides an Application Programming Interface (API) for functional, rapid data retrieval. The database has a minimal storage footprint, facilitating cost-effective long-term storage of high frequency physiological data at full resolution. A prototype system has been recording data in a 42-bed pediatric critical care unit at The Hospital for Sick Children in Toronto, Ontario since February 2016. As of December 2019, the database contains over 720,000 patient-hours of data collected from over 5300 patients, all with complete waveform capture. Using our approach one year of full resolution physiological waveform storage from a unit of this size can be stored in less than 300GB of disk space and can deliver retrospective data to analytical applications at a rate of up to 50 million time-value pairs per second. We outline our motivations for creating such a database and gives an overview of the system architecture and performance.

[1]  D John Doyle,et al.  The Problem of Artifacts in Patient Monitor Data During Surgery: A Clinical and Methodological Review , 2006, Anesthesia and analgesia.

[2]  Mohamed Elgendi,et al.  Optimal Signal Quality Index for Photoplethysmogram Signals , 2016, Bioengineering.

[3]  Abraham Lempel,et al.  A universal algorithm for sequential data compression , 1977, IEEE Trans. Inf. Theory.

[4]  U. Rajendra Acharya,et al.  Heart rate variability: a review , 2006, Medical and Biological Engineering and Computing.

[5]  Barret Rush,et al.  Applying machine learning to continuously monitored physiological data , 2018, Journal of Clinical Monitoring and Computing.

[6]  R. Wetzel,et al.  First Get the Data, Then Do the Science! , 2018, Pediatric critical care medicine : a journal of the Society of Critical Care Medicine and the World Federation of Pediatric Intensive and Critical Care Societies.

[7]  Chris D. Nugent,et al.  A review of ECG storage formats , 2011, Int. J. Medical Informatics.

[8]  S. Nizami,et al.  Implementation of Artifact Detection in Critical Care: A Methodological Review , 2013, IEEE Reviews in Biomedical Engineering.

[9]  Álvaro Alesanco Iglesias,et al.  A Review on Digital ECG Formats and the Relationships Between Them , 2012, IEEE Transactions on Information Technology in Biomedicine.

[10]  Christina Orphanidou,et al.  A review of big data applications of physiological signal data , 2019, Biophysical Reviews.

[11]  Dirk Timmermann,et al.  New IEEE 11073 standards for interoperable, networked point-of-care Medical Devices , 2015, 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[12]  E. Bridges,et al.  Monitoring arterial blood pressure: what you may not know. , 2002, Critical care nurse.

[13]  Danny Eytan,et al.  Insights From Multi-Dimensional Physiological Signals to Predict and Prevent Cardiac Arrests. , 2016, Pediatric critical care medicine : a journal of the Society of Critical Care Medicine and the World Federation of Pediatric Intensive and Critical Care Societies.

[14]  Anthony Rowe,et al.  Specialized Storage for Big Numeric Time Series , 2013, HotStorage.

[15]  Danny Eytan,et al.  Atrial fibrillation classification using step-by-step machine learning , 2018 .

[16]  Andrew Y. Ng,et al.  Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks , 2017, ArXiv.

[17]  Peter Fritzson,et al.  Lossless compression of high-volume numerical data from simulations , 2000, Proceedings DCC 2000. Data Compression Conference.

[18]  Ari Ercole,et al.  HDF5-Based Data Format for Archiving Complex Neuro-monitoring Data in Traumatic Brain Injury Patients. , 2018, Acta neurochirurgica. Supplement.

[19]  Dirk Timmermann,et al.  Enabling artificial intelligence in high acuity medical environments , 2019, Minimally invasive therapy & allied technologies : MITAT : official journal of the Society for Minimally Invasive Therapy.

[20]  S. Haranath,et al.  Pressure control ventilation. , 2007, Critical care clinics.

[21]  J. M. Eklund,et al.  Real-Time Analysis for Intensive Care: Development and Deployment of the Artemis Analytic System , 2010, IEEE Engineering in Medicine and Biology Magazine.

[22]  G D Clifford,et al.  Signal quality indices and data fusion for determining clinical acceptability of electrocardiograms , 2012, Physiological measurement.

[23]  Shiming Yang,et al.  Linking Big Data and Prediction Strategies: Tools, Pitfalls, and Lessons Learned , 2019, Critical care medicine.

[24]  G. Berntson,et al.  ECG artifacts and heart period variability: don't miss a beat! , 1998, Psychophysiology.

[25]  Michael Philippsen,et al.  Chronix: Long Term Storage and Retrieval Technology for Anomaly Detection in Operational Data , 2017, FAST.

[26]  Lan Huang,et al.  An overview of online based platforms for sharing and analyzing electrophysiology data from big data perspective , 2017, WIREs Data Mining Knowl. Discov..

[27]  J. L. Hudson,et al.  Breath-by-breath analysis of cardiorespiratory interaction for quantifying developmental maturity in premature infants. , 2012, Journal of applied physiology.

[28]  Carolyn McGregor,et al.  Real-Time Analysis for Intensive Care , 2010 .

[29]  Hyung-Chul Lee,et al.  Vital Recorder—a free research tool for automatic recording of high-resolution time-synchronised physiological data from multiple anaesthesia devices , 2018, Scientific Reports.

[30]  Geoffrey C. Fox,et al.  Examining the Challenges of Scientific Workflows , 2007, Computer.

[31]  Anton Burykin,et al.  Using "off-the-shelf" tools for terabyte-scale waveform recording in intensive care: Computer system design, database description and lessons learned , 2011, Comput. Methods Programs Biomed..

[32]  Phyllis K Stein,et al.  Challenges of heart rate variability research in the ICU. , 2013, Critical care medicine.

[33]  Alan Edelman,et al.  Julia: A Fresh Approach to Numerical Computing , 2014, SIAM Rev..

[34]  Harlan M Krumholz,et al.  Health Care and Precision Medicine Research: Analysis of a Scalable Data Science Platform , 2019, Journal of medical Internet research.

[35]  Shiming Yang,et al.  Reliable Collection of Real-Time Patient Physiologic Data from less Reliable Networks: a “Monitor of Monitors” System (MoMs) , 2016, Journal of Medical Systems.

[36]  Matthieu Komorowski,et al.  Artificial intelligence in intensive care: are we there yet? , 2019, Intensive Care Medicine.

[37]  B Rajeswari Matam,et al.  Technical challenges related to implementation of a formula one real time data acquisition and analysis system in a paediatric intensive care unit , 2017, Journal of Clinical Monitoring and Computing.

[38]  Rishikesan Kamaleswaran,et al.  PhysOnline: An Open Source Machine Learning Pipeline for Real-Time Analysis of Streaming Physiological Waveform , 2019, IEEE Journal of Biomedical and Health Informatics.

[39]  Martin Isenburg,et al.  LASzip: Lossless Compression of Lidar Data , 2013 .

[40]  Farhad Kaffashi,et al.  Information Technology in Critical Care: Review of Monitoring and Data Acquisition Systems for Patient Care and Research , 2015, TheScientificWorldJournal.

[41]  Jimeng Sun,et al.  Opportunities and challenges in developing deep learning models using electronic health records data: a systematic review , 2018, J. Am. Medical Informatics Assoc..

[42]  T. Penzel,et al.  Modulations of Heart Rate, ECG, and Cardio-Respiratory Coupling Observed in Polysomnography , 2016, Front. Physiol..

[43]  P. Novak,et al.  Influence of respiration on heart rate and blood pressure fluctuations. , 1993, Journal of applied physiology.

[44]  Gilles Clermont,et al.  Using what you get: dynamic physiologic signatures of critical illness. , 2015, Critical care clinics.

[45]  Shamim Nemati,et al.  Machine Learning and Decision Support in Critical Care , 2016, Proceedings of the IEEE.

[46]  John Zaleski.  Connected Medical Devices: Integrating Patient Care Data in Healthcare Systems , 2015 .

[47]  Peter Smielewski,et al.  Medical Device Connectivity Challenges Outline the Technical Requirements and Standards For Promoting Big Data Research and Personalized Medicine in Neurocritical Care. , 2018, Military medicine.

[48]  Michael Stonebraker,et al.  "One Size Fits All": An Idea Whose Time Has Come and Gone (Abstract) , 2005, ICDE.

[49]  Qi Huang,et al.  Gorilla: A Fast, Scalable, In-Memory Time Series Database , 2015, Proc. VLDB Endow..

[50]  Masoumeh Haghpanahi,et al.  Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network , 2019, Nature Medicine.

[51]  Jonathan P. Palma,et al.  Development of data dictionary for neonatal intensive care unit: advancement towards a better critical care unit , 2019, JAMIA open.

[52]  Michael Brudno,et al.  Prediction of Cardiac Arrest from Physiological Signals in the Pediatric ICU , 2018, MLHC.

[53]  Nur A. Touba,et al.  Relationship Between Entropy and Test Data Compression , 2007, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[54]  Kenneth A. Loparo,et al.  Data Acquisition and Complex Systems Analysis in Critical Care: Developing the Intensive Care Unit of the Future , 2010 .

[55]  Maysam F. Abbod,et al.  Design and Evaluation of a Real Time Physiological Signals Acquisition System Implemented in Multi-Operating Rooms for Anesthesia , 2018, Journal of Medical Systems.

[56]  Danny Eytan,et al.  Temporal Variability in the Sampling of Vital Sign Data Limits the Accuracy of Patient State Estimation. , 2019, Pediatric critical care medicine : a journal of the Society of Critical Care Medicine and the World Federation of Pediatric Intensive and Critical Care Societies.

[57]  Pierre Baldi,et al.  Machine learning of physiological waveforms and electronic health record data to predict, diagnose and treat haemodynamic instability in surgical patients: protocol for a retrospective study , 2019, BMJ Open.

[58]  Valentina Baljak,et al.  A scalable realtime analytics pipeline and storage architecture for physiological monitoring big data , 2018 .

[59]  James McNames,et al.  Physiologic data acquisition system and database for the study of disease dynamics in the intensive care unit* , 2003, Critical care medicine.

[60]  David M. Maslove,et al.  A path to precision in the ICU , 2017, Critical Care.

[61]  Lionel Tarassenko,et al.  Experiences implementing a system for widespread recording of patient physiology , 2015 .

[62]  David E. Culler,et al.  BTrDB: Optimizing Storage System Design for Timeseries Processing , 2016, FAST.

[63]  Samuel Madden,et al.  Sprintz , 2018, Proc. ACM Interact. Mob. Wearable Ubiquitous Technol..

[64]  John Allen.  Photoplethysmography and its application in clinical physiological measurement , 2007, Physiological measurement.

[65]  Hans-Arno Jacobsen,et al.  Waveform Signal Entropy and Compression Study of Whole-Building Energy Datasets , 2019, e-Energy.

[66]  M. Sabarimalai Manikandan,et al.  A novel method for detecting R-peaks in electrocardiogram (ECG) signal , 2012, Biomed. Signal Process. Control..

[67]  Jean-Pierre Delplanque,et al.  Development of a research-oriented system for collecting mechanical ventilator waveform data , 2018, J. Am. Medical Informatics Assoc..

[68]  Amandeep Kaur,et al.  A Review of ECG Data Compression Techniques , 2015 .

[69]  Chien-Hung Chen,et al.  Heart beats in the cloud: distributed analysis of electrophysiological 'Big Data' using cloud computing for epilepsy clinical research , 2014, J. Am. Medical Informatics Assoc..

[70]  Deep Ganguli,et al.  Druid: a real-time analytical data store , 2014, SIGMOD Conference.

[71]  Henry Ogoe,et al.  Variability in Vital Sign Documentation As a Barrier to Modeling Patient State: Why Patient Records May Need More Complexity! , 2019, Pediatric critical care medicine : a journal of the Society of Critical Care Medicine and the World Federation of Pediatric Intensive and Critical Care Societies.

[72]  Tapio Seppänen,et al.  Low-frequency oscillations in R–R interval and blood pressure across the continuum of cardiovascular risk , 2010, Autonomic Neuroscience.

[73]  Leonid Boytsov,et al.  Decoding billions of integers per second through vectorization , 2012, Softw. Pract. Exp..

[74]  Mohammed Saeed,et al.  Design and implementation of a hospital wide waveform capture system , 2015, Journal of Clinical Monitoring and Computing.

[75]  Danny Eytan,et al.  Revisiting oxygen dissociation curves and bedside measured arterial saturation in critically ill children , 2019, Intensive Care Medicine.

[76]  Michael Sauthier,et al.  Creating a High-Frequency Electronic Database in the PICU: The Perpetual Patient* , 2018, Pediatric critical care medicine : a journal of the Society of Critical Care Medicine and the World Federation of Pediatric Intensive and Critical Care Societies.

[77]  M. Villarroel,et al.  Waveform Analysis to Estimate Respiratory Rate , 2016 .

[78]  Benjamin H. Brinkmann,et al.  Large-scale electrophysiology: Acquisition, compression, encryption, and storage of big data , 2009, Journal of Neuroscience Methods.

[79]  Torben Bach Pedersen,et al.  Time Series Management Systems: A Survey , 2017, IEEE Transactions on Knowledge and Data Engineering.

[80]  Thomas Heldt,et al.  A Waveform Archiving System for the GE Solar 8000i Bedside Monitor. , 2018, Acta neurochirurgica. Supplement.

[81]  Farhad Kaffashi,et al.  Data Collection and Analysis in the ICU , 2019, Neurocritical Care Informatics.

[82]  C. Naylor,et al.  On the Prospects for a (Deep) Learning Health Care System , 2018, JAMA.

[83]  Matthias Görges,et al.  University of Queensland Vital Signs Dataset: Development of an Accessible Repository of Anesthesia Patient Monitoring Data for Research , 2012, Anesthesia and analgesia.

[84]  I. Karhonen,et al.  The challenges in creating critical-care databases , 2001, IEEE Engineering in Medicine and Biology Magazine.

[85]  Qiao Li,et al.  Artificial arterial blood pressure artifact models and an evaluation of a robust blood pressure and heart rate estimator , 2009, Biomedical engineering online.

[86]  Fei Wang,et al.  Deep Learning in Medicine-Promise, Progress, and Challenges. , 2019, JAMA internal medicine.

[87]  Antonello Lobianco.  Interfacing Julia with Other Languages , 2019 .

[88]  Henrique M. G. Martins,et al.  Preprocessing structured clinical data for predictive modeling and decision support , 2016, Applied Clinical Informatics.

[89]  Yue-Der Lin,et al.  An Efficient Lossless ECG Compression Method Using Delta Coding and Optimal Selective Huffman Coding , 2010 .

[90]  Leo Anthony Celi,et al.  Critical Care, Critical Data , 2019, Biomedical engineering and computational biology.