• Login
    • Join
  • FOLLOW:
  • Subscribe Free
    • Magazine
    • eNewsletter
    Checkout
    • Magazine
    • News
    • Opinions
    • Top 30
    • Research
    • Supply Chain
    • Device Sectors
    • Directory
    • Events
    • Resources
    • Microsites
    • More
  • Magazine
  • News
  • Opinions
  • Top 30
  • Research
  • Supply Chain
  • Device Sectors
  • Directory
  • Events
  • Resources
  • Microsites
  • Current / Back Issues
    Features
    Editorial
    Digital Edition
    eNewsletter Archive
    Our Team
    Editorial Guidelines
    Reprints
    Subscribe Now
    Advertise Now
    Top Features
    Sensing Technology Drives the Future of Medical Care

    New and Developing Diabetes Technologies Offer 'Sweet Relief'

    Discussing Matters of Substance in Medtech Materials

    Medical Device Testers Are Caught Up in a Whirlwind

    6 Ways ERP Systems Help Medical Device Manufacturers Manage Risk and Profitability
    OEM News
    Supplier News
    Service / Press Releases
    Online Exclusives
    Press Releases
    People in the News
    Product & Service Releases
    Supplier News
    Medtech Makers
    Technical Features
    International News
    Videos
    Product & Service Releases
    Live From Shows
    Regulatory
    Financial/Business
    Top News
    Getinge iCast Receives FDA Premarket Approval

    Tessy Plastics Corp. Celebrates 50th Anniversary

    Carium Expands Customization Options with Care Pathways

    InBody Supplying U.S. Marine Corps With Body Composition Analysis Devices

    Blackford and Brainomix Collaborate to Improve Stroke Care
    From the Editor
    Blogs
    Guest Opinions
    Top Opinions
    Sensing Technology Drives the Future of Medical Care

    New and Developing Diabetes Technologies Offer 'Sweet Relief'

    Discussing Matters of Substance in Medtech Materials

    Medical Device Testers Are Caught Up in a Whirlwind

    6 Ways ERP Systems Help Medical Device Manufacturers Manage Risk and Profitability
    Top 30 Medical Device Companies
    Market Data
    White Papers
    Top Research
    CR-SOP Neurotechnology Helps to Achieve ‘Sound’ Sleep

    Inside the Hospital Value Analysis Committee

    Face Time: Why Getting Engineers Out of the Lab Is Good for Business

    Common Paratubing Pitfalls and How to Avoid Them

    During Times of Uncertainty, Create Business Value with an Optimized Workforce
    3D/Additive Manufacturing
    Contract Manufacturing
    Electronics
    Machining & Laser Processing
    Materials
    Molding
    Packaging & Sterilization
    R&D & Design
    Software & IT
    Testing
    Tubing & Extrusion
    Cardiovascular
    Diagnostics
    Digital Health
    Neurological
    Patient Monitoring
    Surgical
    Orthopedics
    All Companies
    Categories
    Company Capabilities
    Add New Company
    Outsourcing Directory
    Medbio LLC

    JBC Technologies

    Cirtec Medical

    Providence Enterprise USA Inc.

    NDH Medical Inc.
    MPO Summit
    Industry Events
    Webinars
    Live From Show Event
    Industry Associations
    Videos
    Career Central
    eBook
    Slideshows
    Top Resources
    3D Printing Medical Devices Revolutionized Manufacturing

    5 Current Trends in Medical Device Security

    How Advanced Sensors Improve Design & Functionality of Respiratory Care Equipment

    Sourcing Silicone Parts: Injection Mold or 3D Print?

    Cybersecurity in Healthcare: Getting on the Right Track
    Companies
    News Releases
    Product Releases
    Press Releases
    Product Spec Sheets
    Service Releases
    Case Studies
    White Papers
    Brochures
    Videos
    Outsourcing Directory
    Medbio LLC

    JBC Technologies

    Cirtec Medical

    Providence Enterprise USA Inc.

    NDH Medical Inc.
    • Magazine
      • Current/Back Issues
      • Features
      • Editorial
      • Columns
      • Digital Editions
      • Subscribe Now
      • Advertise Now
    • News
    • Directory
      • All Companies
      • ALL CATEGORIES
      • Industry Associations
      • Company Capabilities
      • Add Your Company
    • Supply Chain
      • 3D/Additive Manufacturing
      • Contract Manufacturing
      • Electronics
      • Machining & Laser Processing
      • Materials
      • Molding
      • Packaging & Sterilization
      • R&D & Design
      • Software & IT
      • Testing
      • Tubing & Extrusion
    • Device Sectors
      • Cardiovascular
      • Diagnostics
      • Digital Health
      • Neurological
      • Patient Monitoring
      • Surgical
      • Orthopedics
    • Top 30 Company Report
    • Expert Insights
    • Slideshows
    • Videos
    • eBook
    • Resources
    • Podcasts
    • Infographics
    • Whitepapers
    • Research
      • White Papers
      • Case Studies
      • Product Spec Sheets
      • Market Data
    • MPO Summit
    • Events
      • Industry Events
      • Live From Show Events
      • Webinars
    • Microsite
      • Companies
      • Product Releases
      • Product Spec Sheets
      • Services
      • White Papers / Tech Papers
      • Press Releases
      • Videos
      • Literature / Brochures
      • Case Studies
    • About Us
      • About Us
      • Contact Us
      • Advertise with Us
      • eNewsletter Archive
      • Privacy Policy
      • Terms of Use
    Online Exclusives

    How to Improve ECG Rhythm Recognition Using a DCNN

    Comparing and contrasting methods of quality enhancement.

    How to Improve ECG Rhythm Recognition Using a DCNN
    Sergey Kuznetsov, Software Engineer, Auriga07.06.20
    Recently, I published a piece on recognizing ECG rhythms using a deep convolutional neural network (DCNN). The article argues that the reliable recognition of certain heart rhythm pathologies can be performed based on the monitored recordings of two to three patients with that pathology. In this article, the same DCNN and data were used to demonstrate that recognition can be improved by both neural network reconfiguration and input data enhancement.
     
    This article describes three methods of quality enhancement I have investigated:
     
    • Data split interval adjustment.
    • The “transfer learning” method.
    • Balancing classes.
     
    The transfer learning method is based on the assumption that the features of a neural network that have been trained to extract data from a large bulk of data labeled for a task would be suitable for solving another task, usually with less data. Before reducing the number of trainings, the weights for the final layers are cleared. When there is a task that has a different number of classes, the parameters of the final layer are changed.
     
    The task in the review used the same 16-layer convolutional neural network and the same freely available ECG data from one lead (mitdb) discussed in the previous article. Additionally, the labeled data of the 2017 competition published on physionet.org was used where training was held for four classes on ECG implementations lasting 9–60 seconds. For the possibility of joint use, the source data (360 samples per second) were resampled into the input rate of additional data (300 samples per second).
     
    The following describes the application of the three abovementioned methods of input data enhancement for the two versions of the classification task discussed in the previous article (with/without the separation of training data and test data). The version without separation used methods (1) and (2). For the separation option, methods (1), (2), and (3) were used.
     
    1. Data Split Interval Adjustment
    As expected, splitting data into five-second intervals instead of 10-second intervals (method 1) led to a relative decrease in the quality of recognition of atrial fibrillation (AFIB); however, previously unrecognized NOD and IVR rhythms were added. This can be explained by a decrease in data snippet losses, which is particularly important for classes with a small amount of data. The overall index for "ranking-based average precision" (RBAP) increased from 0.968 to 0.975.
     
    Reducing the length of the implementation at the input of the neural network led to its inoperability. This was offset by changing the parameters of the first layer (1D-convolution): the size of the convolution kernel was halved and the stride was reduced from three to two.
     
    To improve the result, “transfer learning” (method 2) with a variable number of erasable layers was implemented. RBAP increased to 0.984 and in this case, it was optimal to erase the weights of not only one or two layers but 10–13 out of the 16 layers (Figure 1).


    Figure 1.

    2. The “Transfer” Learning Method
    Leaping ahead, this “fair and square” option is the only valuable one for practical use. Splitting data into five-second intervals (method 1) resulted in IVR rhythm recognition addition and an RBAP increase from 0.804 to 0.826. The method of “transfer learning” (method 2) with the erasure of the weights of ten layers (optimal for this option) added AFL rhythm recognition and RBAP was increased to 0.885.
     
    Significant results were only obtained for six recognizable rhythm classes using “learning transfer”; these are presented in Table 1:
     
    Classification report   Confusion matrix
    Precision Recall f1-score support rhythm N AFIB P B AFL IVR
    0.98 0.98 0.98 342 N 334 8 0 0 0 0
    0.90 0.83 0.86 260 AFIB 4 215 0 1 40 0
    1.00 0.99 1.00 638 P 0 1 632 0 0 5
    0.96 0.83 0.89 58 B 0 0 0 48 0 1
    0.76 0.95 0.84 132 AFL 0 0 0 1 125 0
    0.87 0.95 0.91 42 IVR 2 0 0 0 0 40
     
    0.95 1472 Accuracy
    0.91 0.92 0.91 1472 Macro average
    0.95 0.95 0.95 1472 Weighted average
    0.973       Ranking-based average precision (RBAP)

    3. Balancing Classes
    The attempt to use all realizations (nine rhythm classes) that resulted from splitting data for training and to use the alignment of classes by the number of copies previously used by decimation was unsuccessful; the significant differences in class capacities may be to blame. Both direct data processing and an indication of the weight coefficients of the classes inverse to the class power were tested (method 3). However, both options yielded worse results than equalizing class capacities, with the only the rather uninteresting exception of when neither “learning transfer” nor class weights were used.
     
    Thus, in the option described above where data is split into five-second intervals, the power of classes is aligned during training and using the “transfer learning” method becomes the best option.
     

    Sergey Kuznetsov is a software engineer at Auriga.
    Related Searches
    • Cardiovascular
    Related Knowledge Center
    • Cardiovascular
    Suggested For You
    Electroducer Raises 3 Million Euros to Market Heart Valve Disease Tech Electroducer Raises 3 Million Euros to Market Heart Valve Disease Tech
    Paragonix Launches Global Registry for Studying Donor Lung Preservation Paragonix Launches Global Registry for Studying Donor Lung Preservation
    Aleva Neurotherapeutics Recruits First Patient Into PMCF Study Aleva Neurotherapeutics Recruits First Patient Into PMCF Study
    Closed Loop Thermal Control in Medical Devices Closed Loop Thermal Control in Medical Devices
    Biomedical Engineers Grow 3D Bioprinted Blood Vessel Biomedical Engineers Grow 3D Bioprinted Blood Vessel
    FDA OKs BrainsWay Deep TMS to Reduce Anxiety in Depressed Patients FDA OKs BrainsWay Deep TMS to Reduce Anxiety in Depressed Patients
    First Clinical Use of SoundBite Medical First Clinical Use of SoundBite Medical's Active Wire Platform
    FDA OKs SpinTech FDA OKs SpinTech's STAGE MRI Software
    Electronics Integration Impacting Medtech Materials Electronics Integration Impacting Medtech Materials
    Nova POC Creatinine/eGFR Method More Accurate Than Lab Method Nova POC Creatinine/eGFR Method More Accurate Than Lab Method
    Researchers Develop Noninvasive Method for Measuring Brain Blood Flow with Light Researchers Develop Noninvasive Method for Measuring Brain Blood Flow with Light
    RSIP Vision Launches Prostate MRI-to-Ultrasound Registration Tool RSIP Vision Launches Prostate MRI-to-Ultrasound Registration Tool
    CerTest Biotec & BD Add Saliva to the Visasure SARS-CoV-2 Detection Kit CerTest Biotec & BD Add Saliva to the Visasure SARS-CoV-2 Detection Kit
    Berlin Heals Berlin Heals' C-MIC Heart Failure Implant Achieves Breakthrough Device Status
    Biomechanical Engineer, Heal Thyself Biomechanical Engineer, Heal Thyself

    Related Breaking News

    • Electroducer Raises 3 Million Euros to Market Heart Valve Disease Tech

      Electroducer Raises 3 Million Euros to Market Heart Valve Disease Tech

      Electroducer Sleeve based on a medical technique called Direct Wire Pacing, which was invented by the company’s founder.
      Electroducer 09.21.21

    • Paragonix Launches Global Registry for Studying Donor Lung Preservation

      Paragonix Launches Global Registry for Studying Donor Lung Preservation

      Registry will capture data on how organ preservation and transportation impact patient outcomes in lung transplantation.
      Business Wire 09.20.21

    • Aleva Neurotherapeutics Recruits First Patient Into PMCF Study

      Aleva Neurotherapeutics Recruits First Patient Into PMCF Study

      Study aims to demonstrate improved outcomes with Aleva´s directSTIM Directional Deep Brain Stimulation system.
      Globe Newswire 09.01.21


    • Electronics | R&D & Design
      Closed Loop Thermal Control in Medical Devices

      Closed Loop Thermal Control in Medical Devices

      A closed-loop feedback approach is an effective mechanism to address thermal control challenges.
      Kenneth MacCallum, P.Eng., Principal Engineering Physicist, StarFish Medical 08.30.21

    • Cardiovascular
      Biomedical Engineers Grow 3D Bioprinted Blood Vessel

      Biomedical Engineers Grow 3D Bioprinted Blood Vessel

      Paves the way for possible cardiovascular drug advancements with better precision.
      Texas A&M Engineering 08.19.21

    Loading, Please Wait..

    Trending
    • Victoria Carr-Brendel Joins Vicarious Surgical Board
    • FDA Clears LiveMetric's Wearable Blood Pressure Monitoring Tech
    • InBody Supplying U.S. Marine Corps With Body Composition Analysis Devices
    • The Future Of Biomedical Engineering Advancements
    • Tessy Plastics Corp. Celebrates 50th Anniversary
    Breaking News
    • Getinge iCast Receives FDA Premarket Approval
    • Tessy Plastics Corp. Celebrates 50th Anniversary
    • Carium Expands Customization Options with Care Pathways
    • InBody Supplying U.S. Marine Corps With Body Composition Analysis Devices
    • Blackford and Brainomix Collaborate to Improve Stroke Care
    View Breaking News >
    CURRENT ISSUE

    March 2023

    • Sensing Technology Drives the Future of Medical Care
    • New and Developing Diabetes Technologies Offer 'Sweet Relief'
    • Discussing Matters of Substance in Medtech Materials
    • Medical Device Testers Are Caught Up in a Whirlwind
    • View More >

    Cookies help us to provide you with an excellent service. By using our website, you declare yourself in agreement with our use of cookies.
    You can obtain detailed information about the use of cookies on our website by clicking on "More information”.

    • About Us
    • Privacy Policy
    • Terms And Conditions
    • Contact Us

    follow us

    Subscribe
    Nutraceuticals World

    Latest Breaking News From Nutraceuticals World

    NPA: ‘Major Victory’ in Colorado After Amendment to Eating Disorder Bill
    GOOD Meat Receives FDA Go-Ahead for Cultured Meat
    IFF Achieves Industrial-Scale Production of Anaerobic Probiotic Strain
    Coatings World

    Latest Breaking News From Coatings World

    HOFFMANN MINERAL to Focus on Comprehensive Sustainability Strategy
    HMG and Prodrive Renew Technical Partnership
    Eastern Coatings Show Sets Schedule for Technical Papers
    Medical Product Outsourcing

    Latest Breaking News From Medical Product Outsourcing

    Getinge iCast Receives FDA Premarket Approval
    Tessy Plastics Corp. Celebrates 50th Anniversary
    Carium Expands Customization Options with Care Pathways
    Contract Pharma

    Latest Breaking News From Contract Pharma

    Willow, Suanfarma Complete Manufacturing Process for Cannabigerol
    Berkshire Sterile to Install nearly 1,500 solar panels at Massachusetts site
    Harm Reduction Therapeutics, Catalent Ink Naloxone Commercial Supply Pact
    Beauty Packaging

    Latest Breaking News From Beauty Packaging

    Interpack 2023 Introduces New Special Areas and Activities
    eSalon Expands into Over 1,900 CVS Stores Nationwide
    The RealReal Discontinues Beauty Business
    Happi

    Latest Breaking News From Happi

    Inolex Launches Sustainable BTAC Replacement AminoSensyl Ultra MB
    A New Way To Measure Skin Barrier Function: Research
    P&G Patents Laundry Scent Additive
    Ink World

    Latest Breaking News From Ink World

    Eastern Coatings Show Announces Schedule for Technical Papers
    Pulse Roll Label Products Adds Sean Labas to Technical Sales Team
    Amcor, Nfinite Enter into Agreement on Recyclable Packaging
    Label & Narrow Web

    Latest Breaking News From Label & Narrow Web

    TLMI announces 2022 Eugene Singer Award winners
    Pulse Roll Label Products expands technical sales team
    Mark Andy introduces ProWORX Label Suite
    Nonwovens Industry

    Latest Breaking News From Nonwovens Industry

    Heartland Polymers Begins Production in Alberta
    Zeta Polimeri Becomes Radici EcoMaterials
    Responsible Flushing Alliance Holds Annual Meeting
    Orthopedic Design & Technology

    Latest Breaking News From Orthopedic Design & Technology

    AI is Effective at Documenting Orthopedic Encounters in Hand Surgery
    3D LifePrints Rebrands to Insight Surgery & Launches New Business in Houston
    Companion Spine Closes $60.1 Million Series A Funding Round
    Printed Electronics Now

    Latest Breaking News From Printed Electronics Now

    Midsummer, UCLA Collaborate on Perovskite-CIGS Tandem Solar Cells
    HID Reports on Reshaping the Security Industry
    Meyers Introduces New Function47 Division

    Copyright © 2023 Rodman Media. All rights reserved. Use of this constitutes acceptance of our privacy policy The material on this site may not be reproduced, distributed, transmitted, or otherwise used, except with the prior written permission of Rodman Media.

    AD BLOCKER DETECTED

    Our website is made possible by displaying online advertisements to our visitors.
    Please consider supporting us by disabling your ad blocker.


    FREE SUBSCRIPTION Already a subscriber? Login