Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.
Upcoming SlideShare
What to Upload to SlideShare
What to Upload to SlideShare
Loading in …3
×
1 of 35

Automatic Real-time Beat-to-beat Detection of Arrhythmia Conditions (HEALTHINF2021)

0

Share

Download to read offline

In this work we present NEAPOLIS, a novel approach for the accurate detection of arrhythmia conditions. NEAPOLIS takes as input a heartbeat signal, extracted from an ECG trace, and provides as output a
5-class classification of the beat, namely normal sinus rhythm and four main types of arrhythmia conditions.
NEAPOLIS is based on ECG characteristics that do not need a long-term observation of an ECG for the classification of the beat. This choice makes NEAPOLIS a (near) real-time detector of arrhythmia because it allows
the detection within few seconds of ECG observation

* SciTePress Digital Library: https://www.scitepress.org/Link.aspx?doi=10.5220/0010267902120222

Related Books

Free with a 30 day trial from Scribd

See all

Related Audiobooks

Free with a 30 day trial from Scribd

See all

Automatic Real-time Beat-to-beat Detection of Arrhythmia Conditions (HEALTHINF2021)

  1. 1. Automatic Real-time Beat-to-beat Detection of Arrhythmia Conditions Giovanni Rosa, Gennaro Laudato, Angela Rita Colavita, Simone Scalabrino, and Rocco Oliveto
  2. 2. IoT for Healthcare
  3. 3. Internet of Medical Things Preventive care Long-term care and chronic diseases
  4. 4. Internet of Medical Things AI and Smart Wearables for early anomaly detection
  5. 5. Internet of Medical Things Preventive medical support thanks to early notified anomalies
  6. 6. Zhao et al. (2005)
  7. 7. Zhao et al. (2005) Haque et al. (2009)
  8. 8. Zhao et al. (2005) Leonarduzzi et al. (2010) Haque et al. (2009)
  9. 9. Zhao et al. (2005) Leonarduzzi et al. (2010) Li et al. (2016) Haque et al. (2009)
  10. 10. A need for automatic systems having real-time anomaly detection with high accuracy
  11. 11. NovEl APproach for the autOmatic reaL-time beat-to-beat detectIon of arrhythmia conditions (NEAPOLIS)
  12. 12. Arrythmia conditions Left and Right Bundle Branch Block (LBBB and RBBB) Premature Ventricular Contraction (PVC) Atrial Premature Beats (APB)
  13. 13. NEAPOLIS in a nutshell
  14. 14. NEAPOLIS in a nutshell
  15. 15. NEAPOLIS in a nutshell
  16. 16. NEAPOLIS in a nutshell
  17. 17. NEAPOLIS in a nutshell
  18. 18. pre-RR interval post-RR interval local-RR interval Single beat Requires at least 10 heart beats Current and post heart beats Previous and current heart beats Pandey and Janghel (2020) Selected features
  19. 19. Selected features Maximum Overlap Discrete Wavelet Transform (MODWT) Autoregressive Model (AR) Multifractal Wavelet Leader Fast Fourier Transform (FFT) R-R interval descriptors ECG Signal Extracted features
  20. 20. Experiment
  21. 21. MIT-BIH Database 48 ECG Recordings ~110,000 Labelled heart beats 30 Minutes of recording Goldberger et al. (2000); Moody and Mark (2001)
  22. 22. Data extraction Extraction of R peaks annotations Beat segmentation Baseline removal 2-step median filter 200 ms 600 ms Filtered ECG signal 180 samples (360hz signal)
  23. 23. Data extraction ~99,000 heart beats Normal LBBB RBBB PVC APB 70,000 35,000 0
  24. 24. What are the most important features for the beat-to-beat classification of arrhythmia conditions? RQ1
  25. 25. Selected features Maximum Overlap Discrete Wavelet Transform (MODWT) Autoregressive Model (AR) Multifractal Wavelet Leader Fast Fourier Transform (FFT) R-R interval descriptors ECG Signal Feature selection using Random Forest Remove co-correlated features (Pearson > 0.9) Extracted features Feature selection
  26. 26. Selected features - Top 5 dw_4 fft_1 fft_3 cfr_1 pre_rr Importance level dw = Discrete Wavelet fft = Fast Fourier Transform pre_rr = pre-RR interval cfr = AR model reflection coefficient
  27. 27. What is the accuracy of NEAPOLIS? RQ2
  28. 28. Heart Beats classification via LSTM Model Pandey and Janghel (2020) Selected baseline
  29. 29. Classification Train/Test Random Split Repeated 1,000 times, due to split randomness DS1 (training set) and DS2 (test set) 50% - 50%
  30. 30. Classification Class balancing and Feature scaling Random Forest Classifier Train/Test Random Split Repeated 1,000 times, due to split randomness DS1 DS1 (training set) and DS2 (test set) 50% - 50%
  31. 31. Classification Class balancing and Feature scaling Random Forest Classifier Validation Train/Test Random Split Repeated 1,000 times, due to split randomness DS1 (training set) and DS2 (test set) DS1 DS2 50% - 50%
  32. 32. Overall Results Average metrics NEAPOLIS (Pandey et al., 2020) Sensitivity Specificity Precision F1 score 97.16 (+ 2.27) 99.53 (+ 0.39) 97.22 (+ 0.49) 97.18 (+ 1.41) 94.89 99.14 96.73 95.77
  33. 33. Results (for each class) Metric Normal Sensitivity Specificity Precision F1 score LBBB RBBB PVC APB 99.18 (+ 0.21) 99.97 (+ 0.04) 99.68 (+ 0.63) 99.43 (+ 0.42) 98.28 (+ 3.10) 99.61 (- 0.02) 95.02 (- 0.05) 96.62 (+ 1.49) 90.48 (+ 7.00) 99.81 (+ 0.02) 92.49 (+ 0.85) 91.47 (+ 4.10) 98.53 (+ 1.01) 99.96 (+ 0.04) 99.50 (+ 0.45) 99.01 (+ 0.73) 99.34 (+ 0.03) 98.29 (+ 1.84) 99.43 (+ 0.59) 99.39 (+ 0.32)
  34. 34. NEAPOLIS is part of a real IoMT system ATTICUS Ambient-intelligent Tele-monitoring System
  35. 35. Summary The paper has been funded by the PON project ARS01_00860 “Telemonitoraggio e telemetria in ambienti intelligenti per migliorare la sostenibilità umana” ATTICUS - RNA/COR 576347

×