Display options
Cite
Gajowniczek K, Grzegorczyk I, Ząbkowski T, et al. Weighted Random Forests to Improve Arrhythmia Classification. Electronics (Basel). 2020;9(1)doi: 10.3390/electronics9010099.
Gajowniczek, K., Grzegorczyk, I., Ząbkowski, T., & Bajaj, C. (2020). Weighted Random Forests to Improve Arrhythmia Classification. Electronics, 9(1), . https://doi.org/10.3390/electronics9010099
Gajowniczek, Krzysztof, et al. "Weighted Random Forests to Improve Arrhythmia Classification." Electronics vol. 9,1 (2020). doi: https://doi.org/10.3390/electronics9010099
Gajowniczek K, Grzegorczyk I, Ząbkowski T, Bajaj C. Weighted Random Forests to Improve Arrhythmia Classification. Electronics (Basel). 2020 Jan;9(1). doi: 10.3390/electronics9010099. Epub 2020 Jan 03. PMID: 32051761; PMCID: PMC7015067.
Copy Download .nbib Format: NLM
Share it on

Electronics (Basel). 2020 Jan;9(1). doi: 10.3390/electronics9010099. Epub 2020 Jan 03.

Weighted Random Forests to Improve Arrhythmia Classification.

Electronics

Krzysztof Gajowniczek, Iga Grzegorczyk, Tomasz Ząbkowski, Chandrajit Bajaj

Affiliations

  1. Department of Artificial Intelligence, Institute of Information Technology, Warsaw University of Life Sciences - SGGW, 02-776 Warsaw, Poland.
  2. Department of Physics of Complex Systems, Faculty of Physics, Warsaw University of Technology, 00-662 Warsaw, Poland.
  3. Department of Computer Science, Institute for Computational Engineering and Sciences, University of Texas at Austin, Austin, TX 78712.

PMID: 32051761 PMCID: PMC7015067 DOI: 10.3390/electronics9010099

Abstract

Construction of an ensemble model is a process of combining many diverse base predictive learners. It arises questions of how to weight each model and how to tune the parameters of the weighting process. The most straightforward approach is simply to average the base models. However, numerous studies have shown that a weighted ensemble can provide superior prediction results to a simple average of models. The main goals of this article are to propose a new weighting algorithm applicable for each tree in the Random Forest model and the comprehensive examination of the optimal parameter tuning. Importantly, the approach is motivated by its flexibility, good performance, stability, and resistance to overfitting. The proposed scheme is examined and evaluated on the Physionet/Computing in Cardiology Challenge 2015 data set. It consists of signals (electrocardiograms and pulsatory waveforms) from intensive care patients which triggered an alarm for five cardiac arrhythmia types (Asystole, Bradycardia, Tachycardia, Ventricular Tachycardia, and Ventricular Fultter/Fibrillation). The classification problem regards whether the alarm should or should not have been generated. It was proved that the proposed weighting approach improved classification accuracy for the three most challenging out of the five investigated arrhythmias comparing to the standard Random Forest model.

Keywords: arrhythmia; false alarm; machine learning; weighted random forest

Conflict of interest statement

Conflicts of Interest: The authors declare no conflict of interest.

References

  1. Physiol Meas. 2012 Jul;33(7):1135-50 - PubMed
  2. Physiol Meas. 2016 Aug;37(8):1204-16 - PubMed
  3. Physiol Meas. 2015 Aug;36(8):1743-61 - PubMed
  4. Comput Methods Programs Biomed. 2017 Apr;141:119-127 - PubMed
  5. Physiol Meas. 2015 Aug;36(8):1629-44 - PubMed
  6. Sensors (Basel). 2019 Apr 02;19(7): - PubMed
  7. IEEE Trans Biomed Eng. 1985 Mar;32(3):230-6 - PubMed
  8. Med Biol Eng Comput. 1997 Nov;35(6):626-32 - PubMed
  9. Physiol Meas. 2016 Aug;37(8):1298-312 - PubMed
  10. IEEE Trans Biomed Eng. 2014 Mar;61(3):832-40 - PubMed
  11. Stat Interface. 2009 Jan 1;2(3):381 - PubMed
  12. Physiol Meas. 2016 Aug;37(8):1313-25 - PubMed
  13. J Biomed Inform. 2016 Dec;64:1-9 - PubMed
  14. Biomed Eng Online. 2004 Aug 27;3(1):28 - PubMed
  15. PLoS One. 2015 Oct 13;10(10):e0140123 - PubMed
  16. Cancer. 1950 Jan;3(1):32-5 - PubMed
  17. Healthc Technol Lett. 2016 Jul 29;3(3):239-246 - PubMed
  18. Conf Proc IEEE Eng Med Biol Soc. 2011;2011:969-72 - PubMed
  19. Physiol Meas. 2016 Aug;37(8):1233-52 - PubMed
  20. Stat Anal Data Min. 2013 Dec 1;6(6):496-505 - PubMed
  21. Data Min Knowl Discov. 2019;33(6):1674-1709 - PubMed
  22. IEEE Trans Biomed Eng. 2008 Feb;55(2 Pt 1):478-84 - PubMed
  23. Biomed Eng Online. 2010 Sep 04;9:43 - PubMed
  24. Comput Cardiol (2010). 2015 Sep;2015:273-276 - PubMed
  25. Physiol Meas. 2016 Aug;37(8):1340-54 - PubMed
  26. Ann Biomed Eng. 2014 Jun;42(6):1340-53 - PubMed
  27. Physiol Meas. 2016 Aug;37(8):1253-72 - PubMed
  28. Med Biol Eng Comput. 1987 May;25(3):241-9 - PubMed

Publication Types

Grant support