Journal of Electrical and Electronics Engineering Research
Subscribe to JEEER
Full Name*
Email Address*

Article Number - 13B00A38058


Vol.2(2), pp. 025-047 , March 2010

ISSN: 1993-8225


 Total Views: 0
 Downloaded: 0

Full Length Research Paper

Detection of acute hypotensive episodes via a trained adaptive network-based fuzzy inference system (ANFIS)


A. Ghaffari1,2, M. R. Homaeinezhad1,2*, M. Atarod2, M. Akraminia1,2 and H. Najjaran Toosi1,2




1CardioVascular Research Group (CVRG), Iran.

2Department of Mechanical Engineering, K. N. Toosi University of Technology, No. 15, Pardis Street, Mollasadra Avenue, Vanak Sq., Tehran, P. O. Box 19395-1999, Iran


Email: [email protected]






 Accepted: 27 September 2009  Published: 31 March 2010

Copyright © 2010 Author(s) retain the copyright of this article.
This article is published under the terms of the Creative Commons Attribution License 4.0


The aim of this study is to detect acute hypotensive episodes (AHE) and mean arterial pressure dropping regimes (MAPDRs) using ECG signal and arterial blood pressure (ABP) waveforms. To meet this end, the QRS complexes and end-systolic end-diastolic pulses are first extracted using two innovative modified Hilbert transform-based algorithms namely as ECGMHT and BPMHT. The resulted systolic blood pressure (SBP) and diastolic blood pressure (DBP) pulses are then used to calculate the mean arterial pressure (MAP) trend. A new smoothing algorithm is then developed based on piecewise polynomial fitting (PPF) to smooth the fast fluctuations observed in RR-tachogram and MAP trend. The PPF algorithm operates by sequentially fitting N number of polynomials to the original signal and calculating the corresponding coefficients using the Best Linear Unbiased Estimation (BLUE) approach. Afterwards, in order to consider the mutual influence of parameters on the evaluation of shock probability, a Sugeno adaptive network-based fuzzy inference system-ANFIS is trained using Hasdai et al. parameters as input, with appropriate membership functions for each parameter. Using this network, it will be possible to incorporate the possible mutual influences between risk parameters such as heart rate (HR), systolic blood pressure (SBP), diastolic blood pressure (DBP), age, gender, weight and some miscellaneous factors to the calculation of shock occurrence probability. In the next step, the proposed algorithm is applied to 15 subjects of the MIMIC II database and AHE and MAPDRs (MAP ≤ 60 mmHg with a period of 30 min or more) are identified. As a result of this study, MAPDR is realized as a specific marker of cardiogenic shock. In that, for a sequence of MAPDRs; as long as 20 min or more, there will exist a consequent high peak with the duration of 3 to 4 min in the corresponding probability of cardiogenic shock diagram. The presented algorithm did not yield any inappropriate or wrong results on MIMICII database (that is false negative = false positive = 0).

 

Key words: Acute hypotensive episode, cardiogenic shock, blood pressure pulse detection, piecewise polynomial fitting, ANFIS approximation.


APA (2010). Detection of acute hypotensive episodes via a trained adaptive network-based fuzzy inference system (ANFIS). Journal of Electrical and Electronics Engineering Research, 2(2), 025-047.
Chicago A. Ghaffari, M. R. Homaeinezhad, M. Atarod, M. Akraminia, and H. Najjaran Toosi,. "Detection of acute hypotensive episodes via a trained adaptive network-based fuzzy inference system (ANFIS)." Journal of Electrical and Electronics Engineering Research 2, no. 2 (2010): 025-047.
MLA A. Ghaffari, et al. "Detection of acute hypotensive episodes via a trained adaptive network-based fuzzy inference system (ANFIS)." Journal of Electrical and Electronics Engineering Research 2.2 (2010): 025-047.
   
DOI https://doi.org/
URL http://academicjournals.org/journal/JEEER/article-abstract/13B00A38058

Subscription Form