TY - GEN
T1 - Modeling heart rate baroreflex mechanism and its application in predicting acute hypotensive episodes
AU - Jalali, Ali
AU - Nataraj, C.
N1 - Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2011
Y1 - 2011
N2 - In this paper a new nonlinear system identification approach is developed for identification of the heart rate (HR) baroreflex mechanism. The developed model in then used in the task of acute hypotensive episodes (AHE) prediction. The AHE is defined as any period of 30 min or more during which at least 90% of the mean arterial pressure (MAP) measurements are below 60 mmHg. The proposed HR baroreflex model is based on inherent features of the autonomic nervous system for which we develop an adaptive neuro-fuzzy inference system (ANFIS) structure. The model showed significant improvement in HR prediction accuracy in terms of the normalized root mean square error (NRMSE) in comparison with previously reported results. We achieved a value of 0.191 in mean NRMSE in prediction of HR in this paper which is about 20% better than the best reported result in other papers. For the task of AHE prediction, since arterial pressure has a direct correlation with heart rate, we could simply find the periods in which HR drops blow a certain level without losing generality. The demonstrated AHE data for twenty patients are selected to validate the proposed algorithm. Results show that the proposed method could truly predict occurrence of the AHE in 9 out of the 10 cases analyzed. Results show reliable accuracy in predicting AHE in these patients.
AB - In this paper a new nonlinear system identification approach is developed for identification of the heart rate (HR) baroreflex mechanism. The developed model in then used in the task of acute hypotensive episodes (AHE) prediction. The AHE is defined as any period of 30 min or more during which at least 90% of the mean arterial pressure (MAP) measurements are below 60 mmHg. The proposed HR baroreflex model is based on inherent features of the autonomic nervous system for which we develop an adaptive neuro-fuzzy inference system (ANFIS) structure. The model showed significant improvement in HR prediction accuracy in terms of the normalized root mean square error (NRMSE) in comparison with previously reported results. We achieved a value of 0.191 in mean NRMSE in prediction of HR in this paper which is about 20% better than the best reported result in other papers. For the task of AHE prediction, since arterial pressure has a direct correlation with heart rate, we could simply find the periods in which HR drops blow a certain level without losing generality. The demonstrated AHE data for twenty patients are selected to validate the proposed algorithm. Results show that the proposed method could truly predict occurrence of the AHE in 9 out of the 10 cases analyzed. Results show reliable accuracy in predicting AHE in these patients.
UR - http://www.scopus.com/inward/record.url?scp=84869187922&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84869187922&partnerID=8YFLogxK
U2 - 10.1115/imece2011-64015
DO - 10.1115/imece2011-64015
M3 - Conference contribution
AN - SCOPUS:84869187922
SN - 9780791854884
T3 - ASME 2011 International Mechanical Engineering Congress and Exposition, IMECE 2011
SP - 525
EP - 529
BT - Biomedical and Biotechnology Engineering; Nanoengineering for Medicine and Biology
PB - American Society of Mechanical Engineers (ASME)
T2 - ASME 2011 International Mechanical Engineering Congress and Exposition, IMECE 2011
Y2 - 11 November 2011 through 17 November 2011
ER -