Left Ventricular Pressure Estimation Using Machine Learning-Based Heart Sound Classification

Overview

Journal Front Cardiovasc Med

Specialty Cardiology & Vascular Diseases

Date 2022 Jun 13

PMID 35694657

Authors

Philip Westphal

Hongxing Luo

Mehrdad Shahmohammadi

Luuk I B Heckman

Marion Kuiper

Frits W Prinzen

Tammo Delhaas

Richard N Cornelussen

Affiliations

Soon will be listed here.

Abstract

Objective: A method to estimate absolute left ventricular (LV) pressure and its maximum rate of rise (LV dP/dtmax) from epicardial accelerometer data and machine learning is proposed.

Methods: Five acute experiments were performed on pigs. Custom-made accelerometers were sutured epicardially onto the right ventricle, LV, and right atrium. Different pacing configurations and contractility modulations, using isoflurane and dobutamine infusions, were performed to create a wide variety of hemodynamic conditions. Automated beat-by-beat analysis was performed on the acceleration signals to evaluate amplitude, time, and energy-based features. For each sensing location, bootstrap aggregated classification tree ensembles were trained to estimate absolute maximum LV pressure (LVPmax) and LV dP/dtmax using amplitude, time, and energy-based features. After extraction of acceleration and pressure-based features, location specific, bootstrap aggregated classification ensembles were trained to estimate absolute values of LVPmax and its maximum rate of rise (LV dP/dtmax) from acceleration data.

Results: With a dataset of over 6,000 beats, the algorithm narrowed the selection of 17 predefined features to the most suitable 3 for each sensor location. Validation tests showed the minimal estimation accuracies to be 93% and 86% for LVPmax at estimation intervals of 20 and 10 mmHg, respectively. Models estimating LV dP/dtmax achieved an accuracy of minimal 93 and 87% at estimation intervals of 100 and 200 mmHg/s, respectively. Accuracies were similar for all sensor locations used.

Conclusion: Under pre-clinical conditions, the developed estimation method, employing epicardial accelerometers in conjunction with machine learning, can reliably estimate absolute LV pressure and its first derivative.

Citing Articles

Machine learning: a new era for cardiovascular pregnancy physiology and cardio-obstetrics research.

Ricci C, Crysup B, Phillips N, Ray W, Santillan M, Trask A Am J Physiol Heart Circ Physiol. 2024; 327(2):H417-H432.

PMID: 38847756 PMC: 11442027. DOI: 10.1152/ajpheart.00149.2024.

References

Martirosyan M, Caliskan K, Theuns D, Szili-Torok T . Remote monitoring of heart failure: benefits for therapeutic decision making. Expert Rev Cardiovasc Ther. 2017; 15(7):503-515. DOI: 10.1080/14779072.2017.1348229. View

Bordachar P, Labrousse L, Ploux S, Thambo J, Lafitte S, Reant P . Validation of a new noninvasive device for the monitoring of peak endocardial acceleration in pigs: implications for optimization of pacing site and configuration. J Cardiovasc Electrophysiol. 2008; 19(7):725-9. DOI: 10.1111/j.1540-8167.2008.01105.x. View

Delnoy P, Marcelli E, Oudeluttikhuis H, Nicastia D, Renesto F, Cercenelli L . Validation of a peak endocardial acceleration-based algorithm to optimize cardiac resynchronization: early clinical results. Europace. 2008; 10(7):801-8. PMC: 2435018. DOI: 10.1093/europace/eun125. View

Vos T, Flaxman A, Naghavi M, Lozano R, Michaud C, Ezzati M . Years lived with disability (YLDs) for 1160 sequelae of 289 diseases and injuries 1990-2010: a systematic analysis for the Global Burden of Disease Study 2010. Lancet. 2012; 380(9859):2163-96. PMC: 6350784. DOI: 10.1016/S0140-6736(12)61729-2. View

Whinnett Z, Francis D, Denis A, Willson K, Pascale P, van Geldorp I . Comparison of different invasive hemodynamic methods for AV delay optimization in patients with cardiac resynchronization therapy: implications for clinical trial design and clinical practice. Int J Cardiol. 2013; 168(3):2228-37. PMC: 3819984. DOI: 10.1016/j.ijcard.2013.01.216. View

OConnell J, Brown J, Hildreth A, Gray C . Optimizing management of congestive heart failure in older people. Age Ageing. 2000; 29(4):371-2. DOI: 10.1093/ageing/29.4.371. View

Kypta A, Blessberger H, Lichtenauer M, Steinwender C . Complete encapsulation of a leadless cardiac pacemaker. Clin Res Cardiol. 2015; 105(1):94. DOI: 10.1007/s00392-015-0929-x. View

Donal E, Giorgis L, Cazeau S, Leclercq C, Senhadji L, Amblard A . Endocardial acceleration (sonR) vs. ultrasound-derived time intervals in recipients of cardiac resynchronization therapy systems. Europace. 2011; 13(3):402-8. DOI: 10.1093/europace/euq411. View

Davie A, Francis C, Caruana L, Sutherland G, McMurray J . Assessing diagnosis in heart failure: which features are any use?. QJM. 1997; 90(5):335-9. DOI: 10.1093/qjmed/90.5.335. View

10.

Breiman . Prediction games and arcing algorithms. Neural Comput. 1999; 11(7):1493-517. DOI: 10.1162/089976699300016106. View

11.

Brugada J, Delnoy P, Brachmann J, Reynolds D, Padeletti L, Noelker G . Contractility sensor-guided optimization of cardiac resynchronization therapy: results from the RESPOND-CRT trial. Eur Heart J. 2016; 38(10):730-738. PMC: 5353752. DOI: 10.1093/eurheartj/ehw526. View

12.

Siecinski S, Kostka P, Tkacz E . Gyrocardiography: A Review of the Definition, History, Waveform Description, and Applications. Sensors (Basel). 2020; 20(22). PMC: 7700364. DOI: 10.3390/s20226675. View

13.

Covino G, Volpicelli M, Ciardiello C, Capogrosso P . Usefulness of Hemodynamic Device-Based Optimization in Heterogeneous Patients Implanted with Cardiac Resynchronization Therapy Defibrillator. J Cardiovasc Transl Res. 2020; 13(6):938-943. DOI: 10.1007/s12265-020-10004-9. View

14.

Siejko K, Thakur P, Maile K, Patangay A, Olivari M . Feasibility of heart sounds measurements from an accelerometer within an ICD pulse generator. Pacing Clin Electrophysiol. 2012; 36(3):334-46. DOI: 10.1111/pace.12059. View

15.

Luciani M, Saccocci M, Kuwata S, Cesarovic N, Lipiski M, Arand P . Reintroducing Heart Sounds for Early Detection of Acute Myocardial Ischemia in a Porcine Model - Correlation of Acoustic Cardiography With Gold Standard of Pressure-Volume Analysis. Front Physiol. 2019; 10:1090. PMC: 6713932. DOI: 10.3389/fphys.2019.01090. View

16.

Teerlink J . Learning the points of COMPASS-HF: assessing implantable hemodynamic monitoring in heart failure patients. J Am Coll Cardiol. 2008; 51(11):1080-2. DOI: 10.1016/j.jacc.2007.12.009. View

17.

Klersy C, De Silvestri A, Gabutti G, Raisaro A, Curti M, Regoli F . Economic impact of remote patient monitoring: an integrated economic model derived from a meta-analysis of randomized controlled trials in heart failure. Eur J Heart Fail. 2011; 13(4):450-9. DOI: 10.1093/eurjhf/hfq232. View

18.

Ambrosy A, Fonarow G, Butler J, Chioncel O, Greene S, Vaduganathan M . The global health and economic burden of hospitalizations for heart failure: lessons learned from hospitalized heart failure registries. J Am Coll Cardiol. 2014; 63(12):1123-1133. DOI: 10.1016/j.jacc.2013.11.053. View

19.

Pekmezaris R, Mitzner I, Pecinka K, Nouryan C, Lesser M, Siegel M . The impact of remote patient monitoring (telehealth) upon Medicare beneficiaries with heart failure. Telemed J E Health. 2012; 18(2):101-8. DOI: 10.1089/tmj.2011.0095. View

20.

Duncker D, Delnoy P, Nagele H, Mansourati J, Mont L, Anselme F . First clinical evaluation of an atrial haemodynamic sensor lead for automatic optimization of cardiac resynchronization therapy. Europace. 2015; 18(5):755-61. PMC: 4880111. DOI: 10.1093/europace/euv114. View