Detection of ventricular suction in an implantable rotary blood pump using support vector machines

Wang, Yu; Faragallah, George; Divo, Eduardo; Simaan, Marwan A.

doi:10.1109/iembs.2011.6090900

Cited by 11 publications

(9 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In its use as bridge-to-transplantation for patients with severe heart failure the controller must increase the power to the device so that the pump (almost always by itself) can provide the necessary blood support to the circulation system because of the inability of the left ventricle to contribute any pumping through the aortic valve. However, as is pointed out in [23] and [24] the controller must also be aware that increased power which leads to increased rotational speed of the pump may lead to ventricular suction which is a dangerous phenomenon that may be a fatal. In the use of the LVAD as a bridge-to-recovery for patients with mild heart failure the controller must also increase the power to the device so that it can provide the necessary blood support to the circulation system; however, it must recognize that it cannot take over this function totally by itself by shutting the direct path of blood flow from the left ventricle to the aorta through the aortic valve.…”

Section: Challenges In the Development Of A Feedback Controller Bmentioning

confidence: 96%

“…The LSVM is a modified standard Support Vector Machine (SVM) [19], which is a reliable and powerful classification technology and has been successfully applied to various pattern recognition problems [20]- [22], especially to the problems in the LVAD field [23], [24]. Like SVM, the main idea of LSVM is to find the optimal separating hyperplane (with the maximum margin) between two different classes of the data points.…”

Section: The Lagrangian Support Vector Machine Approachmentioning

confidence: 99%

“…The classifier is trained on a randomly selected set of 50% of the data and then tested on the remaining 50% of the data. The training and testing procedures are similar to those described in [23], [24]. Due to the random selection of data samples, the classification is repeated 100 times.…”

Section: The Lagrangian Support Vector Machine Approachmentioning

confidence: 99%

See 2 more Smart Citations

Detection of aortic valve dynamics in bridge-to-recovery feedback control of the Left Ventricular Assist Device

Wang

Faragallah

Simaan

2014

2014 European Control Conference (ECC)

View full text Add to dashboard Cite

Aortic valve dynamics -which implies continuous opening and closing of the aortic valve in each cardiac cycle during the feedback control of the rotary Left Ventricular Assist Devices (LVAD) support -has important clinical implications for patients with mild congestive heart failure. When the LVAD is implanted in such patients as a bridge-torecovery device, permanent closure of the aortic valve must be avoided by maintaining proper control on the power delivered to the device. In this paper, a new aortic valve dynamics detection algorithm based on a Lagrangian Support Vector Machine (LSVM) model is presented. A detection indicator is derived from the systemic vascular flow signal in the circulatory system using a nonlinear mathematical model of the combined cardiovascular-LVAD system and forms the input to the LSVM classifier. The LSVM classifier is trained and tested to classify the aortic valve dynamics into two states: aortic valve opening and closing (i.e. operating normally) and aortic valve permanently closed. Our results show that the proposed algorithm can detect the aortic valve dynamics effectively in terms of classification accuracy and stability. This classifier will be an integral part in the development of a feedback controller for the LVAD when used on patients as a bridge-to-recovery device. The output of the classifier will be used to adjust the power delivered to the LVAD to ensure that the aortic valve opens and closes normally within each cardiac cycle while at the same time making sure that the physiological demands of the patient are met.

show abstract

Section: Challenges In the Development Of A Feedback Controller Bmentioning

confidence: 96%

Section: The Lagrangian Support Vector Machine Approachmentioning

confidence: 99%

See 1 more Smart Citation

Detection of aortic valve dynamics in bridge-to-recovery feedback control of the Left Ventricular Assist Device

Wang

Faragallah

Simaan

2014

2014 European Control Conference (ECC)

View full text Add to dashboard Cite

show abstract

“…The ability of the proposed algorithm to detect and classify suction will provide an alternative approach for treating the problem of suction detection and more importantly will facilitate an important step in the development of a feedback 1 shows a flowchart of the proposed LSVM suction detection algorithm. The algorithm is composed of four modules [10]: 1) a pre-processing module whose purpose is to filter the pump flow signal, eliminating high-frequency noise components using a low-pass filter, 2) a feature extraction module that calculates six suction indices from the filtered pump signal. Three of the six indices are based on time domain, two on frequency domain, and one on time-frequency domain.…”

Section: Introductionmentioning

confidence: 99%

A Suction Detection System for Rotary Blood Pumps Based on the Lagrangian Support Vector Machine Algorithm

Wang

Simaan

2013

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

The Left Ventricular Assist Device (LVAD) is a rotary mechanical pump that is implanted in patients with congestive heart failure to help the left ventricle in pumping blood in the circulatory system. However, using such a device may result in a very dangerous event, called ventricular suction that can cause ventricular collapse due to overpumping of blood from the left ventricle when the rotational speed of the pump is high. Therefore, a reliable technique for detecting ventricular suction is crucial. This paper presents a new suction detection system that can precisely classify pump flow patterns, based on a Lagrangian Support Vector Machine (LSVM) model that combines six suction indices extracted from the pump flow signal to make a decision about whether the pump is in suction, approaching suction, or not in suction. The proposed method has been tested using in vivo experimental data based on two different pumps. The simulation results show that the system can produce superior performance in terms of classification accuracy, stability, learning speed, and good robustness compared to three other existing suction detection methods and the original SVM-based algorithm. The ability of the proposed algorithm to detect suction provides a reliable platform for the development of a feedback control system to control the speed of the pump while at the same time ensuring that suction is avoided.

show abstract

“…Thus, some suction indices are based on time-domain features [54 -57], frequency-domain features [55 -57], and time-frequency-domain features [55 -57]. Among them, there exist methods which extract features from the pump flow signal being one of very few signals that can be easily measured and use powerful pattern recognition algorithms to classify the signal into different pump states [57][58][59][60][61]. However, in the majority of the above described approaches, a large number of features are employed.…”

Section: Related Workmentioning

confidence: 99%

A Decision Support System for the Treatment of Patients with Ventricular Assist Device Support

Karvounis¹,

Tsipouras²,

Tzallas³

et al. 2014

Methods Inf Med

View full text Add to dashboard Cite

SummaryBackground: Heart failure (HF) is affecting millions of people every year and it is characterized by impaired ventricular performance, exercise intolerance and shortened life expectancy. Despite significant advancements in drug therapy, mortality of the disease remains excessively high, as heart transplant remains the gold standard treatment for end-stage HF when no contraindications subsist. Traditionally, implanted Ventricular Assist Devices (VADs) have been employed in order to provide circulatory support to patients who cannot survive the waiting time to transplantation, reducing the workload imposed on the heart. In many cases that process could recover its contractility performance.Objectives: The SensorART platform focuses on the management and remote treatment of patients suffering from HF. It provides an inter-operable, extendable and VAD-independent solution, which incorporates various hardware and software components in a holistic approach, in order to improve the quality of the patients’ treatment and the workflow of the specialists. This paper focuses on the description and analysis of Specialist’s Decision Support System (SDSS), an innovative component of the SensorART platform.Methods: The SDSS is a Web-based tool that assists specialists on designing the therapy plan for their patients before and after VAD implantation, analyzing patients’ data, extracting new knowledge, and making informative decisions.Results: SDSS offers support to medical and VAD experts through the different phases of VAD therapy, incorporating several tools covering all related fields; Statistics, Association Rules, Monitoring, Treatment, Weaning, Speed and Suction Detection.Conclusions: SDSS and its modules have been tested in a number of patients and the results are encouraging.

show abstract

Detection of ventricular suction in an implantable rotary blood pump using support vector machines

Cited by 11 publications

References 11 publications

Detection of aortic valve dynamics in bridge-to-recovery feedback control of the Left Ventricular Assist Device

Detection of aortic valve dynamics in bridge-to-recovery feedback control of the Left Ventricular Assist Device

A Suction Detection System for Rotary Blood Pumps Based on the Lagrangian Support Vector Machine Algorithm

A Decision Support System for the Treatment of Patients with Ventricular Assist Device Support

Contact Info

Product

Resources

About