Accelerometer Detects Pump Thrombosis and Thromboembolic Events in an In vitro HVAD Circuit

Schalit, Itai; Espinoza, Andreas; Pettersen, Fred-Johan; Thiara, Amrit P S; Karlsen, Hege; Sørensen, Gro; Fosse, Erik; Fiane, Arnt E.; Halvorsen, Per Steinar

doi:10.1097/mat.0000000000000699

Cited by 17 publications

(24 citation statements)

References 85 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Biosensors for other cardiovascular indications are in development. An external device has been described that can monitor impending thrombosis in intra-arterial mechanical pumps with the use of an accelerometer for real-time analysis of pump vibrations to detect thrombosis and possibly prevent thromboembolic events 54 . Ballistocardiography, a non-invasive measure of body motion generated by the ejection of blood in each cardiac cycle 10 , has been incorporated into devices such as weighing scales to measure heart rate 55 , whereas a digital artificial intelligence (AI)-powered stethoscope that integrates both ECG and phonocardiogram data was approved in 2020 by the FDA to assess patients for the presence of AF and heart murmurs 56 .…”

Section: Biosignal Acquisitionmentioning

confidence: 99%

Integration of novel monitoring devices with machine learning technology for scalable cardiovascular management

et al. 2020

View full text Add to dashboard Cite

Ambulatory monitoring is increasingly important for cardiovascular care but is often limited by the unpredictability of cardiovascular events, the intermittent nature of ambulatory monitors and the variable clinical significance of recorded data in patients. Technological advances in computing have led to the introduction of novel physiological biosignals that can increase the frequency at which abnormalities in cardiovascular parameters can be detected, making expert-level, automated diagnosis a reality. However, use of these biosignals for diagnosis also raises numerous concerns related to accuracy and actionability within clinical guidelines, in addition to medico-legal and ethical issues. Analytical methods such as machine learning can potentially increase the accuracy and improve the actionability of device-based diagnoses. Coupled with interoperability of data to widen access to all stakeholders, seamless connectivity (an internet of things) and maintenance of anonymity, this approach could ultimately facilitate near-real-time diagnosis and therapy. T he se tools are increasingly recognized by regulatory a g e n c ies a n d p r o f e s s ional m e d ic al s oc ie ti es, but several technical and ethical issues remain. In this Review, we describe the current state of cardiovascular monitoring along the continuum from biosignal acquisition to the identification of novel biosensors and the development of analytical techniques and ultimately to regulatory and ethical issues. Furthermore, we outline new paradigms for cardiovascular monitoring.

show abstract

Section: Biosignal Acquisitionmentioning

confidence: 99%

Integration of novel monitoring devices with machine learning technology for scalable cardiovascular management

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Sakota et al developed a sensor using near‐infrared light to detect pump thrombosis quantitatively. Schalit et al developed a method for detecting pump thrombosis in a HVAD using an accelerometer directly attached to the pump housing. Acoustic spectrum analysis to diagnose pump thrombosis has also been developed .…”

Section: Discussionmentioning

confidence: 99%

“…As with the recent advent of artificial intelligent technologies in industrial products, we believe VADs should have intelligent functions to overcome the issue of pump thrombosis. With regard to this, several methods for detecting pump thrombosis using additional equipment, such as an infrared light source, an accelerometer, or an acoustic microphone, have been studied . As for implantable VADs, however, it is desirable to avoid the use of additional equipment inside the body due to the increased cost and complexity of the system.…”

Section: Introductionmentioning

confidence: 99%

Detection of thrombosis in a magnetically levitated blood pump by vibrational excitation of the impeller

et al. 2020

View full text Add to dashboard Cite

The use of contactless support technology for the impeller has led to an increase in the durability of ventricular assist devices (VADs), and these have been in clinical use worldwide. However, pump thrombosis and stroke are still issues to be solved.We have developed a method for detecting the thrombosis in a magnetically levitated blood pump without the need for additional sensors or other equipment. In the proposed method, a sinusoidal current is applied to the electromagnets used for the magnetic bearing, resulting in vibration of the impeller. The phase difference between the current and displacement of the impeller increases with pump thrombosis. First, we describe the principle by which the pump thrombosis is detected.Pump thrombosis reduces the narrowest fluid gap in the pump and this gives rise to a change in the phase difference. Second, we report on experiments in which we changed the narrowest fluid gap using oriented polypropylene tape and showed that decreasing the narrowest fluid gap resulted in an increase in phase difference. For these experiments, the measurements were repeated three times for each condition.Third, we examine the relationship between the pump thrombosis and the phase difference evaluated by observations of the underside of the impeller when operating the pump with porcine blood. Since light was unable to penetrate the blood layer, the erythrocytes were removed for this observation. Only one observation was made.

show abstract

“…On the other hand, the LVAD sound is directly derived from the vibration of the device itself and can directly reflect a slight change in the functional status of the device. Attempts have been made to detect LVAD malfunctions by analyzing LVAD sounds, but their diagnostic accuracy has not been satisfactory [ 7 , 8 ]. This is because the information contained in the LVAD sound is complicated and vast, and it is difficult to analyze it using the commonly used linear statistical analysis methods.…”

Section: Introductionmentioning

confidence: 99%

Prediction of aortic valve regurgitation after continuous-flow left ventricular assist device implantation using artificial intelligence trained on acoustic spectra

et al. 2021

View full text Add to dashboard Cite

Significant aortic regurgitation (AR) is a common complication after continuous-flow left ventricular assist device (LVAD) implantation. Using machine-learning algorithms, this study was designed to examine valuable predictors obtained from LVAD sound and to provide models for identifying AR. During a 2-year follow-up period of 13 patients with Jarvik2000 LVAD, sound signals were serially obtained from the chest wall above the LVAD using an electronic stethoscope for 1 min at 40,000 Hz, and echocardiography was simultaneously performed to confirm the presence of AR. Among the 245 echocardiographic and acoustic data collected, we found 26 episodes of significant AR, which we categorized as “present”; the other 219 episodes were characterized as “none”. Wavelet (time–frequency) analysis was applied to the LVAD sound and 19 feature vectors of instantaneous spectral components were extracted. Important variables for predicting AR were searched using an iterative forward selection method. Seventy-five percent of 245 episodes were randomly assigned as training data and the remaining as test data. Supervised machine learning for predicting concomitant AR involved an ensemble classifier and tenfold stratified cross-validation. Of the 19 features, the most useful variables for predicting concomitant AR were the amplitude of the first harmonic, LVAD rotational speed during intermittent low speed (ILS), and the variation in the amplitude during normal rotation and ILS. The predictive accuracy and area under the curve were 91% and 0.73, respectively. Machine learning, trained on the time–frequency acoustic spectra, provides a novel modality for detecting concomitant AR during follow-up after LVAD.

show abstract

Accelerometer Detects Pump Thrombosis and Thromboembolic Events in an In vitro HVAD Circuit

Cited by 17 publications

References 85 publications

Integration of novel monitoring devices with machine learning technology for scalable cardiovascular management

Integration of novel monitoring devices with machine learning technology for scalable cardiovascular management

Detection of thrombosis in a magnetically levitated blood pump by vibrational excitation of the impeller

Prediction of aortic valve regurgitation after continuous-flow left ventricular assist device implantation using artificial intelligence trained on acoustic spectra

Contact Info

Product

Resources

About