Development of suction detection algorithms for a left ventricular assist device from patient data

Gross, Christoph; Schlöglhofer, Thomas; Dimitrov, Kamen; Zimpfer, Daniel; Moscato, Francesco; Schima, Heinrich

doi:10.1016/j.bspc.2021.102910

Cited by 5 publications

(15 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A suction detection module can be developed either by accessing motor-information of the pumps or with additional sensors within the ventricle or in the pump. Even without the high temporal resolution of 50 Hz provided by the HVAD, many suction detection features rely only on averages and extrema ( 18 ). Similarly, the pulsatility module requires only the signal extrema readily available in the HeartMate 3™ (Abbott Laboratories, Chicago, IL, USA) for example, allowing rapid translation.…”

Section: Discussionmentioning

confidence: 99%

“…Pump power, current, speed and estimated flowrate were recorded at 50 Hz, which were then also used to calculate derived indices such as Aortic Valve opening ( 17 ), Suction Detection ( 18 ), and HR ( 19 ). For greater arrhythmia-detection accuracy, patients were additionally outfitted with a 5-lead Holter electrocardiographic (ECG) device (medilog® AR 12 plus, Schiller AG, Baar, Switzerland).…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A Sensorless Modular Multiobjective Control Algorithm for Left Ventricular Assist Devices: A Clinical Pilot Study

Schlöglhofer

Marko

Aigner

et al. 2022

Front. Cardiovasc. Med.

Self Cite

View full text Add to dashboard Cite

BackgroundContemporary Left Ventricular Assist Devices (LVADs) mainly operate at a constant speed, only insufficiently adapting to changes in patient demand. Automatic physiological speed control promises tighter integration of the LVAD into patient physiology, increasing the level of support during activity and decreasing support when it is excessive.MethodsA sensorless modular control algorithm was developed for a centrifugal LVAD (HVAD, Medtronic plc, MN, USA). It consists of a heart rate-, a pulsatility-, a suction reaction—and a supervisor module. These modules were embedded into a safe testing environment and investigated in a single-center, blinded, crossover, clinical pilot trial (clinicaltrials.gov, NCT04786236). Patients completed a protocol consisting of orthostatic changes, Valsalva maneuver and submaximal bicycle ergometry in constant speed and physiological control mode in randomized sequence. Endpoints for the study were reduction of suction burden, adequate pump speed and flowrate adaptations of the control algorithm for each protocol item and no necessity for intervention via the hardware safety systems.ResultsA total of six patients (median age 53.5, 100% male) completed 13 tests in the intermediate care unit or in an outpatient setting, without necessity for intervention during control mode operation. Physiological control reduced speed and flowrate during patient rest, in sitting by a median of −75 [Interquartile Range (IQR): −137, 65] rpm and in supine position by −130 [−150, 30] rpm, thereby reducing suction burden in scenarios prone to overpumping in most tests [0 [−10, 2] Suction events/minute] in orthostatic upwards transitions and by −2 [−6, 0] Suction events/min in Valsalva maneuver. During submaximal ergometry speed was increased by 86 [31, 193] rpm compared to constant speed for a median flow increase of 0.2 [0.1, 0.8] L/min. In 3 tests speed could not be increased above constant set speed due to recurring suction and in 3 tests speed could be increased by up to 500 rpm with a pump flowrate increase of up to 0.9 L/min.ConclusionIn this pilot study, safety, short-term efficacy, and physiological responsiveness of a sensorless automated speed control system for a centrifugal LVAD was established. Long term studies are needed to show improved clinical outcomes.Clinical Trial RegistrationClinicalTrials.gov, identifier: NCT04786236.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

A Sensorless Modular Multiobjective Control Algorithm for Left Ventricular Assist Devices: A Clinical Pilot Study

Schlöglhofer

Marko

Aigner

et al. 2022

Front. Cardiovasc. Med.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The process is repeated until the algorithm is tested on all folds, and the average performance across all test folds is reported (44). Three studies, in which sample size was less than 60, used leave-one-out crossvalidation in evaluating the model's performance; evaluating the model on one instance / case and training the model using the rest of the cases, iteratively (32,34,37). External validation was only used in…”

Section: Summary Of Model Evaluation Methodsmentioning

confidence: 99%

“…This can also be used to follow up response to therapy in the outpatient setting. The algorithm by Maw et al utilized LVAD log data to diagnose suction events with high success, despite the model overfitting (see below in AI methods) (37). Such physiologic control systems are likely to become more common in the LVAD world, akin to the case of pacemakers, as the large amount of data generated by these devices facilitate AI model training.…”

Section: Post Mechanical Support Management Guidancementioning

confidence: 99%

Artificial intelligence guidance of advanced heart failure therapies: A systematic scoping review

Al‐Ani

Chen

Hashky

et al. 2023

Front. Cardiovasc. Med.

View full text Add to dashboard Cite

IntroductionArtificial intelligence can recognize complex patterns in large datasets. It is a promising technology to advance heart failure practice, as many decisions rely on expert opinions in the absence of high-quality data-driven evidence.MethodsWe searched Embase, Web of Science, and PubMed databases for articles containing “artificial intelligence,” “machine learning,” or “deep learning” and any of the phrases “heart transplantation,” “ventricular assist device,” or “cardiogenic shock” from inception until August 2022. We only included original research addressing post heart transplantation (HTx) or mechanical circulatory support (MCS) clinical care. Review and data extraction were performed in accordance with PRISMA-Scr guidelines.ResultsOf 584 unique publications detected, 31 met the inclusion criteria. The majority focused on outcome prediction post HTx (n = 13) and post durable MCS (n = 7), as well as post HTx and MCS management (n = 7, n = 3, respectively). One study addressed temporary mechanical circulatory support. Most studies advocated for rapid integration of AI into clinical practice, acknowledging potential improvements in management guidance and reliability of outcomes prediction. There was a notable paucity of external data validation and integration of multiple data modalities.ConclusionOur review showed mounting innovation in AI application in management of MCS and HTx, with the largest evidence showing improved mortality outcome prediction.

show abstract

“…Several research groups and companies are studying physiological pump controllers to change the LVAD speed to avoid suction. ( Hatoh et al, 1999 ; Vollkron et al, 2004 ; Karantonis et al, 2006 ; Ferreira et al, 2007 ; Maw et al, 2021 ; Maw et al, 2022 ). Therefore, there is a need for an in vitro test bench with high fidelity and versatility to capture the wide range of suction characteristics observed in the clinics and capable of providing repeatable test scenarios for pump controllers.…”

Section: Introductionmentioning

confidence: 99%

An in vitro model to study suction events by a ventricular assist device: validation with clinical data

Rocchi¹,

Gross²,

Moscato³

et al. 2023

Front. Physiol.

Self Cite

View full text Add to dashboard Cite

Introduction: Ventricular assist devices (LVADs) are a valuable therapy for end-stage heart failure patients. However, some adverse events still persist, such as suction that can trigger thrombus formation and cardiac rhythm disorders. The aim of this study is to validate a suction module (SM) as a test bench for LVAD suction detection and speed control algorithms.Methods: The SM consists of a latex tube, mimicking the ventricular apex, connected to a LVAD. The SM was implemented into a hybrid in vitro-in silico cardiovascular simulator. Suction was induced simulating hypovolemia in a profile of a dilated cardiomyopathy and of a restrictive cardiomyopathy for pump speeds ranging between 2,500 and 3,200 rpm. Clinical data collected in 38 LVAD patients were used for the validation. Clinical and simulated LVAD flow waveforms were visually compared. For a more quantitative validation, a binary classifier was used to classify simulated suction and non-suction beats. The obtained classification was then compared to that generated by the simulator to evaluate the specificity and sensitivity of the simulator. Finally, a statistical analysis was run on specific suction features (e.g., minimum impeller speed pulsatility, minimum slope of the estimated flow, and timing of the maximum slope of the estimated flow).Results: The simulator could reproduce most of the pump waveforms observed in vivo. The simulator showed a sensitivity and specificity and of 90.0% and 97.5%, respectively. Simulated suction features were in the interquartile range of clinical ones.Conclusions: The SM can be used to investigate suction in different pathophysiological conditions and to support the development of LVAD physiological controllers.

show abstract

Development of suction detection algorithms for a left ventricular assist device from patient data

Cited by 5 publications

References 30 publications

A Sensorless Modular Multiobjective Control Algorithm for Left Ventricular Assist Devices: A Clinical Pilot Study

A Sensorless Modular Multiobjective Control Algorithm for Left Ventricular Assist Devices: A Clinical Pilot Study

Artificial intelligence guidance of advanced heart failure therapies: A systematic scoping review

An in vitro model to study suction events by a ventricular assist device: validation with clinical data

Contact Info

Product

Resources

About