Search

Abstract Aims Artificial intelligence (AI) has emerged as a potential useful tool to support clinical treatment of heart failure, including the setting of mechanical circulatory support (MCS). Modern Impella pumps are equipped with advanced technology (SmartAssist), enabling real‐time acquisition and display of data related to both pump performance and the patient's haemodynamic status. These data emerge as an ‘ideal’ source for data‐driven AI applications to predict the clinical course of an ongoing therapeutic protocol. Yet, no evidence of effective application of AI tools in the setting of Impella support is available. On this background, we aimed at identifying possible future applications of AI‐based tools in the setting of temporary MCS with an Impella device. Methods We explored the state of research and development at the intersection of AI and Impella support and derived future potential applications of AI in routine Impella clinical management. Results We identified different areas where the future implementation of AI tools may contribute to addressing important clinical challenges in the setting of Impella support, including (i) early identification of the best suited pathway of care according to patients' conditions at presentation and intention to treat, (ii) prediction of therapy outcomes according to different possible therapeutic actions, (iii) optimization of device implantation procedures and evaluation of proper pump position over the whole course of support and (iv) prevention and/or rationale management of haemocompatibility‐related adverse events. For each of those areas, we discuss the potential advantages, challenges and implications of harnessing AI‐driven insights in the setting of MCS with an Impella device. Conclusions Temporary MCS with an Impella device has great potential to benefit from the integration of AI‐based tools. Such tools may indeed translate into groundbreaking innovation supporting clinical decision‐making and therapy regulation, in particular in complex scenarios such as the multidevice MCS strategy.

IntroductionMicroRNAs (miRs) emerged as promising diagnostic and therapeutic biomarkers in cardiovascular diseases. The potential clinical utility of platelet miRs in the setting of left ventricular assist device (LVAD) support is unexplored.MethodsWe prospectively measured the expression levels of 12 platelet miRs involved in platelet activation, coagulation, and cardiovascular diseases in LVAD patients by quantitative real-time polymerase chain reaction. Data were longitudinally measured before LVAD implant and after 1, 6, and 12 months of LVAD support, and compared with those measured in healthy volunteers (controls). In silico analysis was also performed to identify pathways targeted by differentially expressed miRs.ResultsData from 15 consecutive patients and 5 controls were analyzed. Pre-implant expression levels of platelet miR-126, miR-374b, miR-223, and miR-320a were significantly different in patients vs. controls. The expression levels of platelet miR-25, miR-144, miR-320, and miR-451a changed significantly over the course of LVAD support; in silico analysis revealed that these miRs are implicated in both cardiac- and coagulation-associated pathways. Furthermore, the patients who suffered from bleeding (n = 5, 33%) had significantly higher pre-implant expression levels of platelet miR-151a and miR-454 with respect to the patients who did not. The same miRs were also differentially expressed in bleeders following LVAD implantation early before the clinical manifestation of the events.DiscussionThis study provides a proof-of-concept evidence of significant modulation of platelet miRs expression driven by LVADs. The possible existence of a platelet miRs signature predictive of the development of bleeding events warrants further validation studies.

While earlier studies reported no relevant effect of the HeartMate 3 (HM3) artificial pulse (AP) on bulk pump washout, its effect on regions with prolonged residence times remains unexplored. Using numerical simulations, we compared pump washout in the HM3 with and without AP with a focus on the clearance of the last 5% of the pump volume. Results were examined in terms of flush-volume (Vf, number of times the pump was flushed with new blood) to probe the effect of the AP independent of changing flow rate. Irrespective of the flow condition, the HM3 washout scaled linearly with flush volume up to 70% washout and slowed down for the last 30%. Flush volumes needed to washout 95% of the pump were comparable with and without the AP (1.3–1.4 Vf), while 99% washout required 2.1–2.2 Vf with the AP vs. 2.5 Vf without the AP. The AP enhanced washout of the bend relief and near-wall regions. It also transiently shifted or eliminated stagnation regions and led to rapid wall shear stress fluctuations below the rotor and in the secondary flow path. Our results suggest potential benefits of the AP for clearance of fluid regions that might elicit in-pump thrombosis and provide possible mechanistic rationale behind clinical data showing very low rate of in-pump thrombosis with the HM3. Further optimization of the AP sequence is warranted to balance washout efficacy while limiting blood damage.