Early detection of HVAD pump thrombosis based on technical analysis and power consumption measurements.

Abstract

Continuous-flow left ventricular assist devices (LVADs) have been extensively used in a strategy of bridge to orthotopic heart transplant and destination therapy. The usage of LVAD, however, is not free from limitations such as device-related adverse events, including pump thrombosis (PT). We aimed to develop an algorithm of early PT detection based on the maintenance parameters monitored by the implanted device. We analyzed log files of 101 patients implanted with HeartWare pump (HVAD) with 18 PT events among them. For signal processing, we used the open-high-low-close format transformation and typical price (TP) technical analysis indicator. Model parameters were tuned with 5-fold cross-validation, and the final performance was measured on a separate group of patients. Our algorithm achieved 100% sensitivity and 100% specificity of indications. In the final evaluation, alarms preceded the clinical acknowledgement of events by 2days and 20h on average. In the worst-case scenario, an alarm was raised 1day and 8h prior to the event. The proposed algorithm could be installed to work directly with the device controller and provide clinicians with automatic readings analysis, raising an alarm when there is a high probability of thromboembolism. Early event detection could enable better thrombosis management and improve prognosis in patients implanted with HVAD.