Tolvaptan is an effective therapy for heart failure patients with symptomatic congestion and hyponatremia. The efficacy of its use in patients with continuous-flow left ventricular assist devices (LVADs) is unknown. The aim of this study was to assess the clinical efficacy and safety of tolvaptan in LVAD patients. We retrospectively reviewed medical records of patients who underwent LVAD implantation between January 2014 and August 2018. Among 217 consecutive LVAD patients, tolvaptan was used in 20 patients. Mean age was 46 ± 14 years old and 14 patients were males. The duration of tolvaptan therapy was 4 (interquartile range 1–8) days. Urine volume significantly increased from 2,623 ± 1,109 ml/day before tolvaptan to 4,308 ± 1,432 ml/day during tolvaptan therapy (p < 0.001). Serum sodium increased from 127 ± 3 to 133 ± 3 mEq/L at the end of tolvaptan therapy (p < 0.001). No patients developed hypernatremia (serum sodium >150 mEq/L). The 90-day overall survival following tolvaptan therapy was 89% in both the tolvaptan group and a propensity score-matched non-tolvaptan group (p = 0.918). Survival free of heart failure readmissions was also comparable between the groups (p = 0.751). In conclusion, short-term use of tolvaptan following LVAD implantation is a safe and effective therapy to augment diuresis and improve hyponatremia.

Aortic insufficiency (AI) significantly affects morbidity and mortality in patients with left ventricular assist devices. Although AI may be commonly assessed by echocardiography, expert techniques are required for accurate quantification of AI severity. In this prospective blinded study, screenshots from the HVAD (Medtronic, Framingham, MA) display and simultaneous echocardiographic measurements were obtained. Each screenshot was digitized and the early diastolic phase slope was calculated, with blinding to the echocardiographic results. The regurgitant fraction of AI was quantified by Doppler echocardiography of the outflow graft. A total of 30 patients (median, 57 years old; 57% male) were enrolled. A cutoff of -17.6 L/min/s for the early diastolic phase slope had a sensitivity of 0.92 and a specificity of 0.53 to estimate significant AI with a regurgitant fraction of 30% or greater, and it significantly stratified patients into a low regurgitant faction group (0.3%) and a high regurgitant fraction group (33.0%) (P = .009). The early diastolic phase slope had a moderate correlation with the actually measured regurgitant fraction (r = .50). The early diastolic phase slope of the HVAD flow waveform may be a parameter that can estimate the presence of clinically significant AI.

Previous work used machine learning (ML) to estimate past and current alfalfa yields and showed that domain adaptation (DA) with data synthesis shows promise in classifying yields as high, medium, or low. The current work uses similar techniques to forecast future alfalfa yields. A novel technique is proposed for forecasting alfalfa time series data that exploits stationarity and predicts differences in yields rather than the yields themselves. This forecasting technique generally provides more accurate forecasts than the established ARIMA family of forecasters for both univariate and multivariate time series. Furthermore, this ML-based technique is potentially easier to use than the ARIMA family of models. Also, previous work is extended by showing that DA with data synthesis also works well for predicting continuous values, not just for classification. The novel scale-invariant tabular synthesizer (SITS) is proposed, and it is competitive with or superior to other established synthesizers in producing data that trains strong models. This synthesis algorithm leads to R scores over 100% higher than an established synthesizer in this domain, while ML-based forecasters beat the ARIMA family with symmetric mean absolute percent error (sMAPE) scores as low as 12.81%. Finally, ML-based forecasting is combined with DA (ForDA) to create a novel pipeline that improves forecast accuracy with sMAPE scores as low as 9.81%. As alfalfa is crucial to the global food supply, and as climate change creates challenges with managing alfalfa, this work hopes to help address those challenges and contribute to the field of ML.