Renoprotective Benefit of Tolvaptan in Acute Decompensated Heart Failure Patients With Loop Diuretic-Resistant Status

Machine Learning for Predicting Risk and Prognosis of Acute Kidney Disease in Critically Ill Elderly Patients During Hospitalization: Internet-Based and Interpretable Model Study

BACKGROUND

Acute kidney disease (AKD) affects more than half of critically ill elderly patients with acute kidney injury (AKI), which leads to worse short-term outcomes.

OBJECTIVE

We aimed to establish 2 machine learning models to predict the risk and prognosis of AKD in the elderly and to deploy the models as online apps.

METHODS

Data on elderly patients with AKI (n=3542) and AKD (n=2661) from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database were used to develop 2 models for predicting the AKD risk and in-hospital mortality, respectively. Data collected from Xiangya Hospital of Central South University were for external validation. A bootstrap method was used for internal validation to obtain relatively stable results. We extracted the indicators within 24 hours of the first diagnosis of AKI and the fluctuation range of some indicators, namely delta (day 3 after AKI minus day 1), as features. Six machine learning algorithms were used for modeling; the area under the receiver operating characteristic curve (AUROC), decision curve analysis, and calibration curve for evaluating; Shapley additive explanation (SHAP) analysis for visually interpreting; and the Heroku platform for deploying the best-performing models as web-based apps.

RESULTS

For the model of predicting the risk of AKD in elderly patients with AKI during hospitalization, the Light Gradient Boosting Machine (LightGBM) showed the best overall performance in the training (AUROC=0.844, 95% CI 0.831-0.857), internal validation (AUROC=0.853, 95% CI 0.841-0.865), and external (AUROC=0.755, 95% CI 0.699-0.811) cohorts. In addition, LightGBM performed well for the AKD prognostic prediction in the training (AUROC=0.861, 95% CI 0.843-0.878), internal validation (AUROC=0.868, 95% CI 0.851-0.885), and external (AUROC=0.746, 95% CI 0.673-0.820) cohorts. The models deployed as online prediction apps allowed users to predict and provide feedback to submit new data for model iteration. In the importance ranking and correlation visualization of the model's top 10 influencing factors conducted based on the SHAP value, partial dependence plots revealed the optimal cutoff of some interventionable indicators. The top 5 factors predicting the risk of AKD were creatinine on day 3, sepsis, delta blood urea nitrogen (BUN), diastolic blood pressure (DBP), and heart rate, while the top 5 factors determining in-hospital mortality were age, BUN on day 1, vasopressor use, BUN on day 3, and partial pressure of carbon dioxide (PaCO2).

CONCLUSIONS

We developed and validated 2 online apps for predicting the risk of AKD and its prognostic mortality in elderly patients, respectively. The top 10 factors that influenced the AKD risk and mortality during hospitalization were identified and explained visually, which might provide useful applications for intelligent management and suggestions for future prospective research.

Efficacy of tolvaptan on the short and mid-term prognosis in elderly patients with acute heart failure coexisting with oliguria: A retrospective cohort study

Background

In patients with acute heart failure (AHF) coexisting with oliguria, high doses of loop diuretics are often ineffective in increasing urine output and may adversely affect the patient's prognosis, especially in elderly patients. We investigated the efficacy of adding tolvaptan (TLV) on improving the prognosis in elderly patients with AHF coexisting with oliguria.

Methods

All data for this retrospective cohort study were extracted from the electronic medical record system of the Second Medical Center of Chinese PLA General Hospital from January 2018 to December 2020. Patients diagnosed with AHF coexisting with oliguria were enrolled in this study and were divided into TLV and non-TLV groups based on the use of TLV. The primary outcome was all-cause mortality at 7 and 90-day. The secondary outcomes were the remission of AHF within 7 and 30 days or continued progression of AHF, and new-onset chronic kidney disease (CKD) after 90 days. Cox proportional hazards regression was used to assess the relationships between all-cause mortality and diuretic regimens, demographics, laboratory parameters, comorbidities, and medications.

Results

A total of 308 patients met the study criteria for the final statistical analysis, and they had a median age of 91 years (88, 95). The results showed that the addition of TLV was associated with a decreased risk of the 7 and 90-day all-cause mortality in patients with AHF with oliguria [adjusted HR, 95% CI: 0.60 (0.37, 0.98), p = 0.042; 0.56 (0.41, 0.75), p < 0.001, respectively]. Adding TLV significantly increased urine output and decreased N-terminal pro-B-type natriuretic peptide (NT-proBNP) levels in 7 days, and alleviated the progression of AHF within 30 days. There were no statistically significant differences between the patients with or without TLV in terms of the occurrence of hypernatremia, the development of hepatic impairment within 30 days, and new-onset CKD after 90 days.

Conclusions

This study demonstrated that the addition of TLV was clinically effective in increasing urine output, and had favorable effects on alleviating AHF progression and may reduce the risk of all-cause mortality at 7 and 90-day in elderly patients with AHF with oliguria, and TLV had a good safety profile.

Trial registration

http://www.chictr.org.cn/showprojen.aspx?proj=148046, identifier: ChiCTR2200055518.

Tolvaptan Add-on Therapy to Overcome Loop Diuretic Resistance in Acute Heart Failure With Renal Dysfunction (DR-AHF): Design and Rationale

Background

Diuretic Resistance in Acute Heart Failure (DR-AHF) was designed to demonstrate the effectiveness of the early tolvaptan (a vasopressin-2 receptor antagonist) add-on therapy in patients with AHF with renal dysfunction and to provide clinical evidence of loop diuretic resistance.

Methods and Results

This single-centered, open-labeled, randomized, and controlled trial enrolled 128 patients hospitalized with AHF, as participants. These patients with a wet-warm phenotype, whose estimated glomerular filtration rates are of ≥15 ml/min/1.73 m² and ≤ 60 ml/min/1.73 m², with a cumulative urine output of <300 ml 2 h after the first dose of intravenous furosemide, will be randomly assigned 1:1 to receive standard care with an uptitrating intravenous furosemide alone, or a combination therapy with 15 mg of tolvaptan administered once daily for 2 days. The standard furosemide treatment will follow the latest position statements of the Heart Failure Association. The primary endpoint is the cumulative urine output at 48 h. The key secondary endpoints include the improvement of fractional excretion of sodium at 6 h, the total dose of furosemide, and the incidence of worsening renal function (WRF) at 48 h.

Conclusions

Although the combination of diuretic treatment has recently gained more attention due to its physiologically synergistic action, its advantages may be outweighed by the substantial risk of electrolyte disturbances and severe WRF. Further, there is no consensus on the time point for early starting of add-on therapy and for the preferred diuretic combination.

Trial registration

NCT04331132.

Effectiveness and Safety of Tolvaptan in Patients with Aortic Stenosis

BACKGROUND

Heart failure in severe aortic stenosis (AS) before aortic valve has a poor prognosis with high risk. Although the overuse of loop diuretics may induce hypovolemia, cardiac output reduction, and critical hypotension in severe AS, tolvaptan is characterized by its ability to help maintain hemodynamics and seems to be appropriate for use in heart failure caused by AS. Therefore, we retrospectively examined the effects and safety of tolvaptan use in patients with heart failure caused by severe AS.

METHODS AND RESULTS

Ten patients with heart failure caused by severe AS were enrolled. Tolvaptan administration did not cause blood pressure decrease significantly, whereas urine volume increased significantly from 896±318 to 1322±502 mL/day (P<0.05). Although there was no statistical significance, functional classes tended to be improved. Blood tests indicated no worsening of kidney function and N-terminal pro-brain natriuretic peptide levels after the use of tolvaptan. Echocardiography also showed no hypovolemia and no worsening of aortic valve flow (18.3±3.8 to 15.5±5.5 cm/s, n.s).

CONCLUSIONS

Tolvaptan use in AS patients with heart failure is effective and safe before aortic valve intervention.

Characterization of tolvaptan response and its impact on the outcome for patients with heart failure

BACKGROUND

Conventional diuretic therapy such as loop diuretics is a cornerstone of the treatment for heart failure (HF). Diuretic response is an important factor in determining resistance to HF therapy and has been shown to be associated with subsequent clinical outcome. Tolvaptan (TVP), a vasopressin V2 receptor antagonist, has a favorable profile in terms of rapid fluid removal and less aggravation of renal function. We hypothesized that the response to TVP might be associated with the subsequent clinical outcome.

METHOD

In this single-center retrospective study, 148 consecutive HF patients who were administered TVP from 2014 through 2018 [age 79 (69-86) years, male 89 (60%)] were included. Ninety-six patients were divided into TVP responder [N = 39 (41%)] and non-responder groups based on the cut-off value of gained urine output (+ 93 ml/mg TVP /day) on the day after TVP was introduced.

RESULTS

Early TVP introduction (p = 0.012) and lower dose of loop diuretics (p = 0.043) were predictors of TVP responder. For 2 years after discharge, TVP responders showed more favorable outcomes regarding the primary endpoint defined as the composite of all-cause death and HF readmission (p = 0.034, log-rank test) and HF readmission (p = 0.005). A multivariable Cox model analysis revealed that TVP responder was an independent predictor of the primary endpoint (hazard ratio 0.48, p = 0.041). TVP responders had a lower number of HF readmissions over a 1-year period (p = 0.002). TVP response was independently associated with the number of HF readmissions (p = 0.015). The proportion of patients with an extended period between discharge and HF readmission after TVP administration was higher in responders than non-responders (67% vs. 23%, p = 0.006). These associations of TVP response and post-discharge outcomes were more evident in patients who continued TVP after discharge.

CONCLUSION

TVP response can be indicative of subsequent clinical outcomes and may be informative when considering advanced care planning.

Long-term administration of tolvaptan ameliorates annual decline in estimated glomerular filtration rate in outpatients with chronic heart failure

Protective effects of tolvaptan against worsening renal function in acute heart failure have been shown. However, long-term effects of its agent on renal function remain to be elucidated. The present study investigated retrospectively whether long-term treatment with tolvaptan exerts renoprotective effects in patients with chronic heart failure, by comparing serial changes in estimated glomerular filtration rate (eGFR) for years before and after tolvaptan administration. From 63 outpatients with chronic heart failure taking diuretics including tolvaptan, 34 patients whose eGFR levels were continuously measured for more than 6 months both before and after administration of tolvaptan (average dose, 7.8 mg/day at the end of the follow-up period) were selected as eligible for the present analyses. All eGFR values were separately plotted before and after the initiation of treatment with tolvaptan (except hospitalization periods) along the time course axis and the slope of the linear regression curve was calculated as an annual change in eGFR. The mean follow-up periods before and after tolvaptan administration were 1197 and 784 days (3.3 and 2.1 years), respectively. Changing rates of eGFR per year were significantly ameliorated after treatment with tolvaptan (mean ± SD, - 8.02 ± 9.35 to - 1.62 ± 5.09 mL/min/1.73m² /year, P = 0.001). In echocardiographic parameters, inferior vena cava (IVC) diameter significantly decreased after tolvaptan administration, and the decrease in IVC diameter was correlated with the improvement of eGFR decline slope after administration of tolvaptan (P = 0.0075). This longitudinal observational study indicated that long-term treatment with tolvaptan ameliorated annual decline in eGFR in outpatients with chronic heart failure. Our findings suggest that tolvaptan has a protective effect against chronically worsening renal function in heart failure patients.