Search

Key Points: Question: Does torsemide reduce all-cause mortality compared with furosemide in patients with heart failure following hospitalization? Findings: In this randomized clinical trial of 2859 patients, 26.1% of patients randomized to torsemide and 26.2% randomized to furosemide died over a median follow-up of 17.4 months without a significant difference between groups. Meaning: Among patients discharged after hospitalization for heart failure, torsemide compared with furosemide did not result in a significant difference in all-cause mortality over 12 months; however, interpretation of these findings is limited by loss to follow-up and participant crossover and nonadherence. Importance: Although furosemide is the most commonly used loop diuretic in patients with heart failure, some studies suggest a potential benefit for torsemide. Objective: To determine whether torsemide results in decreased mortality compared with furosemide among patients hospitalized for heart failure. Design, Setting, and Participants: TRANSFORM-HF was an open-label, pragmatic randomized trial that recruited 2859 participants hospitalized with heart failure (regardless of ejection fraction) at 60 hospitals in the United States. Recruitment occurred from June 2018 through March 2022, with follow-up through 30 months for death and 12 months for hospitalizations. The final date for follow-up data collection was July 2022. Interventions: Loop diuretic strategy of torsemide (n = 1431) or furosemide (n = 1428) with investigator-selected dosage. Main Outcomes and Measures: The primary outcome was all-cause mortality in a time-to-event analysis. There were 5 secondary outcomes with all-cause mortality or all-cause hospitalization and total hospitalizations assessed over 12 months being highest in the hierarchy. The prespecified primary hypothesis was that torsemide would reduce all-cause mortality by 20% compared with furosemide. Results: TRANSFORM-HF randomized 2859 participants with a median age of 65 years (IQR, 56-75), 36.9% were women, and 33.9% were Black. Over a median follow-up of 17.4 months, a total of 113 patients (53 [3.7%] in the torsemide group and 60 [4.2%] in the furosemide group) withdrew consent from the trial prior to completion. Death occurred in 373 of 1431 patients (26.1%) in the torsemide group and 374 of 1428 patients (26.2%) in the furosemide group (hazard ratio, 1.02 [95% CI, 0.89-1.18]). Over 12 months following randomization, all-cause mortality or all-cause hospitalization occurred in 677 patients (47.3%) in the torsemide group and 704 patients (49.3%) in the furosemide group (hazard ratio, 0.92 [95% CI, 0.83-1.02]). There were 940 total hospitalizations among 536 participants in the torsemide group and 987 total hospitalizations among 577 participants in the furosemide group (rate ratio, 0.94 [95% CI, 0.84-1.07]). Results were similar across prespecified subgroups, including among patients with reduced, mildly reduced, or preserved ejection fraction. Conclusions and Relevance: Among patients discharged after hospitalization for heart failure, torsemide compared with furosemide did not result in a significant difference in all-cause mortality over 12 months. However, interpretation of these findings is limited by loss to follow-up and participant crossover and nonadherence. Trial Registration: ClinicalTrials.gov Identifier: NCT03296813 This clinical trial compares the efficacy of torsemide vs furosemide in decreasing the risk of death from any cause among patients hospitalized for heart failure (regardless of ejection fraction). [ABSTRACT FROM AUTHOR]

Background The current acute kidney injury (AKI) risk prediction model for patients undergoing percutaneous coronary intervention (PCI) from the American College of Cardiology (ACC) National Cardiovascular Data Registry (NCDR) employed regression techniques. This study aimed to evaluate whether models using machine learning techniques could significantly improve AKI risk prediction after PCI. Methods and findings We used the same cohort and candidate variables used to develop the current NCDR CathPCI Registry AKI model, including 947,091 patients who underwent PCI procedures between June 1, 2009, and June 30, 2011. The mean age of these patients was 64.8 years, and 32.8% were women, with a total of 69,826 (7.4%) AKI events. We replicated the current AKI model as the baseline model and compared it with a series of new models. Temporal validation was performed using data from 970,869 patients undergoing PCIs between July 1, 2016, and March 31, 2017, with a mean age of 65.7 years; 31.9% were women, and 72,954 (7.5%) had AKI events. Each model was derived by implementing one of two strategies for preprocessing candidate variables (preselecting and transforming candidate variables or using all candidate variables in their original forms), one of three variable-selection methods (stepwise backward selection, lasso regularization, or permutation-based selection), and one of two methods to model the relationship between variables and outcome (logistic regression or gradient descent boosting). The cohort was divided into different training (70%) and test (30%) sets using 100 different random splits, and the performance of the models was evaluated internally in the test sets. The best model, according to the internal evaluation, was derived by using all available candidate variables in their original form, permutation-based variable selection, and gradient descent boosting. Compared with the baseline model that uses 11 variables, the best model used 13 variables and achieved a significantly better area under the receiver operating characteristic curve (AUC) of 0.752 (95% confidence interval [CI] 0.749-0.754) versus 0.711 (95% CI 0.708-0.714), a significantly better Brier score of 0.0617 (95% CI 0.0615-0.0618) versus 0.0636 (95% CI 0.0634-0.0638), and a better calibration slope of observed versus predicted rate of 1.008 (95% CI 0.988-1.028) versus 1.036 (95% CI 1.015-1.056). The best model also had a significantly wider predictive range (25.3% versus 21.6%, p < 0.001) and was more accurate in stratifying AKI risk for patients. Evaluated on a more contemporary CathPCI cohort (July 1, 2015-March 31, 2017), the best model consistently achieved significantly better performance than the baseline model in AUC (0.785 versus 0.753), Brier score (0.0610 versus 0.0627), calibration slope (1.003 versus 1.062), and predictive range (29.4% versus 26.2%). The current study does not address implementation for risk calculation at the point of care, and potential challenges include the availability and accessibility of the predictors. Conclusions Machine learning techniques and data-driven approaches resulted in improved prediction of AKI risk after PCI. The results support the potential of these techniques for improving risk prediction models and identification of patients who may benefit from risk-mitigation strategies., Author(s): Chenxi Huang 1, Karthik Murugiah 2, Shiwani Mahajan 1, Shu-Xia Li 1, Sanket S. Dhruva 3,4, Julian S. Haimovich 5, Yongfei Wang 1, Wade L. Schulz 1,6, Jeffrey M. [...]