Development and Validation of a Risk Score for Prediction of Acute Kidney Injury in Patients With Acute Decompensated Heart Failure: A Prospective Cohort Study in China

Development and validation of a dynamic nomogram for acute kidney injury prediction in ICU patients with acute heart failure

Objective

Developing and validating a simple and clinically useful dynamic nomogram for predicting early acute kidney injury (AKI) in patients with acute heart failure (AHF) admitted to the intensive care unit (ICU).

Methods

Clinical data from patients with AHF were obtained from the Medical Information Mart for Intensive Care IV database. The patients with AHF were randomly allocated into derivation and validation sets. The independent predictors for AKI development in AHF patients were identified through least absolute shrinkage and selection operator and multivariate logistic regression analyses. A nomogram was developed based on the results of the multivariable logistic regression to predict early AKI onset in AHF patients, which was subsequently implemented as a web-based calculator for clinical application. An evaluation of the nomogram was conducted using discrimination, calibration curves, and decision curve analyses (DCA).

Results

After strict screening, 1,338 patients with AHF were included in the derivation set, and 3,129 in the validation set. Sepsis, use of human albumin, age, mechanical ventilation, aminoglycoside administration, and serum creatinine levels were identified as predictive factors for AKI in patients with AHF. The discrimination of the nomogram in both the derivation and validation sets was 0.81 (95% confidence interval: 0.78-0.83) and 0.79 (95% confidence interval: 0.76-0.83). Additionally, the calibration curve demonstrated that the predicted outcomes aligned well with the actual observations. Ultimately, the DCA curves indicated that the nomogram exhibited favorable clinical applicability.

Conclusion

The nomogram that integrates clinical risk factors and enables the personalized prediction of AKI in patients with AHF upon admission to the ICU, which has the potential to assist in identifying AHF patients who would derive the greatest benefit from interventions aimed at preventing and treating AKI.

Nomogram Model to Predict Acute Kidney Injury in Hospitalized Patients with Heart Failure

Background

Acute kidney injury (AKI) is a common complication of acute heart failure (HF) that can prolong hospitalization time and worsen the prognosis. The objectives of this research were to ascertain independent risk factors of AKI in hospitalized HF patients and validate a nomogram risk prediction model established using those factors.

Methods

Finally, 967 patients hospitalized for HF were included. Patients were randomly assigned to the training set (n = 677) or test set (n = 290). Least absolute shrinkage and selection operator (LASSO) regression was performed for variable selection, and multivariate logistic regression analysis was used to search for independent predictors of AKI in hospitalized HF patients. A nomogram prediction model was then developed based on the final identified predictors. The performance of the nomogram was assessed in terms of discriminability, as determined by the area under the receiver operating characteristic (ROC) curve (AUC), and predictive accuracy, as determined by calibration plots.

Results

The incidence of AKI in our cohort was 19%. After initial LASSO variable selection, multivariate logistic regression revealed that age, pneumonia, D-dimer, and albumin were independently associated with AKI in hospitalized HF patients. The nomogram prediction model based on these independent predictors had AUCs of 0.760 and 0.744 in the training and test sets, respectively. The calibration plots indicate a strong concordance between the estimated AKI probabilities and the observed probabilities.

Conclusions

A nomogram prediction model based on pneumonia, age, D-dimer, and albumin can help clinicians predict the risk of AKI in HF patients with moderate discriminability.

Time Series AI Model for Acute Kidney Injury Detection Based on a Multicenter Distributed Research Network: Development and Verification Study

Background

Acute kidney injury (AKI) is a marker of clinical deterioration and renal toxicity. While there are many studies offering prediction models for the early detection of AKI, those predicting AKI occurrence using distributed research network (DRN)-based time series data are rare.

Objective

In this study, we aimed to detect the early occurrence of AKI by applying an interpretable long short-term memory (LSTM)-based model to hospital electronic health record (EHR)-based time series data in patients who took nephrotoxic drugs using a DRN.

Methods

We conducted a multi-institutional retrospective cohort study of data from 6 hospitals using a DRN. For each institution, a patient-based data set was constructed using 5 drugs for AKI, and an interpretable multivariable LSTM (IMV-LSTM) model was used for training. This study used propensity score matching to mitigate differences in demographics and clinical characteristics. Additionally, the temporal attention values of the AKI prediction model's contribution variables were demonstrated for each institution and drug, with differences in highly important feature distributions between the case and control data confirmed using 1-way ANOVA.

Results

This study analyzed 8643 and 31,012 patients with and without AKI, respectively, across 6 hospitals. When analyzing the distribution of AKI onset, vancomycin showed an earlier onset (median 12, IQR 5-25 days), and acyclovir was the slowest compared to the other drugs (median 23, IQR 10-41 days). Our temporal deep learning model for AKI prediction performed well for most drugs. Acyclovir had the highest average area under the receiver operating characteristic curve score per drug (0.94), followed by acetaminophen (0.93), vancomycin (0.92), naproxen (0.90), and celecoxib (0.89). Based on the temporal attention values of the variables in the AKI prediction model, verified lymphocytes and calcvancomycin ium had the highest attention, whereas lymphocytes, albumin, and hemoglobin tended to decrease over time, and urine pH and prothrombin time tended to increase.

Conclusions

Early surveillance of AKI outbreaks can be achieved by applying an IMV-LSTM based on time series data through an EHR-based DRN. This approach can help identify risk factors and enable early detection of adverse drug reactions when prescribing drugs that cause renal toxicity before AKI occurs.

Artificial intelligence: a new field of knowledge for nephrologists?

Artificial intelligence (AI) is a science that involves creating machines that can imitate human intelligence and learn. AI is ubiquitous in our daily lives, from search engines like Google to home assistants like Alexa and, more recently, OpenAI with its chatbot. AI can improve clinical care and research, but its use requires a solid understanding of its fundamentals, the promises and perils of algorithmic fairness, the barriers and solutions to its clinical implementation, and the pathways to developing an AI-competent workforce. The potential of AI in the field of nephrology is vast, particularly in the areas of diagnosis, treatment and prediction. One of the most significant advantages of AI is the ability to improve diagnostic accuracy. Machine learning algorithms can be trained to recognize patterns in patient data, including lab results, imaging and medical history, in order to identify early signs of kidney disease and thereby allow timely diagnoses and prompt initiation of treatment plans that can improve outcomes for patients. In short, AI holds the promise of advancing personalized medicine to new levels. While AI has tremendous potential, there are also significant challenges to its implementation, including data access and quality, data privacy and security, bias, trustworthiness, computing power, AI integration and legal issues. The European Commission's proposed regulatory framework for AI technology will play a significant role in ensuring the safe and ethical implementation of these technologies in the healthcare industry. Training nephrologists in the fundamentals of AI is imperative because traditionally, decision-making pertaining to the diagnosis, prognosis and treatment of renal patients has relied on ingrained practices, whereas AI serves as a powerful tool for swiftly and confidently synthesizing this information.

Incidence, mortality, and predictors of acute kidney injury in patients with heart failure: a systematic review

Acute kidney injury (AKI) is common in patients with heart failure (HF), but studies have been inconsistent about the incidence of AKI in patients with HF. We conducted a meta-analysis to examine the incidence of AKI and its impact on mortality in patients with HF. We also looked at inpatient variables that could predict the development of AKI to identify potential risk factors, so that these can be used as a starting point for intervention and prevention in this group. The Embase, Medline, PubMed, Cochrane libraries, and Web of Science databases were used for searching articles from the inception of the database to October 2022. The EndNote software was used for screening. Meta-analysis was performed using Stata 16.0 software to combine effect sizes. A total of 37 studies were included. Of all the 3 533 583 patients with HF, 774 887 had AKI, with a pooled incidence of 33% [95% confidence interval (CI): 32-35%]. The incidence rate of AKI in acute HF and chronic HF was 36% (95% CI: 31-40%) and 30% (95% CI: 24-35%), respectively. Eleven studies found that AKI patients had higher in-hospital mortality than non-AKI patients [risk ratio (RR): 3.65; 95% CI: 3.04-4.39, P < 0.001]. Mortality was assessed in five studies, and it was found that mortality remained high at 1-year follow-up after onset of AKI (RR: 1.85, 95% CI: 1.54-2.22, P < 0.001). Fifteen admission variables were included and analysed in 13 studies. The combined results showed that diabetes, hypertension, history of chronic kidney disease, chronic HF systolic, age, N-terminal pro-B-type natriuretic peptide, creatinine > 1.0 mg/dL, index estimated glomerular filtration rate < 60 mL/min/1.73 m2 , blood urea nitrogen > 24 mg/dL, intravenous dobutamine, and serum albumin were predictor factors for HF patients with AKI (P < 0.05). In this meta-analysis, AKI occurred in approximately 33% of HF patients during hospitalization and the risk of dying in the hospital was tripled. Even during 1-year long-term follow-up, the risk of death remained high, and multiple inpatient variables showed that HF patients tended to have AKI. Early intervention and treatment are important to reduce the incidence of AKI and improve the prognosis.

Association of Hypoalbuminemia With Clinical Outcomes in Patients Admitted With Acute Heart Failure

Albumin is a protein produced by the liver essential for maintaining blood volume and regulating fluid balance. Hypoalbuminemia is characterized by low levels of albumin in the blood. It is also a marker of malnutrition-inflammatory syndrome. Several studies have demonstrated its prognostic role in patients with chronic heart failure; however, data regarding hypoalbuminemia in acute heart failure admissions are scarce. This study aims to analyze the relationship between hypoalbuminemia and heart failure. We used a retrospective cohort study surveying data from the 2016-2018 combined National Inpatient Sample (NIS) database. Adult hospitalizations for heart failure patients were identified using the ICD-10 codes, stratified into cohorts with and without hypoalbuminemia. Primary outcomes were (1) in-patient mortality, (2) length of stay, and total hospital charge. We also reclassified the HF admissions with hypoalbuminemia to those with systolic or diastolic heart failure to compare any differences in mortality and other in-patient complications. Multivariate linear and logistic regression were used to adjust for confounders and to analyze the outcomes. There were 1,365,529 adult hospitalizations for Congestive Heart Failure (CHF), and among them 1,205,990 (88 %) had secondary diagnoses of hypoalbuminemia. Patients with comorbid hypoalbuminemia were, on average, 8 years older (P < 0.001), predominantly white race, and males (P-value <0.001). HF hospitalizations with hypoalbuminemia had double in-hospital mortality than those without (4.8% vs 2.7%, P < 0.001). However, there was no difference in mortality between patients with Systolic heart failure and Diastolic heart failure with concomitant low albumin levels (from 4.9 % vs 4.7%, P 0.13). We found that patients admitted with HF and concomitant Hypoalbuminemia (HA) had nearly twice the odds of in-patient mortality than those with normal albumin levels. The Length of Stay (LOS) was higher between comparison groups. THC remained statistically indifferent in patients regardless of albumin levels but was greater in hypoalbuminemic patients with Systolic heart failure than Diastolic heart failure ones.

Representation of time-varying and time-invariant EMR data and its application in modeling outcome prediction for heart failure patients

OBJECTIVE

To represent a patient record with both time-invariant and time-varying features as a single vector using an end-to-end deep learning model, and further to predict the kidney failure (KF) status and mortality of heart failure (HF) patients.

MATERIALS AND METHODS

The time-invariant EMR data included demographic information and comorbidities, and the time-varying EMR data were lab tests. We used a Transformer encoder module to represent the time-invariant data, and refined a long short-term memory (LSTM) with a Transformer encoder attached to the top to represent the time-varying data, taking the original measured values and their corresponding embedding vectors, masking vectors, and two types of time intervals as inputs. The proposed representations of patients with time-invariant and time-varying data were used to predict KF status (949 out of 5268 HF patients diagnosed with KF) and mortality (463 in-hospital deaths) for HF patients. Comparative experiments were conducted between the proposed model and some representative machine learning models. Ablation experiments were also performed around the time-varying data representation, including replacing the refined LSTM with the standard LSTM, GRU-D and T-LSTM, respectively, and removing the Transformer encoder and the time-varying data representation module, respectively. The visualization of the attention weights of the time-invariant and time-varying features was used to clinically interpret the predictive performance. We used the area under the receiver operating characteristic curve (AUROC), the area under the precision-recall curve (AUPRC), and the F1-score to evaluate the predictive performance of the models.

RESULTS

The proposed model achieved superior performance, with average AUROCs, AUPRCs and F1-scores of 0.960, 0.610 and 0.759 for KF prediction and 0.937, 0.353 and 0.537 for mortality prediction, respectively. Predictive performance improved with the addition of time-varying data from longer time periods. The proposed model outperformed the comparison and ablation references in both prediction tasks.

CONCLUSIONS

Both time-invariant and time-varying EMR data of patients could be efficiently represented by the proposed unified deep learning model, which shows higher performance in clinical prediction tasks. The way to use time-varying data in the current study is hopeful to be used in other kinds of time-varying data and other clinical tasks.

Using a machine learning model to predict the development of acute kidney injury in patients with heart failure

Background

Heart failure (HF) is a life-threatening complication of cardiovascular disease. HF patients are more likely to progress to acute kidney injury (AKI) with a poor prognosis. However, it is difficult for doctors to distinguish which patients will develop AKI accurately. This study aimed to construct a machine learning (ML) model to predict AKI occurrence in HF patients.

Materials and methods

The data of HF patients from the Medical Information Mart for Intensive Care-IV (MIMIC-IV) database was retrospectively analyzed. A ML model was established to predict AKI development using decision tree, random forest (RF), support vector machine (SVM), K-nearest neighbor (KNN), and logistic regression (LR) algorithms. Thirty-nine demographic, clinical, and treatment features were used for model establishment. Accuracy, sensitivity, specificity, and the area under the receiver operating characteristic curve (AUROC) were used to evaluate the performance of the ML algorithms.

Results

A total of 2,678 HF patients were engaged in this study, of whom 919 developed AKI. Among 5 ML algorithms, the RF algorithm exhibited the highest performance with the AUROC of 0.96. In addition, the Gini index showed that the sequential organ function assessment (SOFA) score, partial pressure of oxygen (PaO₂), and estimated glomerular filtration rate (eGFR) were highly relevant to AKI development. Finally, to facilitate clinical application, a simple model was constructed using the 10 features screened by the Gini index. The RF algorithm also exhibited the highest performance with the AUROC of 0.95.

Conclusion

Using the ML model could accurately predict the development of AKI in HF patients.

Does Artificial Intelligence Make Clinical Decision Better? A Review of Artificial Intelligence and Machine Learning in Acute Kidney Injury Prediction

Acute kidney injury (AKI) is a common complication of hospitalization that greatly and negatively affects the short-term and long-term outcomes of patients. Current guidelines use serum creatinine level and urine output rate for defining AKI and as the staging criteria of AKI. However, because they are not sensitive or specific markers of AKI, clinicians find it difficult to predict the occurrence of AKI and prescribe timely treatment. Advances in computing technology have led to the recent use of machine learning and artificial intelligence in AKI prediction, recent research reported that by using electronic health records (EHR) the AKI prediction via machine-learning models can reach AUROC over 0.80, in some studies even reach 0.93. Our review begins with the background and history of the definition of AKI, and the evolution of AKI risk factors and prediction models is also appraised. Then, we summarize the current evidence regarding the application of e-alert systems and machine-learning models in AKI prediction.

Predictors of acute kidney injury in patients with acute decompensated heart failure in emergency departments in China

Objective

This retrospective multicentre observational study was performed to assess the predictors of acute kidney injury (AKI) in patients with acute decompensated heart failure (ADHF) in emergency departments in China.

Methods

In total, 1743 consecutive patients with ADHF were recruited from August 2017 to January 2018. Clinical characteristics and outcomes were compared between patients with and without AKI. Predictors of AKI occurrence and underdiagnosis were assessed in multivariate regression analyses.

Results

Of the 1743 patients, 593 (34.0%) had AKI. AKI was partly associated with short-term all-cause mortality and cost. Cardiovascular comorbidities such as coronary heart disease, diabetes mellitus, and hypertension remained significant predictors of AKI in the univariate analysis. AKI was significantly more likely to occur in patients with a lower arterial pH, lower albumin concentration, higher creatinine concentration, and higher N-terminal pro-brain natriuretic peptide (NT-proBNP) concentration. Patients treated with inotropic agents were significantly more likely to develop AKI during their hospital stay.

Conclusion

This study suggests that cardiovascular comorbidities, arterial pH, the albumin concentration, the creatinine concentration, the NT-proBNP concentration, and use of inotropic agents are predictors of AKI in patients with ADHF.

A validation study comparing existing prediction models of acute kidney injury in patients with acute heart failure

Acute kidney injury (AKI) is a common complication in acute heart failure (AHF) and is associated with prolonged hospitalization and increased mortality. The aim of this study was to externally validate existing prediction models of AKI in patients with AHF. Data for 10,364 patients hospitalized for acute heart failure between 2008 and 2018 were extracted from the Chang Gung Research Database and analysed. The primary outcome of interest was AKI, defined according to the KDIGO definition. The area under the receiver operating characteristic (AUC) curve was used to assess the discrimination performance of each prediction model. Five existing prediction models were externally validated, and the Forman risk score and the prediction model reported by Wang et al. showed the most favourable discrimination and calibration performance. The Forman risk score had AUCs for discriminating AKI, AKI stage 3, and dialysis within 7 days of 0.696, 0.829, and 0.817, respectively. The Wang et al. model had AUCs for discriminating AKI, AKI stage 3, and dialysis within 7 days of 0.73, 0.858, and 0.845, respectively. The Forman risk score and the Wang et al. prediction model are simple and accurate tools for predicting AKI in patients with AHF.

Risk factors and prognosis assessment for acute kidney injury: The 2020 consensus of the Taiwan AKI Task Force

Risk and prognostic factors for acute kidney injury (AKI) have been published in various studies across various populations. We aimed to explore recent advancements in and provide updated recommendations on AKI risk stratification and information about local AKI risk factors. The Taiwan Acute Kidney Injury Task Force reviewed relevant recently published literature and reached a consensus after group meetings. Systemic review and group discussion were performed. We conducted a meta-analysis according to the PRISMA statement for evaluating the diagnostic performance of the furosemide stress test. Several risk and susceptibility factors were identified through literature review. Contrast-associated AKI prediction models after coronary angiography were one of the most discussed prediction models we found. The basic approach and evaluation of patients with AKI was also discussed. Our meta-analysis found that the furosemide stress test can be used as a prognostic tool for AKI progression and to identify patients with AKI who are at low risk of renal replacement therapy. Factors associated with de novo chronic kidney injury or renal non-recovery after AKI were identified and summarized. Our review provided practical information about early identification of patients at high risk of AKI or disease progression for Taiwan local clinics.

Predictive Modeling of the Risk of Acute Kidney Injury in Critical Care: A Systematic Investigation of The Class Imbalance Problem

Acute Kidney Injury (AKI) in critical care is often a quickly-evolving clinical event with high morbidity and mortality. Early prediction of AKI risk in critical care setting can facilitate early interventions that are likely to provide ben- efit. Recently there have been some research on AKI prediction with patient Electronic Health Records (EHR). The class imbalance problem is encountered in such prediction setting where the number of AKI cases is usually much smaller than the controls. This study systematically investigates the impact of class imbalance on the performance of AKI prediction. We systematically investigate several class-balancing strategies to address class imbalance, includ- ing traditional statistical approaches and the proposed methods (case-control matching approach and individualized prediction approach). Our results show that the proposed class-balancing strategies can effectively improve the AKI prediction performance. Additionally, some important predictors (e.g., creatinine, chloride, and urine) for AKI can be found based on the proposed methods.

Invasive fungal disease is associated with chronic graft-versus-host disease after allogeneic hematopoietic stem cell transplant: a single center, retrospective study

BACKGROUND

Invasive fungal disease (IFD) and graft-versus-host disease (GVHD) are major causes of morbidity and mortality after allogeneic hematopoietic stem cell transplantation (allo-HSCT). However, the impacts of IFD on chronic GVHD remain unknown.

METHODS

We conducted a retrospective study of 510 patients with hematologic malignancy undergoing allo-HSCT to explore the effects of IFD on chronic GVHD.

RESULTS

The 2-year cumulative incidences of overall (limited and extensive) and extensive chronic GVHD post-transplantation were higher in patients with IFD compared with those without IFD (69.5% ± 4.2% versus 32.9% ± 2.4%, P < .001; 43.0% ± 5.2% versus 6.6% ± 1.4%, P < .001, respectively). Moreover, the patients with IFD had higher 5-year transplant-related mortality, lower 5-year overall survival and lower 5-year disease-free survival (29.8% ± 4.3% versus 9.8% ± 1.6%, P < .001; 50.5% ± 4.9% versus 71.3% ± 2.4%, P < .001 and 48.8% ± 4.7% versus 71.8% ± 2.3%, P < .001, respectively). Multivariable analyses demonstrated that IFD increased the risk of chronic GVHD.

CONCLUSION

Our results suggest that IFD significantly contributes to the development of chronic GVHD after allo-HSCT.

Early prediction of acute kidney injury following ICU admission using a multivariate panel of physiological measurements

BACKGROUND

The development of acute kidney injury (AKI) during an intensive care unit (ICU) admission is associated with increased morbidity and mortality.

METHODS

Our objective was to develop and validate a data driven multivariable clinical predictive model for early detection of AKI among a large cohort of adult critical care patients. We utilized data form the Medical Information Mart for Intensive Care III (MIMIC-III) for all patients who had a creatinine measured for 3 days following ICU admission and excluded patients with pre-existing condition of Chronic Kidney Disease and Acute Kidney Injury on admission. Data extracted included patient age, gender, ethnicity, creatinine, other vital signs and lab values during the first day of ICU admission, whether the patient was mechanically ventilated during the first day of ICU admission, and the hourly rate of urine output during the first day of ICU admission.

RESULTS

Utilizing the demographics, the clinical data and the laboratory test measurements from Day 1 of ICU admission, we accurately predicted max serum creatinine level during Day 2 and Day 3 with a root mean square error of 0.224 mg/dL. We demonstrated that using machine learning models (multivariate logistic regression, random forest and artificial neural networks) with demographics and physiologic features can predict AKI onset as defined by the current clinical guideline with a competitive AUC (mean AUC 0.783 by our all-feature, logistic-regression model), while previous models aimed at more specific patient cohorts.

CONCLUSIONS

Experimental results suggest that our model has the potential to assist clinicians in identifying patients at greater risk of new onset of AKI in critical care setting. Prospective trials with independent model training and external validation cohorts are needed to further evaluate the clinical utility of this approach and potentially instituting interventions to decrease the likelihood of developing AKI.

Multi-perspective predictive modeling for acute kidney injury in general hospital populations using electronic medical records

Objectives

Acute kidney injury (AKI) in hospitalized patients puts them at much higher risk for developing future health problems such as chronic kidney disease, stroke, and heart disease. Accurate AKI prediction would allow timely prevention and intervention. However, current AKI prediction researches pay less attention to model building strategies that meet complex clinical application scenario. This study aims to build and evaluate AKI prediction models from multiple perspectives that reflect different clinical applications.

Materials and Methods

A retrospective cohort of 76 957 encounters and relevant clinical variables were extracted from a tertiary care, academic hospital electronic medical record (EMR) system between November 2007 and December 2016. Five machine learning methods were used to build prediction models. Prediction tasks from 4 clinical perspectives with different modeling and evaluation strategies were designed to build and evaluate the models.

Results

Experimental analysis of the AKI prediction models built from 4 different clinical perspectives suggest a realistic prediction performance in cross-validated area under the curve ranging from 0.720 to 0.764.

Discussion

Results show that models built at admission is effective for predicting AKI events in the next day; models built using data with a fixed lead time to AKI onset is still effective in the dynamic clinical application scenario in which each patient's lead time to AKI onset is different.

Conclusion

To our best knowledge, this is the first systematic study to explore multiple clinical perspectives in building predictive models for AKI in the general inpatient population to reflect real performance in clinical application.

Higher diuretic dosing within the first 72 h is predictive of longer length of stay in patients with acute heart failure

Objective:

High-dose diuretic strategies during the first 72 h of hospitalization have been shown to improve symptom resolution in patients with acute heart failure with decreased ejection fraction; however, they have not been shown to decrease length of stay (LOS). This study aimed to examine a possible relationship between higher diuretic dosing in the first 72 h of hospitalization and longer LOS in such patients.

Methods:

In this retrospective study, we included 333 consecutive patients hospitalized for acute heart failure with decreased or preserved ejection fraction between July 2014 and June 2015 in an urban academic medical center. Multiple regression models with stepwise selection were used for data analysis. We also performed mediation analysis to assess the relationships between diuretic dose, worsening renal function (WRF) during the hospitalization, and LOS.

Results:

In the multiple regression analysis, higher diuretic dosing in the first 72 h independently predicted longer LOS [β=0.42, 95% CI (0.27, 0.56), p<0.001] after adjustments for baseline characteristics, disease severity, and comorbidities. In the mediation analysis, higher diuretic dosing remained a significant predictor for longer LOS even after controlling for the mediator WRF [β=0.39, 95% CI (0.26, 0.53), p<0.001]. WRF had a weak mediation effect on the relationship between higher diuretic dosing and longer LOS [indirect effect of higher diuretic dosing on longer LOS: 0.07, 95% CI (0.02, 0.14)].

Conclusion:

Higher diuretic dosing in the first 72 h of hospitalization was an independent predictor for longer LOS.