Acute Kidney Injury, Heart Failure, and Health Outcomes

Predictive characteristics and model development for acute heart failure preceding hip fracture surgery in elderly hypertensive patients: a retrospective machine learning approach

BACKGROUND

Hip fractures are a serious health concern among the elderly, particularly in patients with hypertension, where the incidence of acute heart failure preoperatively is high, significantly affecting surgical outcomes and prognosis. This study aims to assess the risk of preoperative acute heart failure in elderly patients with hypertension and hip fractures by constructing a predictive model using machine learning on potential risk factors.

METHODS

A retrospective study design was employed, collecting preoperative data from January 2018 to December 2019 of elderly hypertensive patients with hip fractures at the Third Hospital of Hebei Medical University. Using SPSS 24.0 and R software, predictive models were established through LASSO regression and multivariable logistic regression analysis. The models' predictive performance was evaluated using metrics such as the concordance index (C-index), receiver operating characteristic curve (ROC curve), and decision curve analysis (DCA), providing insights into the nomogram's predictive accuracy and clinical utility.

RESULTS

Out of 1038 patients screened, factors such as gender, age, history of stroke, arrhythmias, anemia, and complications were identified as independent risk factors for preoperative acute heart failure in the study population. Notable predictors included Sex (OR 0.463, 95% CI 0.299-0.7184, P = 0.001), Age (OR 1.737, 95% CI 1.213-2.488, P = 0.003), Stroke (OR 1.627, 95% CI 1.137-2.327, P = 0.008), Arrhythmia (OR 2.727, 95% CI 1.490-4.990, P = 0.001), Complications (OR 2.733, 95% CI 1.850-4.036, P < 0.001), and Anemia (OR 3.258, 95% CI 2.180-4.867, P < 0.001). The prediction model of acute heart failure was Logit(P) = -2.091-0.770 × Sex + 0.552 × Age + 0.487 × Stroke + 1.003 × Arrhythmia + 1.005 × Complications + 1.181 × Anemia, and the prediction model nomogram was established. The model's AUC was 0.785 (95% CI, 0.754-0.815), Decision curve analysis (DCA) further validated the nomogram's excellent performance, identifying an optimal cutoff value probability range of 3% to 58% for predicting preoperative acute heart failure in elderly patients with hypertension and hip fractures.

CONCLUSION

The predictive model developed in this study is highly accurate and serves as a powerful tool for the clinical assessment of the risk of preoperative acute heart failure in elderly hypertensive patients with hip fractures, aiding in the optimization of preoperative risk assessment and patient management.

Machine-learning predictions for acute kidney injuries after coronary artery bypass grafting: a real-life muticenter retrospective cohort study

BACKGROUND

Acute kidney injury (AKI) after coronary artery bypass grafting (CABG) surgery is associated with poor outcomes. The objective of this study was to apply a new machine learning (ML) method to establish prediction models of AKI after CABG.

METHODS

A total of 2,780 patients from two medical centers in East China who underwent primary isolated CABG were enrolled. The dataset was randomly divided for model training (80%) and model testing (20%). Four ML models based on LightGBM, Support vector machine (SVM), Softmax and random forest (RF) algorithms respectively were established in Python. A total of 2,051 patients from two other medical centers were assigned to an external validation group to verify the performances of the ML prediction models. The models were evaluated using the area under the receiver operating characteristics curve (AUC), Hosmer-Lemeshow goodness-of-fit statistic, Bland-Altman plots, and decision curve analysis. The outcome of the LightGBM model was interpreted using SHapley Additive exPlanations (SHAP).

RESULTS

The incidence of postoperative AKI in the modeling group was 13.4%. Similarly, the incidence of postoperative AKI of the two medical centers in the external validation group was 8.2% and 13.6% respectively. LightGBM performed the best in predicting, with an AUC of 0.8027 in internal validation group and 0.8798 and 0.7801 in the external validation group. The SHAP revealed the top 20 predictors of postoperative AKI ranked according to the importance, and the top three features on prediction were the serum creatinine in the first 24 h after operation, the last preoperative Scr level, and body surface area.

CONCLUSION

This study provides a LightGBM predictive model that can make accurate predictions for AKI after CABG surgery. The LightGBM model shows good predictive ability in both internal and external validation. It can help cardiac surgeons identify high-risk patients who may experience AKI after CABG surgery.

Renal function during hospitalization and outcome in Chinese patients with acute decompensated heart failure: A retrospective study and literature review

BACKGROUND

The heart and kidneys had demonstrated a bidirectional interaction that dysfunction of the heart or kidneys can induce dysfunction in the other organ.

HYPOTHESIS

Renal function and its decline during hospitalization may have impact on cardiovascular outcomes in patients with acute decompensated heart failure (ADHF).

METHODS

A total of 119 consecutive Chinese patients admitted for ADHF were prospectively enrolled. The course of renal function was presented with estimated glomerular filtration rate (eGFR), calculated by the four-variable equation proposed by the Modification of Diet in Renal Disease (MDRD) Study. Worsening renal function (WRF) was defined as eGFR decline between admission (eGFR_admission ) and predischarge (eGFR_predischarge ). Clinical outcomes were defined as 4P-major adverse cardiovascular events (4P-MACE), including the composition of cardiovascular death, nonfatal myocardial infarction, nonfatal stroke, and nonfatal HF hospitalization.

RESULTS

During an average 2.6 ± 3.2 years follow-up, 66 patients (55%) experienced 4P-MACE. Patients with impaired eGFR_predischarge (<60 ml/min/1.73 m² ) had more 4P-MACE than those with preserved eGFR_predischarge (64.7% vs. 43.1%, p = .019). The Kaplan-Meier survival curves showed significantly higher incidence of 4P-MACE in patients with impaired eGFR_predischarge than those with preserved eGFR_predischarge (p = .002). Cox regression analysis revealed that impaired eGFR_predischarge was significantly correlated with the development of 4P-MACE (hazard ratio, 2.003; 95% confidence interval, 1.072-3.744; p = .029). In contrast, outcomes would be similar with regard to eGFR on admission and eGFR decline during hospitalization.

CONCLUSIONS

Impaired renal function before discharge, but not impaired renal function on admission or WRF, is a significant risk factor for poor outcomes in patients with ADHF.

Neutrophil circadian rhythm is associated with different outcomes of acute kidney injury due to cholesterol crystal embolism

Cholesterol crystal (CC) embolism can cause acute tissue infarction and ischemic necrosis via triggering diffuse thrombotic angiopathy occluding arterioles and arteries. Neutrophils contribute to crystal-induced immunothrombosis as well as to ischemic necrosis-related necroinflammation. We speculated that CC embolism-induced acute kidney injury (AKI) would be circadian rhythm-dependent and associated with cyclic differences in neutrophil function. Injection of CC into the left kidney induced thrombotic angiopathy progressing starting as early as 3 h after CC injection followed by a progressive ischemic cortical necrosis and AKI at 24 h. In C57BL/6J mice, circulating CD11b+Ly6G+ neutrophils were higher during the day phase [Zeitgeber time (ZT) 0–12] compared to the dark phase (ZT12-24). In the time frame of thrombus formation at ZT13, more neutrophils were recruited into the injured kidney 24 h later compared to CC embolism at ZT5. This effect was associated with an increased circulating number of CXCR2+ neutrophils as well as an upregulated kidney adhesion molecule and chemokine expression. These findings were associated with a significant increase in kidney necrosis, and endothelial injury at ZT13. Thus, the time of day has an effect also on CC embolism-related AKI in association with the circadian rhythm of neutrophil recruitment.

Characteristics and outcomes of patients admitted for acute heart failure in a single-centre study

Aims

Acute heart failure represents a medical condition with very high mortality. Accurate risk stratification can help physicians to improve the health care about these patients. The aim of our study was to characterize real‐life patients admitted for acute heart failure in a specific region with one tertiary medical centre and to describe risk factors of short‐term and long‐term mortality.

Methods and results

We performed a retrospective analysis of patients admitted from January 2017 to December 2017 to Department of cardiology of the tertiary medical centre University Hospital in Hradec Kralove. We identified 385 patients admitted for acute heart failure to the standard care and intensive care unit. The median of age was 74 years (IQR 67.5–80) and 34% of patients were female. Hospital admission was due to de novo heart failure in 222 (57.7%) patients. The most common comorbidities were arterial hypertension (77.7%), dyslipidaemia (67.3%) and coronary artery disease (63.1%). Coronary artery disease (52.7% of cases) and valve disease (28.1% of cases) were the most common aetiologies of heart failure. The all‐cause in‐hospital mortality was 12.7%, 30‐day mortality was 14.6% and 1 year mortality was 34%. Among risk factors of in‐hospital mortality, the most significant factors were haemodialysis during the hospitalization [odds ratio (OR) 15.82, 95% confidence interval (CI) 2.96–84.57, P = 0.0008], chronic heart failure (OR 4.27, 95% CI 1.66–11.03, P = 0.001) and STEMI as a precipitating factor of heart failure (OR 4.19, 95% CI 1.23–14.25, P = 0.023). Haemodialysis during the hospitalization (OR 4.28, 95% CI 1.17–15.61, P = 0.025) and the comorbidity depression and anxiety (OR 3.49, 95% CI 1.45–8.39, P = 0.005) were the most significant risk factors of long‐term mortality.

Conclusions

Our study confirms very high mortality rates among patients with acute heart failure underlying poor prognosis of these patients. Comorbidities (peripheral artery disease, atrial fibrillation, chronic heart failure and depression and anxiety), precipitating factors of heart failure (myocardial infarction with ST segment elevation), complications occurring during the hospitalization (acute kidney injury, pulmonary ventilation for respiratory failure and haemodialysis) and the age of patients should be included in the risk stratification of in‐hospital, 30 day and 1 year mortality.

Diagnostic and prognostic significance of aberrant miR-652-3p levels in patients with acute decompensated heart failure and acute kidney injury

Objective

This study aimed to examine a novel microRNA (miR-652-3p) biomarker to improve early diagnosis of acute kidney injury (AKI) in patients with acute decompensated heart failure (ADHF) and to evaluate the survival predictive value of miR-652-3p.

Methods

We retrospectively analyzed the data of 196 patients with ADHF, including 65 who developed AKI during hospitalization. Neutrophil gelatinase-associated lipocalin (NGAL) levels were measured in serum and urine samples. Real-time quantitative PCR was applied to evaluate miR-652-3p mRNA expression. The diagnostic performance of miR-652-3p was examined using receiver operating characteristic curve analysis. The prognostic value of miR-652-3p was also analyzed.

Results

Serum and urinary NGAL and miR-652-3p levels were elevated in patients with ADHF and AKI. Serum and urinary miR-652-3p expression had diagnostic value in predicting AKI onset in patients with ADHF, and it had improved diagnostic performance when used with NGAL. Patients with AKI and high miR-652-3p levels had a high failure rate of renal recovery and poor 180-day survival.

Conclusion

Serum and urinary miR-652-3p may be a candidate biomarker for early diagnosis of AKI in patients with ADHF and for predicting the prognosis of AKI. The combination of NGAL and miR-652-3p may accurately predict AKI onset in ADHF.

A New Risk Score to Predict In-Hospital Mortality in Elderly Patients With Acute Heart Failure: On Behalf of the Journey HF-TR Study Investigators

We aimed to predict in-hospital mortality of elderly patients with heart failure (HF) by using a risk score model which could be easily applied in routine clinical practice without using an electronic calculator. The study population (n = 1034) recruited from the Journey HF-TR (Patient Journey in Hospital with Heart Failure in Turkish Population) study was divided into a derivation and a validation cohort. The parameters related to in-hospital mortality were first analyzed by univariate analysis, then the variables found to be significant in that analysis were entered into a stepwise multivariate logistic regression (LR) analysis. Patients were classified as low, intermediate, and high risk. A risk score obtained by taking into account the regression coefficients of the significant variables as a result of the LR analysis was tested in the validation cohort using receiver operating characteristic curve analysis. In total, 6 independent variables (age, blood urea nitrogen, previous history of hemodialysis/hemofiltration, inotropic agent use, and length of intensive care stay) associated with in-hospital mortality were included in the analysis. The risk score had a good discrimination in both the derivation and validation cohorts. A new validated risk score to determine the risk of in-hospital mortality of elderly hospitalized patients with HF was developed by including 6 independent predictors.

MicroRNA-423-5p as a biomarker for early diagnosis and outcome prediction of acute kidney injury in patients with acute decompensated heart failure

OBJECTIVE

To evaluate the clinical significance of serum and urinary microRNA-423-5p in the prediction of acute kidney injury onset and survival in patients with acute decompensated heart failure.

METHODS

A total of 180 acute decompensated heart failure patients, including 57 acute kidney injury cases and 123 non-acute kidney injury cases, were included in this study. Serum and urinary neutrophil gelatinase-associated lipocalin, a biomarker of renal injury of acute kidney injury, was detected using an enzyme-linked immunosorbent assay. Expression of microRNA-423-5p in serum and urine samples was examined using quantitative real-time polymerase chain reaction. The clinical significance of microRNA-423-5p was evaluated using receiver operating characteristic curve and Kaplan-Meier survival analysis.

RESULTS

The levels of neutrophil gelatinase-associated lipocalin and microRNA-423-5p in serum and urine samples were elevated in patients with acute kidney injury compared with the non-acute kidney injury cases (all P < 0.05). Serum and urinary microRNA-423-5p had relatively high predictive performance for acute kidney injury onset in acute decompensated heart failure patients, and this predictive value was more significant when combined with urinary neutrophil gelatinase-associated lipocalin. In addition, serum and urinary elevated levels of microRNA-423-5p predicted a poor 180-day survival in the acute kidney injury group.

CONCLUSION

Increased serum and urinary microRNA-423-5p can predict the occurrence of acute kidney injury in acute decompensated heart failure patients, and is associated with poor survival of acute kidney injury patients. In addition, the diagnostic value of urine neutrophil gelatinase-associated lipocalin for the early screening of acute kidney injury from acute decompensated heart failure patients might be improved by considering the changes in urinary microRNA-423-5p.