Validated risk prediction models for outcomes of acute kidney injury: a systematic review

Haredasht, Fateme Nateghi; Vanhoutte, Leen; Vens, Celine; Pottel, Hans; Viaene, Liesbeth; Corte, Wouter De

doi:10.1186/s12882-023-03150-0

Cited by 5 publications

(2 citation statements)

References 51 publications

(39 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Серед потенційних переваг цих біомаркерів -очевидна специфічність для ішемічного ураження нирок. Автори наголосили, що рівні KIM-1 і NAG у сечі значно підвищувались при гострому ураженні нирок [14].…”

Section: оригінальні дослідженняunclassified

The impact of renal tubulointerstitial dysfunction on the early and long-term prognosis in chronic heart failure patients with preserved left ventricular ejection fraction

Syvolap,

Lysenko,

Svitlyi

2024

Pathologia

View full text Add to dashboard Cite

Aim. To study the dependence of the early-term (1 year) and long-term (5 years) prognosis in patients with chronic heart failure (CHF) of ischemic origin with preserved left ventricular ejection fraction (LVEF) depending on renal tubulointerstitial functional disorders. Materials and methods. The study involved 88 patients (men – 46.6 % (n = 41); women – 53.4 % (n = 47)) with CHF of ischemic origin, stage II A–B, stage II–IV according to NYHA, 67 % (n = 59) with sinus rhythm, and 33 % (n = 29) with atrial fibrillation. Patients with sinus rhythm and atrial fibrillation were matched in age (p = 0.483), height (p = 0.345), weight (p = 0.317), body surface area (p = 0.153). NGAL levels were analyzed using an ELISA kit (E-EL-H0096, Elabscience, USA). NAG levels were analyzed using an ELISA kit (SEA 069 Hu, Cloud-Clone Corp., USA). KIM-1 levels were analyzed using an ELISA kit (SEA 785 Hu, Cloud-Clone Corp., USA). Kaplan–Meier curves and Cox proportional hazards regression analysis were performed. Results. No significant difference was found in the frequency of the cumulative endpoint during the first-year follow-up from the initial level of two markers of tubulointerstitial injury – KIM-1 (Log-Rank Test: p = 0.57529) and NAG (Log-Rank Test: p = 0.86001). According to the results of analysis of the Cox proportional hazards, only a tendency to increase in the risk factors of adverse events were observed in case of elevated KIM-1 (HR = 1.66; p = 0.5795) and NAG levels (HR = 1.1712; p = 0.8626) in this CHF patients’ cohort. Kaplan–Meier analysis revealed a probable (Log-Rank Test; p = 0.00141) increase in the frequency of the cumulative endpoint during the first year of follow-up in CHF patients with preserved LVEF due to increased serum NGAL level more than 168 ng/ml. According to the univariate model, an elevated serum NGAL level is associated with an increase in the relative risk by 4.2 times (95 % CI 1.78–16.89; p = 0.014). A reduced sodium level less than 142.5 mmol/l was associated with an increase in number of adverse cardiovascular events during the first-year follow- ups by 22 % (HR = 1.22, p = 0.029). After 5 years of follow-up, a decrease in sodium level less than 142.3 mmol/l is also characterized by a probable difference of the cumulative Kaplan–Meier’s curves (Cox–Mantel F-Test, p = 0.00287). According to the univariate model of Cox proportional hazards, the relative risk of adverse cardiovascular events in patients with CHF during the 5-year follow-up has a tendency to increase by 1.04 times (95 % CI 0.85–1.27; p = 0.72). Serum NGAL, a marker of renal tubulo-interstitial injury, doesn’t lose its properties as a powerful marker of an unfavorable long-term prognosis in patients with CHF with preserved LVEF (HR = 5.96; 95 % CI 1.17–30.50; p = 0.032). Conclusions. The most powerful factors of the early (1-year) prognosis of adverse cardiovascular events in CHF patients with preserved left ventricular ejection fraction are the marker of tubulointerstitial injury, serum NGAL over 168 ng/ml, as well as the marker of tubulointerstitial dysfunction – the serum sodium level less than 142.5 mmol/l. The electrolyte imbalance, decreased sodium level less than 142.3 mmol/l, remains a powerful marker of an unfavorable long-term 5-year prognosis in CHF patients with preserved left ventricular ejection fraction, meanwhile serum NGAL, a marker of renal tubulointerstitial injury, besides doesn’t lose its prognostic value (HR = 5.96; 95 % CI 1.17–30.50; p = 0.032), but also is independent from the parameters of the age (p = 0.409) and gender (p = 0.397) in such patients.

show abstract

Section: оригінальні дослідженняunclassified

The impact of renal tubulointerstitial dysfunction on the early and long-term prognosis in chronic heart failure patients with preserved left ventricular ejection fraction

Syvolap,

Lysenko,

Svitlyi

2024

Pathologia

View full text Add to dashboard Cite

show abstract

“…The duration of renal function recovery is increasingly recognized as a pivotal factor in predicting patient outcomes [ 4 ]. Studies have shown a correlation between prolonged AKI and heightened risks of complications and mortality [ 5 , 6 ].…”

Section: Introductionmentioning

confidence: 99%

A machine learning-based approach for predicting renal function recovery in general ward patients with acute kidney injury

Cho,

Jeong,

Kim

et al. 2024

Kidney Res Clin Pract

View full text Add to dashboard Cite

Background: Acute kidney injury (AKI) is a significant challenge in healthcare. While there are considerable researches dedicated to AKI patients, a crucial factor in their renal function recovery, is often overlooked. Thus, our study aims to address this issue through the development of a machine learning model to predict restoration of kidney function in patients with AKI. Methods: Our study encompassed data from 350,345 cases, derived from three hospitals. AKI was classified in accordance with the Kidney Disease: Improving Global Outcomes. Criteria for recovery were established as either a 33% decrease in serum creatinine levels at AKI onset, which was initially employed for the diagnosis of AKI. We employed various machine learning models, selecting 43 pertinent features for analysis. Results: Our analysis contained 7,041 and 2,929 patients’ data from internal cohort and external cohort respectively. The Categorical Boosting Model demonstrated significant predictive accuracy, as evidenced by an internal area under the receiver operating characteristic (AUROC) of 0.7860, and an external AUROC score of 0.7316, thereby confirming its robustness in predictive performance. SHapley Additive exPlanations (SHAP) values were employed to explain key factors impacting recovery of renal function in AKI patients. Conclusion: This study presented a machine learning approach for predicting renal function recovery in patients with AKI. The model performance was assessed across distinct hospital settings, which revealed its efficacy. Although the model exhibited favorable outcomes, the necessity for further enhancements and the incorporation of more diverse datasets is imperative for its application in real- world.

show abstract

Biomarkers of Acute Kidney Injury

Pavkovic,

Ravindra,

Vaidya

2024

Reference Module in Biomedical Sciences

View full text Add to dashboard Cite

Validated risk prediction models for outcomes of acute kidney injury: a systematic review

Cited by 5 publications

References 51 publications

The impact of renal tubulointerstitial dysfunction on the early and long-term prognosis in chronic heart failure patients with preserved left ventricular ejection fraction

The impact of renal tubulointerstitial dysfunction on the early and long-term prognosis in chronic heart failure patients with preserved left ventricular ejection fraction

A machine learning-based approach for predicting renal function recovery in general ward patients with acute kidney injury

Biomarkers of Acute Kidney Injury

Contact Info

Product

Resources

About