Associations Between Cardiac Biomarkers and Cardiac Structure and Function in CKD

Plasma concentrations of neurofilament light, p-Tau231 and glial fibrillary acidic protein are elevated in patients with chronic kidney disease and correlate with measured glomerular filtration rate

BACKGROUND

Patients with chronic kidney disease (CKD) have a high prevalence of cerebrovascular disease and cognitive impairment. The objective was to analyse whether plasma concentrations of neurofilament light chain (NfL), glial fibrillary acidic protein (GFAP) and phosphorylated Tau231 (p-Tau231) are elevated in patients with CKD and to identify independent predictors of these biomarkers, with an emphasis on the role of measured glomerular filtration rate (mGFR).

METHODS

In this cross-sectional cohort study, we included 110 patients with CKD stages 3 and 4 (estimated GFR 15-59 ml/min/1.73 m2) without manifest cerebrovascular disease or dementia, and 55 healthy controls. Biomarkers of neurological disorders were measured with ultrasensitive single molecule array methods.

RESULTS

Plasma concentrations (median [IQR]) of NfL (37.5 [22.1-47.5] vs. 13.4 [10.5-16.7] ng/L, p < 0.001), p-Tau231 (25.7 [19.1-38.7] vs. 13.9 [10.5-16.3] ng/L, p < 0.001) and GFAP (190 [140-281] vs. 153 [116-211] ng/L, p < 0.001) were elevated in patients with CKD vs. controls. Measured GFR was negatively correlated with NfL (r = - 0.706, p < 0.001), p-Tau231 (r = - 0.561, p < 0.001), and GFAP (r = - 0.385, p < 0.001). In multivariable linear regression models, mGFR was an independent predictor of log-transformed plasma concentrations of NfL (standardized beta coefficient [β] = - 0.439, p < 0.001) and GFAP (β = - 0.321, p < 0.001).

CONCLUSION

Patients with CKD had elevated plasma concentrations of NfL, p-Tau231 and GFAP compared with controls, and these biomarkers were inversely correlated with mGFR. Measured GFR was a significant, independent predictor of plasma concentrations of NfL and GFAP in patients with CKD. The mechanisms underlying this association need further investigation. Plasma levels of NfL and GFAP should be interpreted cautiously in patients with marked reductions in GFR.

Impact of Uric Acid Levels on Mortality and Cardiovascular Outcomes in Relation to Kidney Function

Background: Uric acid levels are linked to cardiovascular outcomes and mortality, especially in chronic kidney disease (CKD). However, their impact across varying kidney function remains unclear. Methods: We conducted a retrospective cohort study using the Observational Medical Outcomes Partnership Common Data Model (OMOP-CDM) database from a single center. Adult patients with at least one serum uric acid measurement between 2002 and 2021 were included and categorized by estimated glomerular filtration rate (eGFR): normal kidney function (≥90 mL/min/1.73 m2), mild dysfunction (60-89 mL/min/1.73 m2), moderate dysfunction (30-59 mL/min/1.73 m2), and advanced dysfunction (<30 mL/min/1.73 m2). The primary outcome was all-cause mortality with secondary outcomes being myocardial infarction (MI) and heart failure (HF). Results: A total of 242,793 participants were analyzed. Uric acid levels showed a U-shaped association with all-cause mortality in advanced kidney dysfunction, where both low (<3 mg/dL) and high (>10 mg/dL) levels increased mortality risk. In mild kidney dysfunction, lower uric acid levels were linked to better survival. HF risk increased linearly with higher uric acid, particularly in normal kidney function, while no significant association was found between uric acid and MI in any group. Conclusions: Uric acid levels are associated with mortality in a U-shaped pattern for advanced kidney dysfunction, while lower levels appear protective in mild dysfunction. These findings suggest the need for personalized uric acid management in CKD patients based on their kidney function.

Association of soluble suppression of tumorigenicity 2 with mortality and adverse outcomes in chronic kidney disease: a systematic review and meta-analysis

BACKGROUND

Early risk stratification is necessary to prevent chronic kidney disease progression and complications. This systematic review aims to evaluate the association of soluble suppression of tumorigenicity 2 (sST2), a member of the interleukin-1 receptor family, with all-cause mortality, cardiovascular disease and renal function deterioration among chronic kidney disease patients.

METHODS

PubMed, Scopus, Web of Science, CENTRAL and Google Scholar were systematically searched from inception to December 20, 2023. Cohort studies examining the prognostic role of sST2 levels in pre-dialysis and dialysis patients were included. In case of 3 or more studies per outcome, conventional and dose-response meta-analyses were conducted.

RESULTS

Overall, 21 studies were included comprising 15,100 patients. In pre-dialysis patients, the qualitative synthesis of studies suggested that high sST2 is associated with significantly increased all-cause mortality, while evidence regarding cardiovascular events or kidney disease progression was conflicting. In the dialysis population, high sST2 was linked to an elevated risk of all-cause (Hazard ratio-HR: 3.00, 95% confidence intervals-CI: 1.95-4.61) and cardiovascular (HR: 2.38, 95% CI: 1.69-3.34) mortality. Dose-response meta-analysis suggested a log-linear association of sST2 with both all-cause (χ2: 34.65, p value < 0.001) and cardiovascular (χ2: 29.14, p value < 0.001) mortality, whereas findings regarding cardiovascular events were limited with mixed results.

CONCLUSIONS

High sST2 values are associated with an increased risk of all-cause mortality in pre-dialysis and dialysis patients, as well as with an elevated risk of cardiovascular mortality in the dialysis population. Further studies are needed to elucidate its potential association with cardiovascular events and kidney disease progression.

Early Serum Biomarkers of Cardiovascular Disease in Elderly Patients with Chronic Kidney Disease

BACKGROUND

The global population is aging. It is estimated that by 2050, the proportion of the elderly population will reach 16%. Various studies have suggested that elderly people have a greater incidence of CKD. These elderly patients are also susceptible to cardiovascular disease (CVD), which is the leading cause of death, resulting in poor prognosis in this population. However, CVD in such patients is often insidious and lacks early markers for effective evaluation. Fortunately, several studies have recently proposed biomarkers associated with this process.

SUMMARY

This study aimed to summarize the early biomarkers of CVD in elderly patients with CKD to provide a basis for its prevention and treatment.

KEY MESSAGES

This review outlines four categories of potential early biomarkers. All of them have been shown to have some clinical value for these patients, but more research is still needed.

Plasma B-type natriuretic peptide is independently associated with cardiovascular events and mortality in patients with chronic kidney disease

The association between B-type natriuretic peptide (BNP) and cardiovascular (CV) events and mortality has not been well characterized in patients with chronic kidney disease (CKD). We prospectively investigated whether BNP was associated with CV events or mortality beyond cardiac alterations in 1078 patients with CKD. Participants were divided into the following 3 groups according to circulating BNP concentration: < 40 pg/mL, low; 40-100 pg/mL, middle; and > 100 pg/mL, high. Primary outcome was fatal or nonfatal CV events, and alternative outcome was a composite of fatal or nonfatal CV events, or non-CV deaths. During a median follow-up of 2.6 years, CV and composite events occurred in 158 and 248 participants, respectively. Cox analyses after adjustment for covariates, including cardiac parameters, showed that the hazard ratios (HRs) (95% confidence intervals [CIs]) for CV events of middle and high groups were 1.00 (0.63, 1.58) and 1.72 (1.06, 2.79), respectively, compared with low group. Additionally, similar results were obtained for composite events; the HRs (95% CIs) of middle and high groups were 1.10 (0.77, 1.57) and 1.54 (1.04, 2.27), respectively, compared with low group. Thus, in CKD, high BNP concentrations were independently associated with CV events and mortality, independent of cardiac alterations.

Galectin-3 in chronic kidney disease

BACKGROUND AND AIMS

High serum galectin-3 has been associated with adverse outcomes among dialysis patients, although its prognostic role remains unclear among individuals with earlier-stage chronic kidney disease. The present systematic review aims to evaluate the association of serum galectin-3 with survival, cardiovascular disease and kidney disease progression among non-dialysis chronic kidney disease patients.

METHODS

PubMed, Scopus, Web of Science, CENTRAL and Google Scholar were systematically searched till November 10, 2023. All observational studies assessing the prognostic role of serum galectin-3 in patients with non-dialysis chronic kidney disease were included.

RESULTS

Overall, 12 studies (10 cohort, 2 cross-sectional) were included, comprising 9,349 patients. The endpoint of survival was assessed in 5 studies, indicating a significant association between increasing serum galectin-3 levels and higher all-cause mortality risk (Hazard ratio per unit: 1.22, 95 % confidence intervals-CI: 1.05-1.41, ≥6 ng/mL: 2.66, 95 % CI: 1.68-4.23). Current evidence coming from 4 studies was inconclusive regarding the potential link of galectin-3 and kidney function decline, yielding conflicting results. No significant associations between serum galectin-3 and heart failure, cardiovascular events or death were consistently reported.

CONCLUSIONS

This systematic review supports the prognostic role of galectin-3 in chronic kidney disease, as its increased serum values may be associated with higher all-cause mortality risk. No clear role could be supported for serum galectin-3 regarding the prediction of cardiovascular disease or kidney disease progression.

Correlations of sST2 and Gal-3 with Cardiothoracic Ratio in Patients with Chronic Kidney Disease

Chronic kidney disease (CKD) frequently correlates with cardiovascular complications. Soluble suppression of tumorigenicity 2 (sST2) and Galectin-3 (Gal-3) are emerging as cardiac markers with potential relevance in cardiovascular risk prediction. The cardiothoracic ratio (CTR), a metric easily obtainable from chest radiographs, has traditionally been used to assess cardiac size and the potential for cardiomegaly. Understanding the correlation between these cardiac markers and the cardiothoracic ratio (CTR) could provide valuable insights into the cardiovascular prognosis of CKD patients. This study aimed to explore the relationship between sST2, Gal-3, and the CTR in individuals with CKD. Plasma concentrations of sST2 and Gal-3 were assessed in a cohort of 123 CKD patients by enzyme-linked immunosorbent assay (ELISA). On a posterior-to-anterior chest X-ray view, the CTR was determined by comparing the widths of the heart to that of the thorax. The mean concentration of sST2 in the study participants ranged from 775.4 to 4475.6 pg/mL, and the mean concentration of Gal-3 ranged from 4.7 to 9796.0 ng/mL. Significant positive correlations were observed between sST2 and the CTR (r = 0.291, p < 0.001) and between Gal-3 and the CTR (r = 0.230, p < 0.01). Our findings indicate that elevated levels of sST2 and Gal-3 are associated with an increased CTR in CKD patients. This relationship may enable better cardiovascular risk evaluation for CKD patients. Further studies are warranted to explore the clinical implications of these associations.

Cardiomyopathy in chronic kidney disease: clinical features, biomarkers and the contribution of murine models in understanding pathophysiology

The cardiorenal syndrome (CRS) is described as a multi-organ disease encompassing bidirectionally heart and kidney. In CRS type 4, chronic kidney disease (CKD) leads to cardiac injury. Different pathological mechanisms have been identified to contribute to the establishment of CKD-induced cardiomyopathy, including a neurohormonal dysregulation, disturbances in the mineral metabolism and an accumulation of uremic toxins, playing an important role in the development of inflammation and oxidative stress. Combined, this leads to cardiac dysfunction and cardiac pathophysiological and morphological changes, like left ventricular hypertrophy, myocardial fibrosis and cardiac electrical changes. Given that around 80% of dialysis patients suffer from uremic cardiomyopathy, the study of cardiac outcomes in CKD is clinically highly relevant. The present review summarizes clinical features and biomarkers of CKD-induced cardiomyopathy and discusses underlying pathophysiological mechanisms recently uncovered in the literature. It discloses how animal models have contributed to the understanding of pathological kidney-heart crosstalk, but also provides insights into the variability in observed effects of CKD on the heart in different CKD mouse models, covering both "single hit" as well as "multifactorial hit" models. Overall, this review aims to support research progress in the field of CKD-induced cardiomyopathy.

The Diagnostic Accuracy of N-Terminal Pro-B-Type Natriuretic Peptide and Soluble ST2 for Heart Failure in Chronic Kidney Disease Patients: A Comparative Analysis

BACKGROUND N-terminal proatrial natriuretic peptide (NT-proBNP) levels are often markedly elevated in patients with chronic kidney disease (CKD). Identifying novel biomarkers is an important step toward effective diagnosis. Interleukin-1 receptor-like 1 (IL1RL1) protein and human/Soluble suppression of tumorigenesis-2 (sST2) are promising biomarkers for heart failure (HF). This study aimed to assess the trend of NT-proBNP and sST2 in chronic kidney disease and their diagnostic value for HF. MATERIAL AND METHODS This study was carried out on 420 patients who were divided into a no heart failure group (N=182) and a heart failure group (N=238). Spearman correlation analysis was used to test the association of sST2 and NT-proBNP with renal function. The diagnostic value of each biomarker was assessed using receiver operating characteristic (ROC) curves according to 3 different forms: Total group (n=420), non-CKD group (n=217), and CKD group (n=203). RESULTS A striking correlation between eGFR and NT-proBNP (r=-0.525; P<0.001) seemed to be far stronger than that with sST2 (r=-0.147; P<0.05). The optimum cutoff points for sST2 and NT-proBNP to detect HF were 28.960 ng/mL and 1280 pg/mL, respectively, in total, 28.71 ng/mL and 481 pg/mL, respectively, in non-CKD patients, and 30.55 ng/mL and 3314 pg/mL, respectively, in CKD patients. The combined model of sST2 and NT-proBNP was superior to the model of sST2 or NT-proBNP alone, and the difference was statistically significant (P<0.05). CONCLUSIONS The diagnostic value of sST2 is less affected by decreased renal function. sST2 combined with NT-proBNP may improve the diagnostic accuracy of HF.

Cardiac markers and cardiovascular disease in chronic kidney disease

Cardiovascular disease (CVD) is prevalent in patients with chronic kidney disease (CKD) and it is responsible for approximately half of all CKD-related deaths. CVDs are the primary cause of death in hemodialysis patients due to major adverse cardiovascular events. Therefore, better approaches for differentiating chronic hemodialysis patients at higher cardiovascular risk will help physicians improve clinical outcomes. Hence, there is an urgent need to discover feasible and reliable cardiac biomarkers to improve diagnostic accuracy, reflect myocardial injury, and identify high-risk patients. Numerous biomarkers that have significant prognostic value with respect to adverse CVD outcomes in the setting of mild to severe CKD have been identified. Therefore, a better understanding of the positive clinical impact of cardiac biomarkers on CVD patient outcomes is an important step toward prevention and improving treatment in the future. In this review, we address the relationship between cardiovascular biomarkers and CKD treatment strategies to elucidate the underlying importance of these biomarkers to patient outcomes.

Connection between Cardiac Fibrosis Biomarkers and Echocardiography Parameters in Advanced Chronic Kidney Disease Patients

BACKGROUND

Myocardial fibrosis represents a mainstay pathway in the pathophysiology of uremic cardiomyopathy. This process leads to structural and functional changes in the heart, which can be detected by echocardiography. The purpose of our study was to determine the association between four echocardiographic parameters (ejection fraction (EF), global longitudinal strain (GLS), mean E/e' ratio, and left atrial volume indexed) and biomarkers associated with cardiac fibrosis, such as procollagen type I carboxy-terminal propeptide (PICP), procollagen type III N-terminal peptide (P3NP), and galectin-3 (Gal-3) in patients with end-stage renal disease (ESRD).

METHODS

140 patients with ESRD were enrolled and investigated by echocardiography and the serum levels of the aforementioned biomarkers were determined at baseline.

RESULTS

The mean EF was 53.63 ± 8%, the mean GLS was -10.2 ± 5.3%, the mean E/e' ratio was 9.8 ± 4.3, and the mean left atrial volume indexed (LAVI) was 45.8 ± 14.2 mL/m². The average levels for PICP, P3NP, and Gal-3 were 457.2 ± 240 µg/L, 242 ± 199.9 µg/L, and 10.7 ± 3.7 ng/mL, respectively. In regression analysis, PICP was strongly associated with all four echocardiographic parameters (EF: p = 0.0002, R² = 0.69; GLS: p = 0.00001, R² = 0.81; mean E/e': p = 0.00002; R² = 0.89; LAVI: p = 0.003; R² = 0.73). P3NP and Gal-3 were only associated with the EF (p = 0.01, R² = 0.31 and p = 0.02; R² = 0.35, respectively).

CONCLUSION

Our study evidenced that PICP, a collagen-derived biomarker, is associated with important echocardiography parameters, suggesting that it can serve as an indicator of the presence of subclinical systolic and diastolic dysfunction in patients with advanced CKD.

Applications of cardiac biomarkers in chronic kidney disease

PURPOSE OF REVIEW

Cardiovascular disease is the leading cause of death in individuals with chronic kidney disease (CKD). The mechanisms connecting CKD and cardiovascular disease are complex, and serum biomarkers can help improve our understanding. Nt-proBNP and troponin have documented success as biomarkers to diagnose and provide mechanistic insights in non-CKD populations. The purpose of this review is to summarize evidence suggesting efficacy and potential for clinical application of Nt-proBNP and troponin in individuals with CKD.

RECENT FINDINGS

Our understanding of how Nt-proBNP and Troponin should be interpreted in those with CKD is evolving. Although both biomarkers are in part cleared by the kidney, elevated levels predominantly reflect cardiovascular disease. Both Nt-proBNP and troponin are associated with risk for future cardiovascular events in CKD. Determining CKD-specific cutoffs and using biomarkers to guide therapy remains under active investigation.

SUMMARY

Of the many serum biomarkers under investigation, Nt-proBNP and troponin best meet the criteria for effective biomarkers in CKD. Assays are widely available and proven to be accurate in CKD populations. Nt-proBNP and troponin deserve special focus in ongoing research of cardiovascular risk reduction in CKD, especially to identify patients at the highest risk, suggest targetable mechanisms and assess treatment efficacy.

Left ventricular myocardial mass index associated with cardiovascular and renal prognosis in IgA nephropathy

Introduction

In chronic kidney disease (CKD), like in IgA nephropathy (IgAN), cardiovascular (CV) mortality and morbidity are many times higher than in the general population, and left ventricular hypertrophy (LVH) is an independent risk factor for CV disease. This follow-up study investigated the association between left ventricular mass index (LVMI) and renal or cardiovascular outcomes.

Methods

We examined 118 IgAN patients prospectively. LVMI and LV geometry was investigated using echocardiography. The primary combined endpoints were total mortality, major CV events, and end-stage renal disease. Secondary endpoints, i.e.—cardiovascular or renal endpoints,—were also examined separately.

Results

Sixty seven percent were males, mean age 53.5 ± 13.5. Mean follow-up time: 184 months. LVMI inversely correlated with eGFR (corr. coefficient: -0.365; p < 0.01). We divided the patients into two groups based on the LVMI cut-off suggested by the literature. The presence of LVH caused a worse prognosis in primary (p < 0.001), renal endpoints (p = 0.01), and also in CV endpoints (p = 0.001). The higher LVMI in men significantly worsened the prognosis in all endpoints. Concentric hypertrophy meant a worse prognosis. Independent predictors of LVMI were gender and eGFR in uni- and multivariate regression and hemoglobin levels only in logistic regression. Independent predictors of the primary endpoint were LVMI, eGFR, gender, obesity, HT, DM, and metabolic syndrome in Cox regression analysis.

Conclusion

Increased LVMI may predict the progression to end-stage renal disease and CV events in IgAN. Determining LVMI may be a useful parameter not only in CV risk but also in the stratification of renal risk in CKD.

Rates of Cardiovascular Disease and CKD Progression in Young Adults with CKD across Racial and Ethnic Groups

Background

Significant racial and ethnic disparities in cardiovascular (CV) and kidney function outcomes in older adults with chronic kidney disease (CKD) have been reported. However, little is known about the extent to which these disparities exist in patients with CKD during the foundational period of young adulthood. The objective of this study was to determine risk factors and rates of CV disease and CKD progression in young adults with CKD across racial and ethnic groups.

Methods

We studied all participants aged 21-40 years of age enrolled in the Chronic Renal Insufficiency Cohort (CRIC) Study (n=317). Baseline CV risk factors were described across racial and ethnic groups.

Results

Outcomes included CV events or death (first incidence of heart failure, myocardial infarction, and stroke or death) and CKD progression (>50% decline in eGFR from baseline or end stage kidney disease [ESKD]). Incidence rate ratios (IRRs) were compared as a secondary analysis for participants identifying as Black or Hispanic with those identifying as White or another race and ethnicity. Adjusted models included age, sex, and per APOL1 high-risk allele. CV risk factors were higher in Black and Hispanic participants, including mean SBP, BMI, median UACr, and LDL. Black and Hispanic participants had higher incidence rates of HF (17.5 versus 5.1/1000 person-years), all-cause mortality (15.2 versus 7.1/1000 person-years), and CKD progression (125 versus 59/1000 person-years).

Conclusions

In conclusion, we found a higher prevalence of CV risk factors, some modifiable, in young adults with CKD who identify as Black or Hispanic. Future strategies to ameliorate the racial and ethnic inequality in health outcomes earlier in life for patients with CKD should be prioritized.

Cardiac biomarkers in pediatric CKD-a prospective follow-up study

BACKGROUND

The N-terminal pro-B-type natriuretic peptide (NT-proBNP) and high-sensitive cardiac-specific troponin T (hs-cTnT) are associated with abnormal cardiac structure and function and an increased risk of cardiovascular death in chronic kidney disease (CKD) patients. There is limited knowledge about these cardiac markers in pediatric CKD patients.

METHODS

Longitudinal levels of NT-proBNP and hs-cTnT were analyzed in 48 pediatric patients, 22 with CKD (GFR range 8.8-68 mL/min/1.73 m²) and 26 transplanted patients (CKD-T; GFR range 30-99 mL/min/1.73 m²). Follow-up was scheduled after 1 and 3 years. Longitudinal patterns and associations to kidney function, cardiovascular risk markers, and echocardiographic parameters were assessed.

RESULTS

High NT-proBNP was present in 27% of CKD and 11% of CKD-T patients. Similarly 32% of CKD and 8% of CKD-T patients had elevated hs-cTnT levels. In longitudinal multivariate analyses, high log NT-proBNP was associated with low GFR (β =  - 0.01, p = 0.01) and elevated left ventricular mass index (LVMI; β = 0.02, p = 0.05). The strong association to LVMI remained when using GFR-adjusted NT-proBNP in similar analysis. Patients with left ventricular hypertrophy (LVH) also had higher NT-proBNP (235 [146-301] ng/L) than patients without LVH (86 [11-477] ng/L), p = 0.02. High hs-cTnT over-time was also associated with low GFR (β =  - 0.007, p = 0.01) and a low cc-TDI e´/a´, indicating a worse LV diastolic function (β =  - 0.09, p = 0.05). This association did not persist for GFR-adjusted hs-cTnT.

CONCLUSIONS

NT-proBNP and hs-cTnT are elevated in pediatric CKD and CKD-T patients. GFR-adjusted NT-proBNP was associated with longitudinal levels of elevated LVMI suggesting this might be a marker for early subclinical myocardial damage. A higher resolution version of the Graphical abstract is available as Supplementary information.

A Growth Differentiation Factor 15-Based Risk Score Model to Predict Mortality in Hemodialysis Patients

BACKGROUND

The risk of cardiovascular (CV) and fatal events remains extremely high in patients with maintenance hemodialysis (MHD), and the growth differentiation factor 15 (GDF15) has emerged as a valid risk stratification biomarker. We aimed to develop a GDF15-based risk score as a death prediction model for MHD patients.

METHODS

Age, biomarker levels, and clinical parameters were evaluated at study entry. One hundred and seventy patients with complete information were finally included for data analysis. We performed the Cox regression analysis of various prognostic factors for mortality. Then, age, GDF15, and robust clinical predictors were included as a risk score model to assess the predictive accuracy for all-cause and CV death in the receiver operating characteristic (ROC) curve analysis.

RESULTS

Age, GDF15, and albumin were significantly associated with higher all-cause and CV mortality risk that were combined as a risk score model. The highest tertile of GDF-15 (>1707.1 pg/mL) was associated with all-cause mortality (adjusted hazard ratios (aHRs): 3.06 (95% confidence interval (CI): 1.20-7.82), p < 0.05) and CV mortality (aHRs: 3.11 (95% CI: 1.02-9.50), p < 0.05). The ROC analysis of GDF-15 tertiles for all-cause and CV mortality showed 0.68 (95% CI = 0.59 to 0.77) and 0.68 (95% CI = 0.58 to 0.79), respectively. By contrast, the GDF15-based prediction model for all-cause and CV mortality showed 0.75 (95% CI: 0.67-0.82) and 0.72 (95% CI: 0.63-0.81), respectively.

CONCLUSION

Age, GDF15, and hypoalbuminemia predict all-cause and CV death in MHD patients, yet a combination scoring system provides more robust predictive powers. An elevated GDF15-based risk score warns clinicians to determine an appropriate intervention in advance. In light of this, the GDF15-based death prediction model could be developed in the artificial intelligence-based precision medicine.