Development of a Biomarker Panel to Distinguish Risk of Progressive Chronic Kidney Disease

Applying stacking ensemble method to predict chronic kidney disease progression in Chinese population based on laboratory information system: a retrospective study

Background and Objective

Chronic kidney disease (CKD) is a major public health issue, and accurate prediction of the progression of kidney failure is critical for clinical decision-making and helps improve patient outcomes. As such, we aimed to develop and externally validate a machine-learned model to predict the progression of CKD using common laboratory variables, demographic characteristics, and an electronic health records database.

Methods

We developed a predictive model using longitudinal clinical data from a single center for Chinese CKD patients. The cohort included 987 patients who were followed up for more than 24 months. Fifty-three laboratory features were considered for inclusion in the model. The primary outcome in our study was an estimated glomerular filtration rate ≤15 mL/min/1.73 m2 or kidney failure. Machine learning algorithms were applied to the modeling dataset (n = 296), and an external dataset (n = 71) was used for model validation. We assessed model discrimination via area under the curve (AUC) values, accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and F1 score.

Results

Over a median follow-up period of 3.75 years, 148 patients experienced kidney failure. The optimal model was based on stacking different classifier algorithms with six laboratory features, including 24-h urine protein, potassium, glucose, urea, prealbumin and total protein. The model had considerable predictive power, with AUC values of 0.896 and 0.771 in the validation and external datasets, respectively. This model also accurately predicted the progression of renal function in patients over different follow-up periods after their initial assessment.

Conclusions

A prediction model that leverages routinely collected laboratory features in the Chinese population can accurately identify patients with CKD at high risk of progressing to kidney failure. An online version of the model can be easily and quickly applied in clinical management and treatment.

Assessment and Risk Prediction of Chronic Kidney Disease and Kidney Fibrosis Using Non-Invasive Biomarkers

Effective management of chronic kidney disease (CKD), a major health problem worldwide, requires accurate and timely diagnosis, prognosis of progression, assessment of therapeutic efficacy, and, ideally, prediction of drug response. Multiple biomarkers and algorithms for evaluating specific aspects of CKD have been proposed in the literature, many of which are based on a small number of samples. Based on the evidence presented in relevant studies, a comprehensive overview of the different biomarkers applicable for clinical implementation is lacking. This review aims to compile information on the non-invasive diagnostic, prognostic, and predictive biomarkers currently available for the management of CKD and provide guidance on the application of these biomarkers. We specifically focus on biomarkers that have demonstrated added value in prospective studies or those based on prospectively collected samples including at least 100 subjects. Published data demonstrate that several valid non-invasive biomarkers of potential value in the management of CKD are currently available.

Rosuvastatin as a Supplemental Treatment for the Clinical Symptoms of Nephropathia Epidemica: A Pilot Clinical Study

Nephropathis epidemica (NE), a mild form of hemorrhagic fever with renal syndrome (HFRS), is an acute zoonotic disease endemic in the Republic of Tatarstan. This study aimed to assess the impact of rosuvastatin on the clinical and laboratory results of NE. A total of 61 NE patients and 30 controls were included in this study; 22 NE patients and 7 controls received a daily dose of rosuvastatin (10 mg) for ten consecutive days. Serum samples were collected on days 1, 5, and 10 after admission to the hospital. These samples were analyzed to determine the levels of lipids, cytokines, and kidney toxicity markers. Our findings indicate that rosuvastatin reduced the duration of the second wave of fever and alleviated back pain and headache symptoms. Additionally, low-density lipoprotein cholesterol (LDL-C) serum levels were significantly decreased on days 5 and 10 upon rosuvastatin treatment. Furthermore, rosuvastatin decreased the levels of cytokines in the serum, particularly proinflammatory cytokines IL-1β and IL-8. NE patients had significantly altered levels of the kidney toxicity markers albumin and osteopontin. The data from our study provide evidence supporting the therapeutic potential of rosuvastatin in NE cases.

Identifying disease progression in chronic kidney disease using proton magnetic resonance spectroscopy

Chronic kidney disease (CKD) affects approximately 10% of the world population, higher still in some developing countries, and can cause irreversible kidney damage eventually leading to kidney failure requiring dialysis or kidney transplantation. However, not all patients with CKD will progress to this stage, and it is difficult to distinguish between progressors and non-progressors at the time of diagnosis. Current clinical practice involves monitoring estimated glomerular filtration rate and proteinuria to assess CKD trajectory over time; however, there remains a need for novel, validated methods that differentiate CKD progressors and non-progressors. Nuclear magnetic resonance techniques, including magnetic resonance spectroscopy and magnetic resonance imaging, have the potential to improve our understanding of CKD progression. Herein, we review the application of magnetic resonance spectroscopy both in preclinical and clinical settings to improve the diagnosis and surveillance of patients with CKD.

Tryptase in type I hypersensitivity

Tryptase is currently the main mast cell biomarker available in medical practice. Tryptase determination is a quantitative test performed in serum or plasma for the diagnosis, stratification, and follow-up of mast cell-related conditions. The continuous secretion of monomeric α and β protryptases forms the baseline tryptase level. Transient, activation-induced release of tryptase is known as acute tryptase. Because mast cells are tissue-resident cells, the detection of an acute tryptase release in the bloodstream is protracted, with a delay of 15 to 20 minutes after the onset of symptoms and a peak at approximately 1 hour. Constitutive release of tryptase is a marker of mast cell number and activity status, whereas transient release of mature tryptase is a marker of mast cell degranulation. Although consensual as a concept, the application of this statement in clinical practice has only been clarified since 2020. For baseline tryptase to be used as a biomarker, reference values need to be established. In contrast, defining a transient increase using acute tryptase can only be achieved as a function of the baseline status.

Metabolomics as a tool for the early diagnosis and prognosis of diabetic kidney disease

Diabetic kidney disease (DKD) is one of the most prevalent comorbidities of diabetes mellitus and the leading cause of the end-stage renal disease (ESRD). DKD results from chronic exposure to hyperglycemia, leading to progressive alterations in kidney structure and function. The early development of DKD is clinically silent and when albuminuria is detected the lesions are often at advanced stages, leading to rapid kidney function decline towards ESRD. DKD progression can be arrested or substantially delayed if detected and addressed at early stages. A major limitation of current methods is the absence of albuminuria in non-albuminuric phenotypes of diabetic nephropathy, which becomes increasingly prevalent and lacks focused therapy. Metabolomics is an ever-evolving omics technology that enables the study of metabolites, downstream products of every biochemical event that occurs in an organism. Metabolomics disclosures complex metabolic networks and provide knowledge of the very foundation of several physiological or pathophysiological processes, ultimately leading to the identification of diseases' unique metabolic signatures. In this sense, metabolomics is a promising tool not only for the diagnosis but also for the identification of pre-disease states which would confer a rapid and personalized clinical practice. Herein, the use of metabolomics as a tool to identify the DKD metabolic signature of tubule interstitial lesions to diagnose or predict the time-course of DKD will be discussed. In addition, the proficiency and limitations of the currently available high-throughput metabolomic techniques will be discussed.

Identification of kidney injury released circulating osteopontin as causal agent of respiratory failure

Tissue injury can drive secondary organ injury; however, mechanisms and mediators are not well understood. To identify interorgan cross-talk mediators, we used acute kidney injury (AKI)-induced acute lung injury (ALI) as a clinically important example. Using kidney and lung single-cell RNA sequencing after AKI in mice followed by ligand-receptor pairing analysis across organs, kidney ligands to lung receptors, we identify kidney-released circulating osteopontin (OPN) as a novel AKI-ALI mediator. OPN release from kidney tubule cells triggered lung endothelial leakage, inflammation, and respiratory failure. Pharmacological or genetic OPN inhibition prevented AKI-ALI. Transplantation of ischemic wt kidneys caused AKI-ALI, but not of ischemic OPN-global knockout kidneys, identifying kidney-released OPN as necessary interorgan signal to cause AKI-ALI. We show that OPN serum levels are elevated in patients with AKI and correlate with kidney injury. Our results demonstrate feasibility of using ligand-receptor analysis across organs to identify interorgan cross-talk mediators and may have important therapeutic implications in human AKI-ALI and multiorgan failure.

High-performance surface-enhanced Raman spectroscopy chip integrated with a micro-optical system for the rapid detection of creatinine in serum

To improve the sensitivity of disease biomarker detection, we proposed a high-performance surface-enhanced Raman spectroscopy (SERS) chip integrated with a micro-optical system (MOS). The MOS, which is based on the micro-reflecting cavity and the micro-lens, optimizes the optical matching characteristics of the SERS substrate and the Raman detection system, and greatly improves the SERS detection sensitivity by improving the collection efficiency of the Raman scattering signal. A uniform single layer of silver nanoparticles on a gold film was prepared as the SERS substrate using a liquid-liquid interface self-assembly method. The micro-reflecting cavity and micro-lens were prepared using micro-processing technology. The SERS chip was constructed based on the MOS and the Au film-based SERS substrate, and experimental results showed an EF of 1.46×10⁸, which is about 22.4 times higher than that of the Si-based SERS substrate. The chip was used for the detection of creatinine and the detection limit of creatinine in aqueous solution was 1 µM while the detection limit in serum was 5 µM. In addition, SERS testing was conducted on serum samples from normal people and patients with chronic renal impairment. Principal component analysis and linear discriminant analysis were used for modeling and identification, and the results showed a 90% accuracy of blind sample detection. These results demonstrate the value of this SERS chip for both research and practical applications in the fields of disease diagnosis and screening.

Self-assembled nano-Ag/Au@Au film composite SERS substrates show high uniformity and high enhancement factor for creatinine detection

Serum creatinine is a key biomarker for the diagnosis and monitoring of kidney disease. Rapid and sensitive creatinine detection is thus important. Here, we propose a high-performance nano-Ag/Au@Au film composite SERS substrate for the rapid detection of creatinine in human serum. Au nanoparticles (AuNPs) and Ag nanoparticles (AgNPs) with uniform particle size were synthesized by a chemical reduction method, and the nano-Ag/Au@Au film composite SERS substrate was successfully prepared via a consecutive layer-on-layer deposition using an optimized liquid-liquid interface self-assembly method. The finite element simulation analysis showed that due to the multi-dimensional plasmonic coupling effect formed between the AuNPs, AgNPs, and the Au film, the intensity of the local electromagnetic field was greatly improved, and a very high enhancement factor (EF) was obtained. Experimental results showed that the limit of detection (LOD) of this composite SERS substrate for rhodamine 6G (R6G) molecules was as low as 1 × 10^-13M, and the Raman EF was 15.7 and 2.9 times that of the AuNP and AgNP monolayer substrates respectively. The results of different batch tests and SERS mapping showed that the relative standard deviations of the Raman intensity of R6G at 612 cm^-1were 12.5% and 11.7%, respectively. Finally, we used the SERS substrate for the label-free detection of human serum creatinine. The results showed that the LOD of this SERS substrate for serum creatinine was 5 × 10^-6M with a linear correlation coefficient of 0.96. In conclusion, the SERS substrate has high sensitivity, good uniformity, simple preparation, and has important developmental potential for the rapid detection and application of disease biomarkers.

Healthcare Data for Achieving a More Personalized Treatment of Chronic Kidney Disease

The current concept of healthcare incites a more personalized treatment of diseases. To this aim, biomarkers are needed to improve decision-making facing chronic kidney disease (CKD) patients. Prognostic markers provided by real-world (observational) evidence are proposed in this Special Issue entitled "Biomarkers in Chronic Kidney Disease", with the intention to identify high-risk patients. These markers do not target measurable parameters in patients but clinical endpoints that may be in turn transformed to benefits under the effect of future interventions.