Development of a MALDI MS-based platform for early detection of acute kidney injury

Predictive models of sepsis-associated acute kidney injury based on machine learning: a scoping review

BACKGROUND

With the development of artificial intelligence, the application of machine learning to develop predictive models for sepsis-associated acute kidney injury has made potential breakthroughs in early identification, grading, diagnosis, and prognosis determination.

METHODS

Here, we conducted a systematic search of the PubMed, Cochrane Library, Embase (Ovid), Web of Science, and Scopus databases on April 28, 2023, and screened relevant literature. Then, we comprehensively extracted relevant data related to machine learning algorithms, predictors, and predicted objectives. We subsequently performed a critical evaluation of research quality, data aggregation, and analyses.

RESULTS

We screened 25 studies on predictive models for sepsis-associated acute kidney injury from a total of originally identified 2898 studies. The most commonly used machine learning algorithm is traditional logistic regression, followed by eXtreme gradient boosting. We categorized these predictive models into early identification models (60%), prognostic prediction models (32%), and subtype identification models (8%) according to their predictive purpose. The five most commonly used predictors were serum creatinine levels, lactate levels, age, blood urea nitrogen concentration, and diabetes mellitus. In addition, a single data source, insufficient assessment of clinical utility, lack of model bias assessment, and hyperparameter adjustment may be the main reasons for the low quality of the current research.

CONCLUSIONS

However, studies on the nondeath prognostic outcomes, the long-term clinical outcomes, and the subtype identification models are insufficient. Additionally, the poor quality of the research and the insufficient practicality of the model are problems that need to be addressed urgently.

Recent Advances of Proteomics in Management of Acute Kidney Injury

Acute Kidney Injury (AKI) is currently recognized as a life-threatening disease, leading to an exponential increase in morbidity and mortality worldwide. At present, AKI is characterized by a significant increase in serum creatinine (SCr) levels, typically followed by a sudden drop in glomerulus filtration rate (GFR). Changes in urine output are usually associated with the renal inability to excrete urea and other nitrogenous waste products, causing extracellular volume and electrolyte imbalances. Several molecular mechanisms were proposed to be affiliated with AKI development and progression, ultimately involving renal epithelium tubular cell-cycle arrest, inflammation, mitochondrial dysfunction, the inability to recover and regenerate proximal tubules, and impaired endothelial function. Diagnosis and prognosis using state-of-the-art clinical markers are often late and provide poor outcomes at disease onset. Inappropriate clinical assessment is a strong disease contributor, actively driving progression towards end stage renal disease (ESRD). Proteins, as the main functional and structural unit of the cell, provide the opportunity to monitor the disease on a molecular level. Changes in the proteomic profiles are pivotal for the expression of molecular pathways and disease pathogenesis. Introduction of highly-sensitive and innovative technology enabled the discovery of novel biomarkers for improved risk stratification, better and more cost-effective medical care for the ill patients and advanced personalized medicine. In line with those strategies, this review provides and discusses the latest findings of proteomic-based biomarkers and their prospective clinical application for AKI management.

MALDI mass Spectrometry based proteomics for drug discovery & development

Matrix-assisted laser desorption/ ionization (MALDI) is a soft ionization technique for introducing wide range of analytes into a mass spectrometer (MS). MALDI MS is a powerful tool in drug discovery research and development, providing a high-throughput molecular analysis technique in both preclinical and clinical systems. In particular, MALDI MS is invaluable in the study of peptides and proteins that drive all biological functions. This technology is label-free, provides high specificity in molecular identification, and is high-throughput. MALDI MS has been used in biomarker discovery and quantitation in virtually all tissues, serum, plasma, CSF, and urine for diagnostics, patient stratification, and monitoring drug efficacy. Other applications include characterization of biological drugs, spatial mapping of biomarkers and drugs in tissues, drug screening, and toxicological assessment.

The application of omic technologies to research in sepsis-associated acute kidney injury

Acute kidney injury (AKI) is common in critically ill children and adults, and sepsis-associated AKI (SA-AKI) is the most frequent cause of AKI in the ICU. To date, no mechanistically targeted therapeutic interventions have been identified. High-throughput "omic" technologies (e.g., genomics, proteomics, metabolomics, etc.) offer a new angle of approach to achieve this end. In this review, we provide an update on the current understanding of SA-AKI pathophysiology. Omic technologies themselves are briefly discussed to facilitate interpretation of studies using them. We next summarize the body of SA-AKI research to date that has employed omic technologies. Importantly, omic studies are helping to elucidate a pathophysiology of SA-AKI centered around cellular stress responses, metabolic changes, and dysregulation of energy production that underlie its clinical features. Finally, we propose opportunities for future research using clinically relevant animal models, integrating multiple omic technologies and ultimately progressing to translational human studies focusing therapeutic strategies on targeted disease mechanisms.

Value of Urine Peptides in Assessing Kidney and Cardiovascular Disease

Urinary peptides gained significant attention as potential biomarkers especially in the context of kidney and cardiovascular disease. In this manuscript the recent literature since 2015 on urinary peptide investigation in human kidney and cardiovascular disease is reviewed. The technology most commonly used in this context is capillary electrophoresis coupled mass spectrometry, in part owed to the large database available and the well-defined dataspace. Several studies based on over 1000 subjects are reported in the recent past, especially examining CKD273, a classifier for assessment of chronic kidney disease based on 273 urine peptides. Interestingly, the most abundant urinary peptides are generally collagen fragments, which may have gone undetected for some time as they are typically modified via proline hydroxylation. The data available suggest that urinary peptides specifically depict inflammation and fibrosis, and may serve as a non-invasive tool to assess fibrosis, which appears to be a key driver in kidney and cardiovascular disease. The recent successful completion of the first urinary peptide guided intervention trial, PRIORITY, is expected to further spur clinical application of urinary peptidomics, aiming especially at early detection of chronic diseases, prediction of progression, and prognosis of drug response.

New Approaches to Identify Sepsis Biomarkers: The Importance of Model and Sample Source for Mass Spectrometry

Septic shock is a systemic inflammatory response syndrome associated with circulatory failure leading to organ failure with a 40% mortality rate. Early diagnosis and prognosis of septic shock are necessary for specific and timely treatment. However, no predictive biomarker is available. In recent years, improvements in proteomics-based mass spectrometry have improved the detection of such biomarkers. This approach can be performed on different samples such as tissue or biological fluids. Working directly from human samples is complicated owing to interindividual variability. Indeed, patients are admitted at different stages of disease development and with signs of varying severity from one patient to another. All of these elements interfere with the identification of early, sensitive, and specific septic shock biomarkers. For these reasons, animal models of sepsis, although imperfect, are used to control the kinetics of the development of the pathology and to standardise experimentation, facilitating the identification of potential biomarkers. These elements underline the importance of the choice of animal model used and the sample to be studied during preclinical studies. The aim of this review is to discuss the relevance of different approaches to enable the identification of biomarkers that could indirectly be relevant to the clinical setting.

Urinary Peptidomic Biomarkers in Kidney Diseases

In order to effectively develop personalized medicine for kidney diseases we urgently need to develop highly accurate biomarkers for use in the clinic, since current biomarkers of kidney damage (changes in serum creatinine and/or urine albumin excretion) apply to a later stage of disease, lack accuracy, and are not connected with molecular pathophysiology. Analysis of urine peptide content (urinary peptidomics) has emerged as one of the most attractive areas in disease biomarker discovery. Urinary peptidome analysis allows the detection of short and long-term physiological or pathological changes occurring within the kidney. Urinary peptidomics has been applied extensively for several years now in renal patients, and may greatly improve kidney disease management by supporting earlier and more accurate detection, prognostic assessment, and prediction of response to treatment. It also promises better understanding of kidney disease pathophysiology, and has been proposed as a "liquid biopsy" to discriminate various types of renal disorders. Furthermore, proteins being the major drug targets, peptidome analysis may allow one to evaluate the effects of therapies at the protein signaling pathway level. We here review the most recent findings on urinary peptidomics in the setting of the most common kidney diseases.

Novel Urinary Biomarkers For Improved Prediction Of Progressive Egfr Loss In Early Chronic Kidney Disease Stages And In High Risk Individuals Without Chronic Kidney Disease

Chronic kidney disease is associated with increased risk of CKD progression and death. Therapeutic approaches to limit progression are limited. Developing tools for the early identification of those individuals most likely to progress will allow enriching clinical trials in high risk early CKD patients. The CKD273 classifier is a panel of 273 urinary peptides that enables early detection of CKD and prognosis of progression. We have generated urine capillary electrophoresis-mass spectrometry-based peptidomics CKD273 subclassifiers specific for CKD stages to allow the early identification of patients at high risk of CKD progression. In the validation cohort, the CKD273 subclassifiers outperformed albuminuria and CKD273 classifier for predicting rapid loss of eGFR in individuals with baseline eGFR > 60 ml/min/1.73 m². In individuals with eGFR > 60 ml/min/1.73 m² and albuminuria <30 mg/day, the CKD273 subclassifiers predicted rapid eGFR loss with AUC ranging from 0.797 (0.743-0.844) to 0.736 (0.689-0.780). The association between CKD273 subclassifiers and rapid progression remained significant after adjustment for age, sex, albuminuria, DM, baseline eGFR, and systolic blood pressure. Urinary peptidomics CKD273 subclassifiers outperformed albuminuria and CKD273 classifier for predicting the risk of rapid CKD progression in individuals with eGFR > 60 ml/min/1.73 m². These CKD273 subclassifiers represented the earliest evidence of rapidly progressive CKD in non-albuminuric individuals with preserved renal function.

Novel acute kidney injury biomarkers: their characteristics, utility and concerns

Acute kidney injury (AKI) consists of a rapid renal function decline which usually increases serum urea and creatinine levels. Since kidney injury begins by inducing biological and molecular changes which evolve to cellular damage, biomarkers could be used as tools for monitoring early AKI appearance, and predicting its recovery. Among the main AKI biomarkers the neutrophil gelatinase-associated lipocalin, cystatin C, kidney injury molecule-1, monocyte chemotactic peptide-1, N-acetyl-β-D-glucosaminidase, interleukin-18, liver-type fatty acid-binding protein, netrin-1, cycle arrest markers, endogenous ouabain, selenium-binding protein 1, and BPIFA2 marker, have been described. Even though novel biomarkers seem to be more helpful to early detect AKI and/or predict the need for renal replacement, and mortality compared to serum creatinine, more comprehensive studies are still required to determine their clinical utility.

Management of patients at risk of acute kidney injury

Acute kidney injury (AKI) is a multifaceted syndrome that occurs in different settings. The course of AKI can be variable, from single hit and complete recovery, to multiple hits resulting in end-stage renal disease. No interventions to improve outcomes of established AKI have yet been developed, so prevention and early diagnosis are key. Awareness campaigns and education for health-care professionals on diagnosis and management of AKI-with attention to avoidance of volume depletion, hypotension, and nephrotoxic interventions-coupled with electronic early warning systems where available can improve outcomes. Biomarker-based strategies have not shown improvements in outcome. Fluid management should aim for early, rapid restoration of circulatory volume, but should be more limited after the first 24-48 h to avoid volume overload. Use of balanced crystalloid solutions versus normal saline remains controversial. Renal replacement therapy should only be started on the basis of hard criteria, but should not be delayed when criteria are met. On the basis of recent evidence, the risk of contrast-induced AKI might be overestimated for many conditions.

Urinary neprilysin in the critically ill patient

Background

Critically ill patients in intensive care face hazardous conditions. Among these, acute kidney injury (AKI) is frequently seen as a result of sepsis. Early diagnosis of kidney injury is of the utmost importance in the guidance of interventions or avoidance of treatment-induced kidney injury. On these grounds, we searched for markers that could indicate proximal tubular cell injury.

Methods

Urine samples of 90 patients admitted to the intensive or intermediate care unit were collected over 2 to 5 days. The biomarker neprilysin (NEP) was investigated in urine using several methods such as dot blot, ELISA and immunofluorescence of urinary casts. Fifty-five healthy donors acted as controls.

Results

NEP was highly significantly elevated in the urine of patients who suffered AKI according to the KDIGO criteria in comparison to healthy controls. It was also found to be elevated in ICU patients without overt signs of AKI according to serum creatinine changes, however they were suffering from potential nephrotoxic insults. According to our findings, urinary NEP is indicative of epithelial cell alterations at the proximal tubule. This was elaborated in ICU patients when ghost fragments and NEP⁺ microvesicles were observed in urinary sediment cytopreparations. Furthermore, NEP⁺ immunofluorescence of healthy kidney tissue showed staining at the proximal tubules.

Conclusions

NEP, a potential marker for proximal tubular epithelia, can be measured in urine. This does not originate from leakage of elevated serum levels, but indicates proximal tubular cell alterations such as brush border severing, which can heal in most cases.