Precision Nephrology Is a Non-Negligible State of Mind in Clinical Research: Remember the Past to Face the Future

Artificial intelligence in chronic kidney diseases: methodology and potential applications

Chronic kidney disease (CKD) represents a significant global health challenge, characterized by kidney damage and decreased function. Its prevalence has steadily increased, necessitating a comprehensive understanding of its epidemiology, risk factors, and management strategies. While traditional prognostic markers such as estimated glomerular filtration rate (eGFR) and albuminuria provide valuable insights, they may not fully capture the complexity of CKD progression and associated cardiovascular (CV) risks.This paper reviews the current state of renal and CV risk prediction in CKD, highlighting the limitations of traditional models and the potential for integrating artificial intelligence (AI) techniques. AI, particularly machine learning (ML) and deep learning (DL), offers a promising avenue for enhancing risk prediction by analyzing vast and diverse patient data, including genetic markers, biomarkers, and imaging. By identifying intricate patterns and relationships within datasets, AI algorithms can generate more comprehensive risk profiles, enabling personalized and nuanced risk assessments.Despite its potential, the integration of AI into clinical practice faces challenges such as the opacity of some algorithms and concerns regarding data quality, privacy, and bias. Efforts towards explainable AI (XAI) and rigorous data governance are essential to ensure transparency, interpretability, and trustworthiness in AI-driven predictions.

Generalizability of kidney and cardiovascular protection by finerenone to the real world in Italy: insights from Fidelio and Figaro studies

BACKGROUND

We evaluated the proportion of Type 2 diabetes (T2D) patients with chronic kidney disease (CKD) participating in the AMD (Association of Medical Diabetologists) Annals initiative who met the eligibility criteria for phase III-studies on finerenone, showing its renal and cardiovascular benefits.

METHODS

This analysis involved all T2D patients seen in 2019 in 282 diabetes centers in Italy, for whom data on kidney function (estimated glomerular filtration rate and albuminuria) were available. Data are presented separately for different scenarios, covering the population with main eligibility criteria for inclusion in the FIDELIO-DKD and FIGARO-DKD trials.

RESULTS

Among 343,037 T2D patients involved in the analysis, 5.4% met the eligibility criteria of the FIDELIO-DKD study (13.3% if we consider the population with fundus data) and 22.3% met those of the FIGARO-DKD trial. Overall, 110,000 (33%) patients were eligible for treatment with finerenone, with a male prevalence, an average age of 71 years, and good control of the main risk factors (HbA1c 7.3%; BP 138/76 mmHg; LDL-c 87 mg/dl), albeit with large percentages of not well controlled patients (50% with SBP > 140 mmHg; > 30% with LDL-c > 100 mg/dl). Over 12% were on sodium/glucose cotransporter 2 inhibitors or glucagon-like peptide 1 receptor agonists. Based on the event rate from the FIDELITY pooled analysis, the number of potentially avoidable events was 21.7 per 1000 eligible patients for the cardiovascular composite outcome and 16.7 for the renal outcome.

CONCLUSIONS

This analysis showed that approximately 33% of patients with T2D present the main eligibility criteria for treatment with finerenone and could therefore benefit from it in the near future.

Omics Studies in CKD: Diagnostic Opportunities and Therapeutic Potential

Omics technologies have significantly advanced the prediction and therapeutic approaches for chronic kidney disease (CKD) by providing comprehensive molecular insights. This is a review of the current state and future prospects of integrating biomarkers into the clinical practice for CKD, aiming to improve patient outcomes by targeted therapeutic interventions. In fact, the integration of genomic, transcriptomic, proteomic, and metabolomic data has enhanced our understanding of CKD pathogenesis and identified novel biomarkers for an early diagnosis and targeted treatment. Advanced computational methods and artificial intelligence (AI) have further refined multi-omics data analysis, leading to more accurate prediction models for disease progression and therapeutic responses. These developments highlight the potential to improve CKD patient care with a precise and individualized treatment plan .

SGLT2 inhibitors and NLRP3 inflammasome: potential target in diabetic kidney disease

Diabetic kidney disease (DKD) remains the leading cause of chronic kidney disease (CKD) worldwide. The pathogenesis of DKD is influenced by functional, histopathological, and immune mechanisms, including NLRP3 inflammasome activity and oxidative stress. The sodium-glucose cotransporter 2 inhibitors (SGLT2i) have shown metabolic benefits and the ability to slow the progression of DKD in several clinical studies over the years. Recent studies suggest that the antidiabetic activity also extends to inhibition of the inflammatory response, including modulation of the NLRP3 inflammasome, reduction of pro-inflammatory markers and reduction of oxidative stress. Here we review the efficacy of SGLT2i in the treatment of CKD and discuss the role of the inflammatory response in the development of DKD, including its relationship to the NLRP3 inflammasome and oxidative stress.

Rationale and design of the Innsbruck Diabetic Kidney Disease Cohort (IDKDC)-a prospective study investigating etiology and progression of early-stage chronic kidney disease in type 2 diabetes

Background

The development of chronic kidney disease (CKD) in about 20%-40% of patients with type 2 diabetes (T2D) aggravates cardiovascular morbidity and mortality. Pathophysiology is of increasing relevance for individual management and prognosis, though it is largely unknown among T2D patients with CKD as histologic work-up is not routinely performed upon typical clinical presentation. However, as clinical parameters do not appropriately reflect underlying kidney pathology, reluctance regarding timely histologic assessment in T2D patients with CKD should be critically questioned. As the etiology of CKD in T2D is heterogeneous, we aim to assess the prevalence and clinical disease course of typical diabetic vs atypical/non-specific vs non-diabetic vs coexisting kidney pathologies among T2D patients with mild-to-moderate kidney impairment [KDIGO stage G3a/A1-3 or G2/A2-3; i.e. estimated glomerular filtration rate (eGFR) 59-45 mL/min irrespective of albuminuria or eGFR 89-60 mL/min and albuminuria >30 mg/g creatinine].

Methods

The Innsbruck Diabetic Kidney Disease Cohort (IDKDC) study aims to enroll at least 65 T2D patients with mild-to-moderate kidney impairment to undergo a diagnostic kidney biopsy. Six-monthly clinical follow-ups for up to 5 years will provide clinical and laboratory data to assess cardio-renal outcomes. Blood, urine and kidney tissue specimen will be biobanked to identify diagnostic and prognostic biomarkers.

Conclusions

While current risk assessment is primarily based on clinical parameters, our study will provide the scientific background for a potential change of the diagnostic standard towards routine kidney biopsy and clarify its role for individual risk prediction regarding cardio-renal outcome in T2D patients with mild-to-moderate kidney impairment.

Identifying subtypes of chronic kidney disease with machine learning: development, internal validation and prognostic validation using linked electronic health records in 350,067 individuals

BACKGROUND

Although chronic kidney disease (CKD) is associated with high multimorbidity, polypharmacy, morbidity and mortality, existing classification systems (mild to severe, usually based on estimated glomerular filtration rate, proteinuria or urine albumin-creatinine ratio) and risk prediction models largely ignore the complexity of CKD, its risk factors and its outcomes. Improved subtype definition could improve prediction of outcomes and inform effective interventions.

METHODS

We analysed individuals ≥18 years with incident and prevalent CKD (n = 350,067 and 195,422 respectively) from a population-based electronic health record resource (2006-2020; Clinical Practice Research Datalink, CPRD). We included factors (n = 264 with 2670 derived variables), e.g. demography, history, examination, blood laboratory values and medications. Using a published framework, we identified subtypes through seven unsupervised machine learning (ML) methods (K-means, Diana, HC, Fanny, PAM, Clara, Model-based) with 66 (of 2670) variables in each dataset. We evaluated subtypes for: (i) internal validity (within dataset, across methods); (ii) prognostic validity (predictive accuracy for 5-year all-cause mortality and admissions); and (iii) medications (new and existing by British National Formulary chapter).

FINDINGS

After identifying five clusters across seven approaches, we labelled CKD subtypes: 1. Early-onset, 2. Late-onset, 3. Cancer, 4. Metabolic, and 5. Cardiometabolic. Internal validity: We trained a high performing model (using XGBoost) that could predict disease subtypes with 95% accuracy for incident and prevalent CKD (Sensitivity: 0.81-0.98, F1 score:0.84-0.97). Prognostic validity: 5-year all-cause mortality, hospital admissions, and incidence of new chronic diseases differed across CKD subtypes. The 5-year risk of mortality and admissions in the overall incident CKD population were highest in cardiometabolic subtype: 43.3% (42.3-42.8%) and 29.5% (29.1-30.0%), respectively, and lowest in the early-onset subtype: 5.7% (5.5-5.9%) and 18.7% (18.4-19.1%).

MEDICATIONS

Across CKD subtypes, the distribution of prescription medication classes at baseline varied, with highest medication burden in cardiometabolic and metabolic subtypes, and higher burden in prevalent than incident CKD.

INTERPRETATION

In the largest CKD study using ML, to-date, we identified five distinct subtypes in individuals with incident and prevalent CKD. These subtypes have relevance to study of aetiology, therapeutics and risk prediction.

FUNDING

AstraZeneca UK Ltd, Health Data Research UK.

Harnessing the Full Potential of Multi-Omic Analyses to Advance the Study and Treatment of Chronic Kidney Disease

Chronic kidney disease (CKD) was the 12th leading cause of death globally in 2017 with the prevalence of CKD estimated at ~9%. Early detection and intervention for CKD may improve patient outcomes, but standard testing approaches even in developed countries do not facilitate identification of patients at high risk of developing CKD, nor those progressing to end-stage kidney disease (ESKD). Recent advances in CKD research are moving towards a more personalised approach for CKD. Heritability for CKD ranges from 30% to 75%, yet identified genetic risk factors account for only a small proportion of the inherited contribution to CKD. More in depth analysis of genomic sequencing data in large cohorts is revealing new genetic risk factors for common diagnoses of CKD and providing novel diagnoses for rare forms of CKD. Multi-omic approaches are now being harnessed to improve our understanding of CKD and explain some of the so-called 'missing heritability'. The most common omic analyses employed for CKD are genomics, epigenomics, transcriptomics, metabolomics, proteomics and phenomics. While each of these omics have been reviewed individually, considering integrated multi-omic analysis offers considerable scope to improve our understanding and treatment of CKD. This narrative review summarises current understanding of multi-omic research alongside recent experimental and analytical approaches, discusses current challenges and future perspectives, and offers new insights for CKD.

Precision Nephrology in Patients with Diabetes and Chronic Kidney Disease

Diabetes is the leading cause of kidney failure and specifically, diabetic kidney disease (DKD) occurs in up to 30% of all diabetic patients. Kidney disease attributed to diabetes is a major contributor to the global burden of the disease in terms of clinical and socio-economic impact, not only because of the risk of progression to End-Stage Kidney Disease (ESKD), but also because of the associated increase in cardiovascular (CV) risk. Despite the introduction of novel treatments that allow us to reduce the risk of future outcomes, a striking residual cardiorenal risk has been reported. This risk is explained by both the heterogeneity of DKD and the individual variability in response to nephroprotective treatments. Strategies that have been proposed to improve DKD patient care are to develop novel biomarkers that classify with greater accuracy patients with respect to their future risk (prognostic) and biomarkers that are able to predict the response to nephroprotective treatment (predictive). In this review, we summarize the principal prognostic biomarkers of type 1 and type 2 diabetes and the novel markers that help clinicians to individualize treatments and the basis of the characteristics that predict an optimal response.

OMICS in Chronic Kidney Disease: Focus on Prognosis and Prediction

Chronic kidney disease (CKD) patients are characterized by a high residual risk for cardiovascular (CV) events and CKD progression. This has prompted the implementation of new prognostic and predictive biomarkers with the aim of mitigating this risk. The ‘omics’ techniques, namely genomics, proteomics, metabolomics, and transcriptomics, are excellent candidates to provide a better understanding of pathophysiologic mechanisms of disease in CKD, to improve risk stratification of patients with respect to future cardiovascular events, and to identify CKD patients who are likely to respond to a treatment. Following such a strategy, a reliable risk of future events for a particular patient may be calculated and consequently the patient would also benefit from the best available treatment based on their risk profile. Moreover, a further step forward can be represented by the aggregation of multiple omics information by combining different techniques and/or different biological samples. This has already been shown to yield additional information by revealing with more accuracy the exact individual pathway of disease.

Hypoxia-Inducible Factor Stabilizers in End Stage Kidney Disease: "Can the Promise Be Kept?"

Anemia is a common complication of chronic kidney disease (CKD). The prevalence of anemia in CKD strongly increases as the estimated Glomerular Filtration Rate (eGFR) decreases. The pathophysiology of anemia in CKD is complex. The main causes are erythropoietin (EPO) deficiency and functional iron deficiency (FID). The administration of injectable preparations of recombinant erythropoiesis-stimulating agents (ESAs), especially epoetin and darbepoetin, coupled with oral or intravenous(iv) iron supplementation, is the current treatment for anemia in CKD for both dialysis and non-dialysis patients. This approach reduces patients' dependence on transfusion, ensuring the achievement of optimal hemoglobin target levels. However, there is still no evidence that treating anemia with ESAs can significantly reduce the risk of cardiovascular events. Meanwhile, iv iron supplementation causes an increased risk of allergic reactions, gastrointestinal side effects, infection, and cardiovascular events. Currently, there are no studies defining the best strategy for using ESAs to minimize possible risks. One class of agents under evaluation, known as prolyl hydroxylase inhibitors (PHIs), acts to stabilize hypoxia-inducible factor (HIF) by inhibiting prolyl hydroxylase (PH) enzymes. Several randomized controlled trials showed that HIF-PHIs are almost comparable to ESAs. In the era of personalized medicine, it is possible to envisage and investigate specific contexts of the application of HIF stabilizers based on the individual risk profile and mechanism of action.

Low performance of prognostic tools for predicting death before dialysis in older patients with advanced CKD

INTRODUCTION

Chronic kidney disease (CKD) is a disease which is spreading worldwide, especially among older patients. Several prognostic scores have been developed to predict death in older CKD patients, but they have not been validated. We aimed to evaluate the existing risk scores for predicting death before dialysis start, identified via an in-depth review, in a cohort of elderly patients with advanced CKD.

METHODS

We performed a review to identify scores predicting death, developed in and applicable to CKD patients. Each score was evaluated with an absolute risk calculation from the patients' baseline characteristics. We used a French prospective multicentre cohort of elderly patients (> 75 years) with advanced CKD [estimated glomerular filtration rate (eGFR) < 20 mL/min/1.73 m²], recruited from nephrological centres, with a 5-year follow-up. The outcome considered was death before initiating dialysis. Discrimination [area under curve (AUC)], calibration and Brier score were calculated for each score at its time frame.

RESULTS

Our review found 6 equations predicting death before dialysis in CKD patients. Four of these (GOLDFARB, BANSAL, GRAMS 2 and 4 years) were evaluated. The validation cohort (Parcours de Soins des Personnes Âgées Parcours de Soins des Personnes Âgées, PSPA) included 573 patients, with a median age of 82 years and a median eGFR of 13 mL/min/1.73 m². At the end of follow-up, 287 (50%) patients had started dialysis and 238 (41%) patients had died before dialysis. The four equations evaluated showed average discrimination (AUC 0.61-0.70) and, concerning calibration, a global overestimation of the risk of death.

DISCUSSION

The available scores predicting death before dialysis showed low performance among older patients with advanced CKD in a French multicentre cohort, indicating the need to upgrade them or develop new scores for this population.

The Impact of Chronic Kidney Disease on Peripheral Artery Disease and Peripheral Revascularization

Chronic kidney disease (CKD) is a clinical condition characterized by high morbidity and mortality. Globally, CKD is also increasing in prevalence and incidence. The two principal kidney measures namely estimated glomerular filtration rate (eGFR) and albuminuria have been found to be predictors of renal and cardiovascular (CV) endpoints including peripheral artery disease (PAD). The prevalence of PAD was increased in CKD patients and, particularly, in patients with more severe CKD stages. Despite the fact that revascularization strategies are suitable in CKD patients in similar fashion to non-CKD patients, few CKD patients underwent these procedures. In fact, if it is true that revascularization improves prognosis in PAD patients irrespective of baseline eGFR, it was also demonstrated that CKD patients, who underwent revascularization, were at higher risk for amputations, mortality, re-intervention and perioperative complications. With the present review article, we have examined the association between CKD, PAD and peripheral revascularization highlighting data about epidemiology, pathophysiologic mechanisms, and results from previous observational and intervention studies. We have also examined the future perspectives and challenges of research around the association between CKD and PAD.

Sodium-Glucose Co-transporter-2 Inhibitors and Nephroprotection in Diabetic Patients: More Than a Challenge

Diabetic nephropathy is the most common cause of end-stage renal disease worldwide. Control of blood glucose and blood pressure (BP) reduces the risk of developing this complication, but once diabetic nephropathy is established, it is then only possible to slow its progression. Sodium-glucose cotransporter-2 inhibitors (SGLT2is) are a novel class of oral hypoglycemic agents that increase urinary glucose excretion by suppressing glucose reabsorption at the renal proximal tubule. SGLT2is lower glycated hemoglobin (HbA1c) without increasing the risk of hypoglycemia, induce weight loss and improve various metabolic parameters including BP, lipid profile, albuminuria and uric acid. Several clinical trials have shown that SGLT2is (empagliflozin, dapagliflozin canagliflozin, and ertugliflozin) improve cardiovascular and renal outcomes and mortality in patients with type 2 diabetes. Effects of SGLT2is on the kidney can be explained by multiple pathways. SGLT2is may improve renal oxygenation and intra-renal inflammation thereby slowing the progression of kidney function decline. Additionally, SGLT2is are associated with a reduction in glomerular hyperfiltration, an effect which is mediated by the increase in natriuresis, the re-activation of tubule-glomerular feedback and independent of glycemic control. In this review, we will focus on renal results of major cardiovascular and renal outcome trials and we will describe direct and indirect mechanisms through which SGLT2is confer renal protection.

Risk prediction models for acute kidney injury in adults: An overview of systematic reviews

Background

The incidence of Acute Kidney Injury (AKI) and its human and economic cost is increasing steadily. One way to reduce the burden associated with AKI is to prevent the event altogether. An important step in prevention lies in AKI risk prediction. Due to the increasing number of available risk prediction models (RPMs) clinicians need to be able to rely on systematic reviews (SRs) to provide an objective assessment on which RPM can be used in a specific setting. Our aim was to assess the quality of SRs of RPMs in AKI.

Methods

The protocol for this overview was registered in PROSPERO. MEDLINE and Embase were searched for SRs of RPMs of AKI in any setting from 2003 till August 2020. We used the ROBIS tool to assess the methodological quality of the retrieved SRs.

Results

Eight SRs were retrieved. All studies were assessed as being at high risk for bias using the ROBIS tool. Eight reviews had a high risk of bias in study eligibility criteria (domain 1), five for study identification and selection (domain 2), seven for data collection and appraisal (domain 3) and seven for synthesis and findings (domain 4). Five reviews were scored at high risk of bias across all four domains. Risk of bias assessment with a formal risk of bias tool was only performed in five reviews. Primary studies were heterogeneous and used a wide range of AKI definitions. Only 19 unique RPM were externally validated, of which 11 had only 1 external validation report.

Conclusion

The methodological quality of SRs of RPMs of AKI is inconsistent. Most SRs lack a formal risk of bias assessment. SRs ought to adhere to certain standard quality criteria so that clinicians can rely on them to select a RPM for use in an individual patient.

Trial registration

PROSPERO registration number is CRD 42020204236, available at https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=204236.

Aortic Aneurysms, Chronic Kidney Disease and Metalloproteinases

Metalloproteinases (MPs) are proteolytic enzymes involved in extracellular matrix deposition, regulation of cellular signals of inflammation, proliferation, and apoptosis. Metalloproteinases are classified into three families: Matrix-MPs (MMPs), A-Disintegrin-and-Metalloprotease (ADAMs), and the A-Disintegrin-and-Metalloproteinase-with-Thrombospondin-1-like-Domains (ADAMTS). Previous studies showed that MPs are involved in the development of aortic aneurysms (AA) and, concomitantly, in the onset of chronic kidney disease (CKD). CKD has been, per se, associated with an increased risk for AA. The aim of this review is to examine the pathways that may associate MPs with CKD and AA. Several MMPs, such as MMP-2, -8, -9, and TIMP-1 have been shown to damage the AA wall and to have a toxic effect on renal tubular cells, leading to fibrosis. Similarly, ADAM10 and 17 have been shown to degrade collagen in the AA wall and to worsen kidney function via pro-inflammatory stimuli, the impairment of the Renin-Angiotensin-Aldosterone System, and the degradation of structural proteins. Moreover, MMP-2 and -9 inhibitors reduced aneurysm growth and albuminuria in experimental and human studies. It would be important, in the future, to expand research on MPs from both a prognostic, namely, to refine risk stratification in CKD patients, and a predictive perspective, likely to improve prognosis in response to targeted treatments.

Low performance of prognostic tools for predicting dialysis in elderly people with advanced CKD

INTRODUCTION

Clinical decision-making about care plans can be difficult for very elderly people with advanced chronic kidney disease (CKD). Current guidelines propose the use of prognostic tools predicting end stage renal disease (ESRD) to assist in a patient-centered shared decision-making approach. Our objective was to evaluate the existing risk model scores predicting ESRD, from data collected for a French prospective multicenter cohort of mainly octogenarians with advanced CKD.

METHODS

We performed a rapid review to identify the risk model scores predicting ESRD developed from CKD patient cohorts and evaluated them with data from a prospective multicenter French cohort of elderly (> 75 years) patients with advanced CKD (estimated glomerular filtration rate [eGFR] < 20 mL/min/1.75m²), followed up for 5 years. We evaluated these scores (in absolute risk) for discrimination, calibration and the Brier score. For scores using the same time frame, we made a joint calibration curve and compared areas under the curve (AUCs).

RESULTS

The PSPA cohort included 573 patients; their mean age was 83 years and their median eGFR was 13 mL/min/1.73 m². At the end of follow-up, 414 had died and 287 had started renal replacement therapy (RRT). Our rapid review found 12 scores that predicted renal replacement therapy. Five were evaluated: the TANGRI 4-variable, DRAWZ, MARKS, GRAMS, and LANDRAY scores. No score performed well in the PSPA cohort: AUCs ranged from 0.57 to 0.65, and Briers scores from 0.18 to 0.25.

CONCLUSIONS

The low predictiveness for ESRD of the scores tested in a cohort of octogenarian patients with advanced CKD underlines the need to develop new tools for this population.

Selective endothelin A receptor antagonism in patients with proteinuric chronic kidney disease

Introduction: Selective antagonists of Endothelin-1 receptors (ERA) have been tested in diabetic and nondiabetic chronic kidney disease (CKD). The SONAR trial (Study Of diabetic Nephropathy with AtRasentan) was the first randomized, phase 3, study assessing the long-term effect of ERA on CKD progression.Areas covered: We examine the ERA effects in proteinuric CKD. We discuss the results of the main clinical studies on ERA in CKD and offer an opinion on the findings of SONAR study and future perspectives in this field. We searched in PubMed and ISI Web of Science databases for including experimental and clinical studies that evaluated ERA in proteinuric CKD.Expert opinion: The SONAR study demonstrated that ERA confers protection against risk for CKD progression. This trial stimulated clinical research on ERA, to expand the therapeutic opportunities in CKD patients. Two novel phase 3 studies testing ERA in patients with glomerular disease are ongoing. Within the context of personalized medicine, we think it would be relevant to evaluate the effect of multiple treatments, including ERA, in proteinuric CKD patients. Testing ERA in clinical trials of novel design will also help at identifying the patients who would more benefit from these drugs.