Derivation and validation of a machine learning risk score using biomarker and electronic patient data to predict progression of diabetic kidney disease

A digital twin model incorporating generalized metabolic fluxes to identify and predict chronic kidney disease in type 2 diabetes mellitus

We have developed a digital twin-based CKD identification and prediction model that leverages generalized metabolic fluxes (GMF) for patients with Type 2 Diabetes Mellitus (T2DM). GMF digital twins utilized basic clinical and physiological biomarkers as inputs for identification and prediction of CKD. We employed four diverse multi-ethnic cohorts (n = 7072): a Singaporean cohort (EVAS, n = 289) and a North American cohort (NHANES, n = 1044) for baseline CKD identification, and two multi-center Singaporean cohorts (CDMD, n = 2119 and SDR, n = 3627) for 3-year CKD prediction and risk stratification. We subsequently conducted a comprehensive study utilizing a single dataset to evaluate the clinical utility of GMF for CKD prediction. The GMF-based identification model performed strongly, achieving an AUC between 0.80 and 0.82. In prediction, the GMF generated with complete parameters attained high performance with an AUC of 0.86, while with incomplete parameters, it achieved an AUC of 0.75. The GMF-based prediction model utilizing complete inputs is the standard implementation of our algorithm: HealthVector Diabetes®. We have established the GMF digital twin-based model as a robust clinical tool capable of predicting and stratifying the risk of future CKD within a 3-year time horizon. We report the correlation of GMF with basic input parameters, their ability to differentiate between future health states and medication status at baseline, and their capability to quantify CKD progression rates. This holistic methodology provides insights into patients' health states and CKD progression rates based on GMF metabolic profile differences, enabling personalized care plans.

Current knowledge about immunotherapy resistance for melanoma and potential predictive and prognostic biomarkers

Melanoma still reaches thousands of new diagnoses per year, and its aggressiveness makes recovery challenging, especially for those with stage III/IV unresectable melanoma. Immunotherapy, emerging as a beacon of hope, stands at the forefront of treatments for advanced melanoma. This review delves into the various immunotherapeutic strategies, prominently featuring cytokine immunotherapy, adoptive cell therapy, immune checkpoint inhibitors, and vaccinations. Among these, immune checkpoint inhibitors, notably anti-programmed cell death-1 (PD-1) and anti-cytotoxic T lymphocyte antigen-4 (CTLA-4) antibodies, emerge as the leading strategy. However, a significant subset of melanoma patients remains unresponsive to these inhibitors, underscoring the need for potent biomarkers. Efficient biomarkers have the potential to revolutionize the therapeutic landscape by facilitating the design of personalized treatments for patients with melanoma. This comprehensive review highlights the latest advancements in melanoma immunotherapy and potential biomarkers at the epicenter of recent research endeavors.

Investigating Machine Learning Techniques for Predicting Risk of Asthma Exacerbations: A Systematic Review

Asthma, a common chronic respiratory disease among children and adults, affects more than 200 million people worldwide and causes about 450,000 deaths each year. Machine learning is increasingly applied in healthcare to assist health practitioners in decision-making. In asthma management, machine learning excels in performing well-defined tasks, such as diagnosis, prediction, medication, and management. However, there remain uncertainties about how machine learning can be applied to predict asthma exacerbation. This study aimed to systematically review recent applications of machine learning techniques in predicting the risk of asthma attacks to assist asthma control and management. A total of 860 studies were initially identified from five databases. After the screening and full-text review, 20 studies were selected for inclusion in this review. The review considered recent studies published from January 2010 to February 2023. The 20 studies used machine learning techniques to support future asthma risk prediction by using various data sources such as clinical, medical, biological, and socio-demographic data sources, as well as environmental and meteorological data. While some studies considered prediction as a category, other studies predicted the probability of exacerbation. Only a group of studies applied prediction windows. The paper proposes a conceptual model to summarise how machine learning and available data sources can be leveraged to produce effective models for the early detection of asthma attacks. The review also generated a list of data sources that other researchers may use in similar work. Furthermore, we present opportunities for further research and the limitations of the preceding studies.

Leveraging Artificial Intelligence to Optimize the Care of Peripheral Artery Disease Patients

Peripheral artery disease is a major atherosclerotic disease that is associated with poor outcomes such as limb loss, cardiovascular morbidity, and death. Artificial intelligence (AI) has seen increasing integration in medicine, and its various applications can optimize the care of peripheral artery disease (PAD) patients in diagnosis, predicting patient outcomes, and imaging interpretation. In this review, we introduce various AI applications such as natural language processing, supervised machine learning, and deep learning, and we analyze the current literature in which these algorithms have been applied to PAD.

A novel electronic health record-based, machine-learning model to predict severe hypoglycemia leading to hospitalizations in older adults with diabetes: A territory-wide cohort and modeling study

BACKGROUND

Older adults with diabetes are at high risk of severe hypoglycemia (SH). Many machine-learning (ML) models predict short-term hypoglycemia are not specific for older adults and show poor precision-recall. We aimed to develop a multidimensional, electronic health record (EHR)-based ML model to predict one-year risk of SH requiring hospitalization in older adults with diabetes.

METHODS AND FINDINGS

We adopted a case-control design for a retrospective territory-wide cohort of 1,456,618 records from 364,863 unique older adults (age ≥65 years) with diabetes and at least 1 Hong Kong Hospital Authority attendance from 2013 to 2018. We used 258 predictors including demographics, admissions, diagnoses, medications, and routine laboratory tests in a one-year period to predict SH events requiring hospitalization in the following 12 months. The cohort was randomly split into training, testing, and internal validation sets in a 7:2:1 ratio. Six ML algorithms were evaluated including logistic-regression, random forest, gradient boost machine, deep neural network (DNN), XGBoost, and Rulefit. We tested our model in a temporal validation cohort in the Hong Kong Diabetes Register with predictors defined in 2018 and outcome events defined in 2019. Predictive performance was assessed using area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC) statistics, and positive predictive value (PPV). We identified 11,128 SH events requiring hospitalization during the observation periods. The XGBoost model yielded the best performance (AUROC = 0.978 [95% CI 0.972 to 0.984]; AUPRC = 0.670 [95% CI 0.652 to 0.688]; PPV = 0.721 [95% CI 0.703 to 0.739]). This was superior to an 11-variable conventional logistic-regression model comprised of age, sex, history of SH, hypertension, blood glucose, kidney function measurements, and use of oral glucose-lowering drugs (GLDs) (AUROC = 0.906; AUPRC = 0.085; PPV = 0.468). Top impactful predictors included non-use of lipid-regulating drugs, in-patient admission, urgent emergency triage, insulin use, and history of SH. External validation in the HKDR cohort yielded AUROC of 0.856 [95% CI 0.838 to 0.873]. Main limitations of this study included limited transportability of the model and lack of geographically independent validation.

CONCLUSIONS

Our novel-ML model demonstrated good discrimination and high precision in predicting one-year risk of SH requiring hospitalization. This may be integrated into EHR decision support systems for preemptive intervention in older adults at highest risk.

Validation of the Klinrisk chronic kidney disease progression model in the FIDELITY population

Background

Chronic kidney disease (CKD) affects >800 million individuals worldwide and is often underrecognized. Early detection, identification and treatment can delay disease progression. Klinrisk is a proprietary CKD progression risk prediction model based on common laboratory data to predict CKD progression. We aimed to externally validate the Klinrisk model for prediction of CKD progression in FIDELITY (a prespecified pooled analysis of two finerenone phase III trials in patients with CKD and type 2 diabetes). In addition, we sought to identify evidence of an interaction between treatment and risk.

Methods

The validation cohort included all participants in FIDELITY up to 4 years. The primary and secondary composite outcomes included a ≥40% decrease in estimated glomerular filtration rate (eGFR) or kidney failure, and a ≥57% decrease in eGFR or kidney failure. Prediction discrimination was calculated using area under the receiver operating characteristic curve (AUC). Calibration plots were calculated by decile comparing observed with predicted risk.

Results

At time horizons of 2 and 4 years, 993 and 1795 patients experienced a primary outcome event, respectively. The model predicted the primary outcome accurately with an AUC of 0.81 for 2 years and 0.86 for 4 years. Calibration was appropriate at both 2 and 4 years, with Brier scores of 0.067 and 0.115, respectively. No evidence of interaction between treatment and risk was identified for the primary composite outcome (P = .31).

Conclusions

Our findings demonstrate the accuracy and utility of a laboratory-based prediction model for early identification of patients at the highest risk of CKD progression.

Risk Prediction and Management of Chronic Kidney Disease in People Living with Type 2 Diabetes Mellitus

People with type 2 diabetes mellitus have increased risk of chronic kidney disease and atherosclerotic cardiovascular disease. Improved care delivery and implementation of guideline-directed medical therapy have contributed to the declining incidence of atherosclerotic cardiovascular disease in high-income countries. By contrast, the global incidence of chronic kidney disease and associated mortality is either plateaued or increased, leading to escalating direct and indirect medical costs. Given limited resources, better risk stratification approaches to identify people at risk of rapid progression to end-stage kidney disease can reduce therapeutic inertia, facilitate timely interventions and identify the need for early nephrologist referral. Among people with chronic kidney disease G3a and beyond, the kidney failure risk equations (KFRE) have been externally validated and outperformed other risk prediction models. The KFRE can also guide the timing of preparation for kidney replacement therapy with improved healthcare resources planning and may prevent multiple complications and premature mortality among people with chronic kidney disease with and without type 2 diabetes mellitus. The present review summarizes the evidence of KFRE to date and call for future research to validate and evaluate its impact on cardiovascular and mortality outcomes, as well as healthcare resource utilization in multiethnic populations and different healthcare settings.

Development and deployment of a nationwide predictive model for chronic kidney disease progression in diabetic patients

Aim

Chronic kidney disease (CKD) is a major complication of diabetes and a significant disease burden on the healthcare system. The aim of this work was to apply a predictive model to identify high-risk patients in the early stages of CKD as a means to provide early intervention to avert or delay kidney function deterioration.

Materials and methods

Using the data from the National Diabetes Database in Singapore, we applied a machine-learning algorithm to develop a predictive model for CKD progression in diabetic patients and to deploy the model nationwide.

Results

Our model was rigorously validated. It outperformed existing models and clinician predictions. The area under the receiver operating characteristic curve (AUC) of our model is 0.88, with the 95% confidence interval being 0.87 to 0.89. In recognition of its higher and consistent accuracy and clinical usefulness, our CKD model became the first clinical model deployed nationwide in Singapore and has been incorporated into a national program to engage patients in long-term care plans in battling chronic diseases. The risk score generated by the model stratifies patients into three risk levels, which are embedded into the Diabetes Patient Dashboard for clinicians and care managers who can then allocate healthcare resources accordingly.

Conclusion

This project provided a successful example of how an artificial intelligence (AI)-based model can be adopted to support clinical decision-making nationwide.

A Real-World Precision Medicine Program Including the KidneyIntelX Test Effectively Changes Management Decisions and Outcomes for Patients With Early-Stage Diabetic Kidney Disease

INTRODUCTION/OBJECTIVE

The KidneyIntelX is a multiplex, bioprognostic, immunoassay consisting of 3 plasma biomarkers and clinical variables that uses machine learning to predict a patient's risk for a progressive decline in kidney function over 5 years. We report the 1-year pre- and post-test clinical impact on care management, eGFR slope, and A1C along with engagement of population health clinical pharmacists and patient coordinators to promote a program of sustainable kidney, metabolic, and cardiac health.

METHODS

The KidneyIntelX in vitro prognostic test was previously validated for patients with type 2 diabetes and diabetic kidney disease (DKD) to predict kidney function decline within 5 years was introduced into the RWE study (NCT04802395) across the Health System as part of a population health chronic disease management program from [November 2020 to April 2023]. Pre- and post-test patients with a minimum of 12 months of follow-up post KidneyIntelX were assessed across all aspects of the program.

RESULTS

A total of 5348 patients with DKD had a KidneyIntelX assay. The median age was 68 years old, 52% were female, 27% self-identified as Black, and 89% had hypertension. The median baseline eGFR was 62 ml/min/1.73 m2, urine albumin-creatinine ratio was 54 mg/g, and A1C was 7.3%. The KidneyIntelX risk level was low in 49%, intermediate in 40%, and high in 11% of cases. New prescriptions for SGLT2i, GLP-1 RA, or referral to a specialist were noted in 19%, 33%, and 43% among low-, intermediate-, and high-risk patients, respectively. The median A1C decreased from 8.2% pre-test to 7.5% post-test in the high-risk group (P < .001). UACR levels in the intermediate-risk patients with albuminuria were reduced by 20%, and in a subgroup treated with new scripts for SGLT2i, UACR levels were lowered by approximately 50%. The median eGFR slope improved from -7.08 ml/min/1.73 m2/year to -4.27 ml/min/1.73 m2/year in high-risk patients (P = .0003), -2.65 to -1.04 in intermediate risk, and -3.26 ml/min/1.73 m2/year to +0.45 ml/min/1.73 m2/year in patients with low-risk (P < .001).

CONCLUSIONS

Deployment and risk stratification by KidneyIntelX was associated with an escalation in action taken to optimize cardio-kidney-metabolic health including medications and specialist referrals. Glycemic control and kidney function trajectories improved post-KidneyIntelX testing, with the greatest improvements observed in those scored as high-risk.

Machine learning prediction models for diabetic kidney disease: systematic review and meta-analysis

BACKGROUND

Machine learning is increasingly recognized as a viable approach for identifying risk factors associated with diabetic kidney disease (DKD). However, the current state of real-world research lacks a comprehensive systematic analysis of the predictive performance of machine learning (ML) models for DKD.

OBJECTIVES

The objectives of this study were to systematically summarize the predictive capabilities of various ML methods in forecasting the onset and the advancement of DKD, and to provide a basic outline for ML methods in DKD.

METHODS

We have searched mainstream databases, including PubMed, Web of Science, Embase, and MEDLINE databases to obtain the eligible studies. Subsequently, we categorized various ML techniques and analyzed the differences in their performance in predicting DKD.

RESULTS

Logistic regression (LR) was the prevailing ML method, yielding an overall pooled area under the receiver operating characteristic curve (AUROC) of 0.83. On the other hand, the non-LR models also performed well with an overall pooled AUROC of 0.80. Our t-tests showed no statistically significant difference in predicting ability between LR and non-LR models (t = 1.6767, p > 0.05).

CONCLUSION

All ML predicting models yielded relatively satisfied DKD predicting ability with their AUROCs greater than 0.7. However, we found no evidence that non-LR models outperformed the LR model. LR exhibits high performance or accuracy in practice, while it is known for algorithmic simplicity and computational efficiency compared to others. Thus, LR may be considered a cost-effective ML model in practice.

Revolutionizing clinical trials: the role of AI in accelerating medical breakthroughs

Clinical trials are the essential assessment for safe, reliable, and effective drug development. Data-related limitations, extensive manual efforts, remote patient monitoring, and the complexity of traditional clinical trials on patients drive the application of Artificial Intelligence (AI) in medical and healthcare organisations. For expeditious and streamlined clinical trials, a personalised AI solution is the best utilisation. AI provides broad utility options through structured, standardised, and digitally driven elements in medical research. The clinical trials are a time-consuming process with patient recruitment, enrolment, frequent monitoring, and medical adherence and retention. With an AI-powered tool, the automated data can be generated and managed for the trial lifecycle with all the records of the medical history of the patient as patient-centric AI. AI can intelligently interpret the data, feed downstream systems, and automatically fill out the required analysis report. This article explains how AI has revolutionised innovative ways of collecting data, biosimulation, and early disease diagnosis for clinical trials and overcomes the challenges more precisely through cost and time reduction, improved efficiency, and improved drug development research with less need for rework. The future implications of AI to accelerate clinical trials are important in medical research because of its fast output and overall utility.

Artificial intelligence: a new field of knowledge for nephrologists?

Artificial intelligence (AI) is a science that involves creating machines that can imitate human intelligence and learn. AI is ubiquitous in our daily lives, from search engines like Google to home assistants like Alexa and, more recently, OpenAI with its chatbot. AI can improve clinical care and research, but its use requires a solid understanding of its fundamentals, the promises and perils of algorithmic fairness, the barriers and solutions to its clinical implementation, and the pathways to developing an AI-competent workforce. The potential of AI in the field of nephrology is vast, particularly in the areas of diagnosis, treatment and prediction. One of the most significant advantages of AI is the ability to improve diagnostic accuracy. Machine learning algorithms can be trained to recognize patterns in patient data, including lab results, imaging and medical history, in order to identify early signs of kidney disease and thereby allow timely diagnoses and prompt initiation of treatment plans that can improve outcomes for patients. In short, AI holds the promise of advancing personalized medicine to new levels. While AI has tremendous potential, there are also significant challenges to its implementation, including data access and quality, data privacy and security, bias, trustworthiness, computing power, AI integration and legal issues. The European Commission's proposed regulatory framework for AI technology will play a significant role in ensuring the safe and ethical implementation of these technologies in the healthcare industry. Training nephrologists in the fundamentals of AI is imperative because traditionally, decision-making pertaining to the diagnosis, prognosis and treatment of renal patients has relied on ingrained practices, whereas AI serves as a powerful tool for swiftly and confidently synthesizing this information.

Derivation and independent validation of kidneyintelX.dkd: A prognostic test for the assessment of diabetic kidney disease progression

AIMS

To develop and validate an updated version of KidneyIntelX (kidneyintelX.dkd) to stratify patients for risk of progression of diabetic kidney disease (DKD) stages 1 to 3, to simplify the test for clinical adoption and support an application to the US Food and Drug Administration regulatory pathway.

METHODS

We used plasma biomarkers and clinical data from the Penn Medicine Biobank (PMBB) for training, and independent cohorts (BioMe and CANVAS) for validation. The primary outcome was progressive decline in kidney function (PDKF), defined by a ≥40% sustained decline in estimated glomerular filtration rate or end-stage kidney disease within 5 years of follow-up.

RESULTS

In 573 PMBB participants with DKD, 15.4% experienced PDKF over a median of 3.7 years. We trained a random forest model using biomarkers and clinical variables. Among 657 BioMe participants and 1197 CANVAS participants, 11.7% and 7.5%, respectively, experienced PDKF. Based on training cut-offs, 57%, 35% and 8% of BioMe participants, and 56%, 38% and 6% of CANVAS participants were classified as having low-, moderate- and high-risk levels, respectively. The cumulative incidence at these risk levels was 5.9%, 21.2% and 66.9% in BioMe and 6.7%, 13.1% and 59.6% in CANVAS. After clinical risk factor adjustment, the adjusted hazard ratios were 7.7 (95% confidence interval [CI] 3.0-19.6) and 3.7 (95% CI 2.0-6.8) in BioMe, and 5.4 (95% CI 2.5-11.9) and 2.3 (95% CI 1.4-3.9) in CANVAS, for high- versus low-risk and moderate- versus low-risk levels, respectively.

CONCLUSIONS

Using two independent cohorts and a clinical trial population, we validated an updated KidneyIntelX test (named kidneyintelX.dkd), which significantly enhanced risk stratification in patients with DKD for PDKF, independently from known risk factors for progression.

Circulating Activin A, Kidney Fibrosis, and Adverse Events

BACKGROUND

Identification of reliable biomarkers to assess kidney fibrosis severity is necessary for patients with CKD. Activin A, a member of the TGF- β superfamily, has been suggested as a biomarker for kidney fibrosis. However, its precise utility in this regard remains to be established.

METHODS

We investigated the correlation between plasma activin A levels, kidney fibrosis severity, and the incidence of major adverse kidney events in patients who underwent native kidney biopsies at a tertiary medical center. We performed RNA sequencing and histological analyses on kidney biopsy specimens to assess activin A expression. In vitro experiments were also conducted to explore the potential attenuation of TGF- β -induced fibroblast activation through activin A inhibition.

RESULTS

A total of 339 patients with biopsy-confirmed kidney diseases were enrolled. Baseline eGFR was 36 ml/min per 1.73 m 2 , and the urine protein/creatinine ratio was 2.9 mg/mg. Multivariable logistic regression analysis revealed a significant association between plasma activin A levels and the extent of tubulointerstitial fibrosis. Our RNA sequencing data demonstrated a positive correlation between kidney INHBA expression and plasma activin A levels. Furthermore, the histological analysis showed that myofibroblasts were the primary activin A-positive interstitial cells in diseased kidneys. During a median follow-up of 22 months, 113 participants experienced major adverse kidney events. Cox proportional hazards analysis initially found a positive association between plasma activin A levels and kidney event risk, but it became insignificant after adjusting for confounders. In cultured fibroblasts, knockdown of activin A significantly attenuated TGF- β -induced fibroblast-myofibroblast conversion.

CONCLUSIONS

Plasma activin A levels correlate with kidney fibrosis severity and adverse outcomes in various kidney disorders.

Self-supervised machine learning using adult inpatient data produces effective models for pediatric clinical prediction tasks

OBJECTIVE

Development of electronic health records (EHR)-based machine learning models for pediatric inpatients is challenged by limited training data. Self-supervised learning using adult data may be a promising approach to creating robust pediatric prediction models. The primary objective was to determine whether a self-supervised model trained in adult inpatients was noninferior to logistic regression models trained in pediatric inpatients, for pediatric inpatient clinical prediction tasks.

MATERIALS AND METHODS

This retrospective cohort study used EHR data and included patients with at least one admission to an inpatient unit. One admission per patient was randomly selected. Adult inpatients were 18 years or older while pediatric inpatients were more than 28 days and less than 18 years. Admissions were temporally split into training (January 1, 2008 to December 31, 2019), validation (January 1, 2020 to December 31, 2020), and test (January 1, 2021 to August 1, 2022) sets. Primary comparison was a self-supervised model trained in adult inpatients versus count-based logistic regression models trained in pediatric inpatients. Primary outcome was mean area-under-the-receiver-operating-characteristic-curve (AUROC) for 11 distinct clinical outcomes. Models were evaluated in pediatric inpatients.

RESULTS

When evaluated in pediatric inpatients, mean AUROC of self-supervised model trained in adult inpatients (0.902) was noninferior to count-based logistic regression models trained in pediatric inpatients (0.868) (mean difference = 0.034, 95% CI=0.014-0.057; P < .001 for noninferiority and P = .006 for superiority).

CONCLUSIONS

Self-supervised learning in adult inpatients was noninferior to logistic regression models trained in pediatric inpatients. This finding suggests transferability of self-supervised models trained in adult patients to pediatric patients, without requiring costly model retraining.

The automatic detection of diabetic kidney disease from retinal vascular parameters combined with clinical variables using artificial intelligence in type-2 diabetes patients

BACKGROUND

Diabetic kidney disease (DKD) has become the largest cause of end-stage kidney disease. Early and accurate detection of DKD is beneficial for patients. The present detection depends on the measurement of albuminuria or the estimated glomerular filtration rate, which is invasive and not optimal; therefore, new detection tools are urgently needed. Meanwhile, a close relationship between diabetic retinopathy and DKD has been reported; thus, we aimed to develop a novel detection algorithm for DKD using artificial intelligence technology based on retinal vascular parameters combined with several easily available clinical parameters in patients with type-2 diabetes.

METHODS

A total of 515 consecutive patients with type-2 diabetes mellitus from Xiangyang Central Hospital were included. Patients were stratified by DKD diagnosis and split randomly into either the training set (70%, N = 360) or the testing set (30%, N = 155) (random seed = 1). Data from the training set were used to develop the machine learning algorithm (MLA), while those from the testing set were used to validate the MLA. Model performances were evaluated.

RESULTS

The MLA using the random forest classifier presented optimal performance compared with other classifiers. When validated, the accuracy, sensitivity, specificity, F1 score, and AUC for the optimal model were 84.5%(95% CI 83.3-85.7), 84.5%(82.3-86.7), 84.5%(82.7-86.3), 0.845(0.831-0.859), and 0.914(0.903-0.925), respectively.

CONCLUSIONS

A new machine learning algorithm for DKD diagnosis based on fundus images and 8 easily available clinical parameters was developed, which indicated that retinal vascular changes can assist in DKD screening and detection.

Prognostic prediction of idiopathic membranous nephropathy using interpretable machine learning

BACKGROUND

Established prognostic models of idiopathic membranous nephropathy (IMN) were limited to traditional modeling methods and did not comprehensively consider clinical and pathological patient data. Based on the electronic medical record (EMR) system, machine learning (ML) was used to construct a risk prediction model for the prognosis of IMN.

METHODS

Data from 418 patients with IMN were diagnosed by renal biopsy at the Fifth Clinical Medical College of Shanxi Medical University. Fifty-nine medical features of the patients could be obtained from EMR, and prediction models were established based on five ML algorithms. The area under the curve, recall rate, accuracy, and F1 were used to evaluate and compare the performances of the models. Shapley additive explanation (SHAP) was used to explain the results of the best-performing model.

RESULTS

One hundred and seventeen patients (28.0%) with IMN experienced adverse events, 28 of them had compound outcomes (ESRD or double serum creatinine (SCr)), and 89 had relapsed. The gradient boosting machine (LightGBM) model had the best performance, with the highest AUC (0.892 ± 0.052, 95% CI 0.840-0.945), accuracy (0.909 ± 0.016), recall (0.741 ± 0.092), precision (0.906 ± 0.027), and F1 (0.905 ± 0.020). Recursive feature elimination with random forest and SHAP plots based on LightGBM showed that anti-phospholipase A2 receptor (anti-PLA2R), immunohistochemical immunoglobulin G4 (IHC IgG4), D-dimer (D-DIMER), triglyceride (TG), serum albumin (ALB), aspartate transaminase (AST), β2-microglobulin (BMG), SCr, and fasting plasma glucose (FPG) were important risk factors for the prognosis of IMN. Increased risk of adverse events in IMN patients was correlated with high anti-PLA2R and low IHC IgG4.

CONCLUSIONS

This study established a risk prediction model for the prognosis of IMN using ML based on clinical and pathological patient data. The LightGBM model may become a tool for personalized management of IMN patients.

Identification of endoplasmic reticulum stress-related biomarkers of diabetes nephropathy based on bioinformatics and machine learning

Backgrounds

Diabetes nephropathy (DN) is a growing public health concern worldwide. Renal dysfunction impairment in DN is intimately linked to ER stress and its related signaling pathways. Nonetheless, the underlying mechanism and biomarkers for this function of ER stress in the DN remain unknown.

Methods

Microarray datasets were retrieved from the Gene Expression Omnibus (GEO) database, and ER stress-related genes (ERSRGs) were downloaded from the MSigDB and GeneCards database. We identified hub ERSRGs for DN progression by intersecting ERSRGs with differentially expressed genes and significant genes in WGCNA, followed by a functional analysis. After analyzing hub ERSRGs with three machine learning techniques and taking the intersection, we did external validation as well as developed a DN diagnostic model based on the characteristic genes. Immune infiltration was performed using CIBERSORT. Moreover, patients with DN were then categorized using a consensus clustering approach. Eventually, the candidate ERSRGs-specific small-molecule compounds were defined by CMap.

Results

Several biological pathways driving pathological injury of DN and disordered levels of immune infiltration were revealed in the DN microarray datasets and strongly related to deregulated ERSRGs by bioinformatics multi-chip integration. Moreover, CDKN1B, EGR1, FKBP5, GDF15, and MARCKS were identified as ER stress signature genes associated with DN by machine learning algorithms, demonstrating their potential as DN biomarkers.

Conclusions

Our research sheds fresh light on the function of ER stress in DN pathophysiology and the development of early diagnostic and ER stress-related treatment targets in patients with DN.

CKD Progression Prediction in a Diverse US Population: A Machine-Learning Model

Rationale & Objective

Chronic kidney disease (CKD) is a major cause of morbidity and mortality. To date, there are no widely used machine-learning models that can predict progressive CKD across the entire disease spectrum, including the earliest stages. The objective of this study was to use readily available demographic and laboratory data from Sonic Healthcare USA laboratories to train and test the performance of machine learning-based predictive risk models for CKD progression.

Study Design

Retrospective observational study.

Setting & Participants

The study population was composed of deidentified laboratory information services data procured from a large US outpatient laboratory network. The retrospective data set included 110,264 adult patients over a 5-year period with initial estimated glomerular filtration rate (eGFR) values between 15-89 mL/min/1.73 m2.

Predictors

Patient demographic and laboratory characteristics.

Outcomes

Accelerated (ie, >30%) eGFR decline associated with CKD progression within 5 years.

Analytical Approach

Machine-learning models were developed using random forest survival methods, with laboratory-based risk factors analyzed as potential predictors of significant eGFR decline.

Results

The 7-variable risk classifier model accurately predicted an eGFR decline of >30% within 5 years and achieved an area under the curve receiver-operator characteristic of 0.85. The most important predictor of progressive decline in kidney function was the eGFR slope. Other key contributors to the model included initial eGFR, urine albumin-creatinine ratio, serum albumin (initial and slope), age, and sex.

Limitations

The cohort study did not evaluate the role of clinical variables (eg, blood pressure) on the performance of the model.

Conclusions

Our progressive CKD classifier accurately predicts significant eGFR decline in patients with early, mid, and advanced disease using readily obtainable laboratory data. Although prospective studies are warranted, our results support the clinical utility of the model to improve timely recognition and optimal management for patients at risk for CKD progression.

Plain-Language Summary

Defined by a significant decrease in estimated glomerular filtration rate (eGFR), chronic kidney disease (CKD) progression is strongly associated with kidney failure. However, to date, there are no broadly used resources that can predict this clinically significant event. Using machine-learning techniques on a diverse US population, this cohort study aimed to address this deficiency and found that a 5-year risk prediction model for CKD progression was accurate. The most important predictor of progressive decline in kidney function was the eGFR slope, followed by the urine albumin-creatinine ratio and serum albumin slope. Although further study is warranted, the results showed that a machine-learning model using readily obtainable laboratory information accurately predicts CKD progression, which may inform clinical diagnosis and management for this at-risk population.

Predictive role of serum C-peptide in new-onset renal dysfunction in type 2 diabetes: a longitudinal observational study

Background

Our previous cross-sectional study has demonstrated the independently non-linear relationship between fasting C-peptide with renal dysfunction odds in patients with type 2 diabetes (T2D) in China. This longitudinal observational study aims to explore the role of serum C-peptide in risk prediction of new-onset renal dysfunction, then construct a predictive model based on serum C-peptide and other clinical parameters.

Methods

The patients with T2D and normal renal function at baseline were recruited in this study. The LASSO algorithm was performed to filter potential predictors from the baseline variables. Logistic regression (LR) was performed to construct the predictive model for new-onset renal dysfunction risk. Power analysis was performed to assess the statistical power of the model.

Results

During a 2-year follow-up period, 21.08% (35/166) of subjects with T2D and normal renal function at baseline progressed to renal dysfunction. Six predictors were determined using LASSO regression, including baseline albumin-to-creatinine ratio, glycated hemoglobin, hypertension, retinol-binding protein-to-creatinine ratio, quartiles of fasting C-peptide, and quartiles of fasting C-peptide to 2h postprandial C-peptide ratio. These 6 predictors were incorporated to develop model for renal dysfunction risk prediction using LR. Finally, the LR model achieved a high efficiency, with an AUC of 0.83 (0.76 - 0.91), an accuracy of 75.80%, a sensitivity of 88.60%, and a specificity of 70.80%. According to the power analysis, the statistical power of the LR model was found to be 0.81, which was at a relatively high level. Finally, a nomogram was developed to make the model more available for individualized prediction in clinical practice.

Conclusion

Our results indicated that the baseline level of serum C-peptide had the potential role in the risk prediction of new-onset renal dysfunction. The LR model demonstrated high efficiency and had the potential to guide individualized risk assessments for renal dysfunction in clinical practice.

Predicting diabetic kidney disease for type 2 diabetes mellitus by machine learning in the real world: a multicenter retrospective study

Objective

Diabetic kidney disease (DKD) has been reported as a main microvascular complication of diabetes mellitus. Although renal biopsy is capable of distinguishing DKD from Non Diabetic kidney disease(NDKD), no gold standard has been validated to assess the development of DKD.This study aimed to build an auxiliary diagnosis model for type 2 Diabetic kidney disease (T2DKD) based on machine learning algorithms.

Methods

Clinical data on 3624 individuals with type 2 diabetes (T2DM) was gathered from January 1, 2019 to December 31, 2019 using a multi-center retrospective database. The data fell into a training set and a validation set at random at a ratio of 8:2. To identify critical clinical variables, the absolute shrinkage and selection operator with the lowest number was employed. Fifteen machine learning models were built to support the diagnosis of T2DKD, and the optimal model was selected in accordance with the area under the receiver operating characteristic curve (AUC) and accuracy. The model was improved with the use of Bayesian Optimization methods. The Shapley Additive explanations (SHAP) approach was used to illustrate prediction findings.

Results

DKD was diagnosed in 1856 (51.2 percent) of the 3624 individuals within the final cohort. As revealed by the SHAP findings, the Categorical Boosting (CatBoost) model achieved the optimal performance 1in the prediction of the risk of T2DKD, with an AUC of 0.86 based on the top 38 characteristics. The SHAP findings suggested that a simplified CatBoost model with an AUC of 0.84 was built in accordance with the top 12 characteristics. The more basic model features consisted of systolic blood pressure (SBP), creatinine (CREA), length of stay (LOS), thrombin time (TT), Age, prothrombin time (PT), platelet large cell ratio (P-LCR), albumin (ALB), glucose (GLU), fibrinogen (FIB-C), red blood cell distribution width-standard deviation (RDW-SD), as well as hemoglobin A1C(HbA1C).

Conclusion

A machine learning-based model for the prediction of the risk of developing T2DKD was built, and its effectiveness was verified. The CatBoost model can contribute to the diagnosis of T2DKD. Clinicians could gain more insights into the outcomes if the ML model is made interpretable.

Development and economic assessment of machine learning models to predict glycosylated hemoglobin in type 2 diabetes

Background: Glycosylated hemoglobin (HbA1c) is recommended for diagnosing and monitoring type 2 diabetes. However, the monitoring frequency in real-world applications has not yet reached the recommended frequency in the guidelines. Developing machine learning models to screen patients with poor glycemic control in patients with T2D could optimize management and decrease medical service costs. Methods: This study was carried out on patients with T2D who were examined for HbA1c at the Sichuan Provincial People's Hospital from April 2018 to December 2019. Characteristics were extracted from interviews and electronic medical records. The data (excluded FBG or included FBG) were randomly divided into a training dataset and a test dataset with a radio of 8:2 after data pre-processing. Four imputing methods, four screening methods, and six machine learning algorithms were used to optimize data and develop models. Models were compared on the basis of predictive performance metrics, especially on the model benefit (MB, a confusion matrix combined with economic burden associated with therapeutic inertia). The contributions of features were interpreted using SHapley Additive exPlanation (SHAP). Finally, we validated the sample size on the best model. Results: The study included 980 patients with T2D, of whom 513 (52.3%) were defined as positive (need to perform the HbA1c test). The results indicated that the model trained in the data (included FBG) presented better forecast performance than the models that excluded the FBG value. The best model used modified random forest as the imputation method, ElasticNet as the feature screening method, and the LightGBM algorithms and had the best performance. The MB, AUC, and AUPRC of the best model, among a total of 192 trained models, were 43475.750 (¥), 0.972, 0.944, and 0.974, respectively. The FBG values, previous HbA1c values, having a rational and reasonable diet, health status scores, type of manufacturers of metformin, interval of measurement, EQ-5D scores, occupational status, and age were the most significant contributors to the prediction model. Conclusion: We found that MB could be an indicator to evaluate the model prediction performance. The proposed model performed well in identifying patients with T2D who need to undergo the HbA1c test and could help improve individualized T2D management.

Current and Novel Biomarkers of Progression Risk in Children with Chronic Kidney Disease

BACKGROUND

Due to the complexity of chronic kidney disease (CKD) pathophysiology, biomarkers representing different mechanistic pathways have been targeted for the study and development of novel biomarkers. The discovery of clinically useful CKD biomarkers would allow for the identification of those children at the highest risk of kidney function decline for timely interventions and enrollment in clinical trials.

SUMMARY

Glomerular filtration rate and proteinuria are traditional biomarkers to classify and prognosticate CKD progression in clinical practice but have several limitations. Over the recent decades, novel biomarkers have been identified from blood or urine with metabolomic screening studies, proteomic screening studies, and an improved knowledge of CKD pathophysiology. This review highlights promising biomarkers associated with the progression of CKD that could potentially serve as future prognostic markers in children with CKD.

KEY MESSAGES

Further studies are needed in children with CKD to validate putative biomarkers, particularly candidate proteins and metabolites, for improving clinical management.

Recent updates in kidney risk prediction modeling: novel approaches and earlier outcomes

PURPOSE OF REVIEW

Recent years have witnessed the development of kidney risk prediction models which diverge from traditional model designs to incorporate novel approaches along with a focus on earlier outcomes. This review summarizes these recent advances, evaluates their pros and cons, and discusses their potential implications.

RECENT FINDINGS

Several kidney risk prediction models have recently been developed utilizing machine learning rather than traditional Cox regression. These models have demonstrated accurate prediction of kidney disease progression, often beyond that of traditional models, in both internal and external validation. On the opposite end of the spectrum, a simplified kidney risk prediction model was recently developed which minimized the need for laboratory data and instead relies primarily on self-reported data. While internal testing showed good overall predictive performance, the generalizability of this model remains uncertain. Finally, there is a growing trend toward prediction of earlier kidney outcomes (e.g., incident chronic kidney disease [CKD]) and away from a sole focus on kidney failure.

SUMMARY

Newer approaches and outcomes now being incorporated into kidney risk prediction modeling may enhance prediction and benefit a broader patient population. However, future work should address how best to implement these models into practice and assess their long-term clinical effectiveness.

A Primer in Precision Nephrology: Optimizing Outcomes in Kidney Health and Disease through Data-Driven Medicine

This year marks the 63rd anniversary of the International Society of Nephrology, which signaled nephrology's emergence as a modern medical discipline. In this article, we briefly trace the course of nephrology's history to show a clear arc in its evolution-of increasing resolution in nephrological data-an arc that is converging with computational capabilities to enable precision nephrology. In general, precision medicine refers to tailoring treatment to the individual characteristics of patients. For an operational definition, this tailoring takes the form of an optimization, in which treatments are selected to maximize a patient's expected health with respect to all available data. Because modern health data are large and high resolution, this optimization process requires computational intervention, and it must be tuned to the contours of specific medical disciplines. An advantage of this operational definition for precision medicine is that it allows us to better understand what precision medicine means in the context of a specific medical discipline. The goal of this article was to demonstrate how to instantiate this definition of precision medicine for the field of nephrology. Correspondingly, the goal of precision nephrology was to answer two related questions: ( 1 ) How do we optimize kidney health with respect to all available data? and ( 2 ) How do we optimize general health with respect to kidney data?

Different roles of protein biomarkers predicting eGFR trajectories in people with chronic kidney disease and diabetes mellitus: a nationwide retrospective cohort study

BACKGROUND

Chronic kidney disease (CKD) is a common comorbidity in people with diabetes mellitus, and a key risk factor for further life-threatening conditions such as cardiovascular disease. The early prediction of progression of CKD therefore is an important clinical goal, but remains difficult due to the multifaceted nature of the condition. We validated a set of established protein biomarkers for the prediction of trajectories of estimated glomerular filtration rate (eGFR) in people with moderately advanced chronic kidney disease and diabetes mellitus. Our aim was to discern which biomarkers associate with baseline eGFR or are important for the prediction of the future eGFR trajectory.

METHODS

We used Bayesian linear mixed models with weakly informative and shrinkage priors for clinical predictors (n = 12) and protein biomarkers (n = 19) to model eGFR trajectories in a retrospective cohort study of people with diabetes mellitus (n = 838) from the nationwide German Chronic Kidney Disease study. We used baseline eGFR to update the models' predictions, thereby assessing the importance of the predictors and improving predictive accuracy computed using repeated cross-validation.

RESULTS

The model combining clinical and protein predictors had higher predictive performance than a clinical only model, with an [Formula: see text] of 0.44 (95% credible interval 0.37-0.50) before, and 0.59 (95% credible interval 0.51-0.65) after updating by baseline eGFR, respectively. Only few predictors were sufficient to obtain comparable performance to the main model, with markers such as Tumor Necrosis Factor Receptor 1 and Receptor for Advanced Glycation Endproducts being associated with baseline eGFR, while Kidney Injury Molecule 1 and urine albumin-creatinine-ratio were predictive for future eGFR decline.

CONCLUSIONS

Protein biomarkers only modestly improve predictive accuracy compared to clinical predictors alone. The different protein markers serve different roles for the prediction of longitudinal eGFR trajectories potentially reflecting their role in the disease pathway.

Artificial Intelligence Applications in Clinical Chemistry

Artificial intelligence (AI) applications are an area of active investigation in clinical chemistry. Numerous publications have demonstrated the promise of AI across all phases of testing including preanalytic, analytic, and postanalytic phases; this includes novel methods for detecting common specimen collection errors, predicting laboratory results and diagnoses, and enhancing autoverification workflows. Although AI applications pose several ethical and operational challenges, these technologies are expected to transform the practice of the clinical chemistry laboratory in the near future.

Analysis of clinical predictors of kidney diseases in type 2 diabetes patients based on machine learning

BACKGROUND

The heterogeneity of Type 2 Diabetes Mellitus (T2DM) complicated with renal diseases has not been fully understood in clinical practice. The purpose of the study was to propose potential predictive factors to identify diabetic kidney disease (DKD), nondiabetic kidney disease (NDKD), and DKD superimposed on NDKD (DKD + NDKD) in T2DM patients noninvasively and accurately.

METHODS

Two hundred forty-one eligible patients confirmed by renal biopsy were enrolled in this retrospective, analytical study. The features composed of clinical and biochemical data prior to renal biopsy were extracted from patients' electronic medical records. Machine learning algorithms were used to distinguish among different kidney diseases pairwise. Feature variables selected in the developed model were evaluated.

RESULTS

Logistic regression model achieved an accuracy of 0.8306 ± 0.0057 for DKD and NDKD classification. Hematocrit, diabetic retinopathy (DR), hematuria, platelet distribution width and history of hypertension were identified as important risk factors. Then SVM model allowed us to differentiate NDKD from DKD + NDKD with accuracy 0.8686 ± 0.052 where hematuria, diabetes duration, international normalized ratio (INR), D-Dimer, high-density lipoprotein cholesterol were the top risk factors. Finally, the logistic regression model indicated that DD-dimer, hematuria, INR, systolic pressure, DR were likely to be predictive factors to identify DKD with DKD + NDKD.

CONCLUSION

Predictive factors were successfully identified among different renal diseases in type 2 diabetes patients via machine learning methods. More attention should be paid on the coagulation factors in the DKD + NDKD patients, which might indicate a hypercoagulable state and an increased risk of thrombosis.

Development and validation of a risk score for diabetic kidney disease prediction in type 2 diabetes patients: a machine learning approach

PURPOSE

This study aims to develop and validate a risk score to predict the occurrence of DKD in individuals with type 2 diabetes using a machine learning (ML) approach.

METHODS

By implementing Recursive Feature Elimination with Cross-Validation (RFECV) and RFE on the Diabetes Clinic of Imam Khomeini Hospital Complex (IKHC) dataset, the most critical features were identified. These features were used in the multivariate logistic regression (LR) analysis, and the discrimination and calibration of the model were evaluated. Finally, external validation of the model was assessed.

RESULTS

The development dataset included 1907 type 2 diabetic patients, 763 of whom developed DKD over 5 years. The predictive model performed well in the development dataset by implementing RFECV with the RF algorithm and considering six features (AUC: 79%). Using these features, the LR-based risk score indicated appropriate discrimination (AUC: 75.5%, 95% CI 73-78%) and acceptable calibration ([Formula: see text]= 7.44; p value = 0.49). This risk score was then used for 1543 diabetic patients in the validation dataset, including 633 patients with DKD over 5 years. The results showed sufficient discrimination (AUC: 75.8%, 95% CI 73-78%) of the risk score in the validation dataset.

CONCLUSIONS

We developed and validated a new risk score for predicting DKD via ML approach, which used common features in the periodic screening of type 2 diabetic patients that are readily available. In addition, a web-based online tool that is readily available to the public was developed to calculate the DKD risk score.

Federated Learning in Health care Using Structured Medical Data

The success of machine learning-based studies is largely subjected to accessing a large amount of data. However, accessing such data is typically not feasible within a single health system/hospital. Although multicenter studies are the most effective way to access a vast amount of data, sharing data outside the institutes involves legal, business, and technical challenges. Federated learning (FL) is a newly proposed machine learning framework for multicenter studies, tackling data-sharing issues across participant institutes. The promise of FL is simple. FL facilitates multicenter studies without losing data access control and allows the construction of a global model by aggregating local models trained from participant institutes. This article reviewed recently published studies that utilized FL in clinical studies with structured medical data. In addition, challenges and open questions in FL in clinical studies with structured medical data were discussed.

Artificial Intelligence in Pediatric Nephrology-A Call for Action

Artificial intelligence is playing an increasingly important role in many fields of clinical care to assist health care providers in patient management. In adult-focused nephrology, artificial intelligence is beginning to be used to improve clinical care, hemodialysis prescriptions, and follow-up of transplant recipients. This article provides an overview of medical artificial intelligence applications relevant to pediatric nephrology. We describe the core concepts of artificial intelligence and machine learning and cover the basics of neural networks and deep learning. We also discuss some examples for clinical applications of artificial intelligence in pediatric nephrology, including neonatal kidney function, early recognition of acute kidney injury, renally cleared drug dosing, intrapatient variability, urinary tract infection workup in infancy, and longitudinal disease progression. Furthermore, we consider the future of artificial intelligence in clinical pediatric nephrology and its potential impact on medical practice and address the ethical issues artificial intelligence raises in terms of clinical decision-making, health care provider-patient relationship, patient privacy, and data collection. This article also represents a call for action involving those of us striving to provide optimal services for children, adolescents, and young adults with chronic conditions.

Non-linear association of fasting C-peptide and uric acid levels with renal dysfunction based on restricted cubic spline in patients with type 2 diabetes: A real-world study

BACKGROUND

Previous studies had showed divergent findings on the associations of C-peptide and/or uric acid (UA) with renal dysfunction odds in patients with type 2 diabetes mellitus (T2DM). We hypothesized that there were non-linear relationships between C-peptide, UA and renal dysfunction odds. This study aimed to further investigate the relationships of different stratification of C-peptide and UA with renal dysfunction in patients with T2DM.

METHOD

We conducted a cross-sectional real-world observational study of 411 patients with T2DM. The levels of fasting C-peptide, 2h postprandial C-peptide, the ratio of fasting C-peptide to 2h postprandial C-peptide (C0/C2 ratio), UA and other characteristics were recorded. Restricted cubic spline (RCS) curves was performed to evaluated the associations of stratified C-peptide and UA with renal dysfunction odds.

RESULTS

Fasting C-peptide, C0/C2 ratio and UA were independently and significantly associated with renal dysfunction in patients with T2DM as assessed by multivariate analyses (p < 0.05). In especial, non-linear relationships with threshold effects were observed among fasting C-peptide, UA and renal dysfunction according to RCS analyses. Compared with patients with 0.28 ≤ fasting C-peptide ≤ 0.56 nmol/L, patients with fasting C-peptide < 0.28 nmol/L (OR = 1.38, p = 0.246) or fasting C-peptide > 0.56 nmol/L (OR = 1.85, p = 0.021) had relatively higher renal dysfunction odds after adjusting for confounding factors. Similarly, compared with patients with 276 ≤ UA ≤ 409 μmol/L, patients with UA < 276 μmol/L (OR = 1.32, p = 0.262) or UA > 409 μmol/L (OR = 6.24, p < 0.001) had relatively higher odds of renal dysfunction.

CONCLUSION

The renal dysfunction odds in patients with T2DM was non-linearly associated with the levels of serum fasting C-peptide and UA. Fasting C-peptide and UA might have the potential role in odds stratification of renal dysfunction.

Artificial Intelligence for Predicting and Diagnosing Complications of Diabetes

Artificial intelligence can use real-world data to create models capable of making predictions and medical diagnosis for diabetes and its complications. The aim of this commentary article is to provide a general perspective and present recent advances on how artificial intelligence can be applied to improve the prediction and diagnosis of six significant complications of diabetes including (1) gestational diabetes, (2) hypoglycemia in the hospital, (3) diabetic retinopathy, (4) diabetic foot ulcers, (5) diabetic peripheral neuropathy, and (6) diabetic nephropathy.

Pre-operative kidney biomarkers and risks for death, cardiovascular and chronic kidney disease events after cardiac surgery: the TRIBE-AKI study

BACKGROUND

Soluble tumor necrosis factor receptor (sTNFR)1, sTNFR2, and plasma kidney injury molecule-1 (KIM-1) are associated with kidney events in patients with and without diabetes. However, their associations with clinical outcomes when obtained pre-operatively have not been explored.

METHODS

The TRIBE-AKI cohort study is a prospective, multicenter, cohort study of high-risk adults undergoing cardiac surgery. We assessed the associations between pre-operative concentrations of plasma sTNFR1, sTNFR2, and KIM-1 and post-operative long-term outcomes including mortality, cardiovascular events, and chronic kidney disease (CKD) incidence or progression after discharge.

RESULTS

Among 1378 participants included in the analysis with a median follow-up period of 6.7 (IQR 4.0-7.9) years, 434 (31%) patients died, 256 (19%) experienced cardiovascular events and out of 837 with available long-term kidney function data, 30% developed CKD. After adjustment for clinical covariates, each log increase in biomarker concentration was independently associated with mortality with 95% CI adjusted hazard ratios (aHRs) of 3.0 (2.3-4.0), 2.3 (1.8-2.9), and 2.0 (1.6-2.4) for sTNFR1, sTNFR2, and KIM-1, respectively. For cardiovascular events, the 95% CI aHRs were 2.1 (1.5-3.1), 1.9 (1.4-2.6) and 1.6 (1.2-2.1) for sTNFR1, sTNFR2 and KIM-1, respectively. For CKD events, the aHRs were 2.2 (1.5-3.1) for sTNFR1, 1.9 (1.3-2.7) for sTNFR2, and 1.7 (1.3-2.3) for KIM-1. Despite the associations, each of the biomarkers alone or in combination failed to result in robust discrimination on an absolute basis or compared to a clinical model.

CONCLUSION

sTNFR1, sTNFR2, and KIM-1 were independently associated with longitudinal outcomes after discharge from a cardiac surgery hospitalization including death, cardiovascular, and CKD events when obtained pre-operatively in high-risk individuals. Pre-operative plasma biomarkers could serve to assist during the evaluation of patients in whom cardiac surgery is planned.

Machine learning models for prediction of HF and CKD development in early-stage type 2 diabetes patients

Chronic kidney disease (CKD) and heart failure (HF) are the first and most frequent comorbidities associated with mortality risks in early-stage type 2 diabetes mellitus (T2DM). However, efficient screening and risk assessment strategies for identifying T2DM patients at high risk of developing CKD and/or HF (CKD/HF) remains to be established. This study aimed to generate a novel machine learning (ML) model to predict the risk of developing CKD/HF in early-stage T2DM patients. The models were derived from a retrospective cohort of 217,054 T2DM patients without a history of cardiovascular and renal diseases extracted from a Japanese claims database. Among algorithms used for the ML, extreme gradient boosting exhibited the best performance for CKD/HF diagnosis and hospitalization after internal validation and was further validated using another dataset including 16,822 patients. In the external validation, 5-years prediction area under the receiver operating characteristic curves for CKD/HF diagnosis and hospitalization were 0.718 and 0.837, respectively. In Kaplan-Meier curves analysis, patients predicted to be at high risk showed significant increase in CKD/HF diagnosis and hospitalization compared with those at low risk. Thus, the developed model predicted the risk of developing CKD/HF in T2DM patients with reasonable probability in the external validation cohort. Clinical approach identifying T2DM at high risk of developing CKD/HF using ML models may contribute to improved prognosis by promoting early diagnosis and intervention.

Real World Evidence and Clinical Utility of KidneyIntelX on Patients With Early-Stage Diabetic Kidney Disease: Interim Results on Decision Impact and Outcomes

INTRODUCTION AND OBJECTIVE

The lack of precision to identify patients with early-stage diabetic kidney disease (DKD) at near-term risk for progressive decline in kidney function results in poor disease management often leading to kidney failure requiring unplanned dialysis. The KidneyIntelX is a multiplex, bioprognostic, immunoassay consisting of 3 plasma biomarkers and clinical variables that uses machine learning to generate a risk score for progressive decline in kidney function over 5-year in adults with early-stage DKD. Our objective was to assess the impact of KidneyIntelX on management and outcomes in a Health System in the real-world evidence (RWE) study.

METHODS

KidneyIntelX was introduced into a large metropolitan Health System via a population health-defined approved care pathway for patients with stages 1 to 3 DKD between [November 2020 to March 2022]. Decision impact on visit frequency, medication management, specialist referral, and selected lab values was assessed. We performed an interim analysis in patients through 6-months post-test date to evaluate the impact of risk level with clinical decision-making and outcomes.

RESULTS

A total of 1686 patients were enrolled in the RWE study and underwent KidneyIntelX testing and subsequent care pathway management. The median age was 68 years, 52% were female, 26% self-identified as Black, and 94% had hypertension. The median baseline eGFR was 59 ml/minute/1.73 m², urine albumin-creatinine ratio was 69 mg/g, and HbA1c was 7.7%. After testing, a clinical encounter in the first month occurred in 13%, 43%, and 53% of low-risk, intermediate-risk, and high-risk patients, respectively and 46%, 61%, and 71% had at least 1 action taken within the first 6 months. High-risk patients were more likely to be placed on SGLT2 inhibitors (OR = 4.56; 95% CI 3.00-6.91 vs low-risk), and more likely to be referred to a specialist such as a nephrologist, endocrinologist, or dietician (OR = 2.49; 95% CI 1.53-4.01) compared to low-risk patients.

CONCLUSIONS

The combination of KidneyIntelX, clinical guidelines and educational support resulted in changes in clinical management by clinicians. After testing, there was an increase in visit frequency, referrals for disease management, and introduction to guideline-recommended medications. These differed by risk category, indicating an impact of KidneyIntelX risk stratification on clinical care.

A Post Hoc Analysis of KidneyIntelX and Cardiorenal Outcomes in Diabetic Kidney Disease

KidneyIntelX, a bioprognostic test for assessing risk of CKD progression, risk stratified individuals for kidney, heart failure, and death outcomes in the Canagliflozin Cardiovascular Assessment Study.Individuals scored as high risk seemed to derive more of benefit from treatment with canagliflozin versus placebo.These findings may serve to increase adoption of underutilized therapies for cardiorenal risk reduction in patients with diabetic kidney disease.

Potential progression biomarkers of diabetic kidney disease determined using comprehensive machine learning analysis of non-targeted metabolomics

Diabetic kidney disease is the main cause of end-stage renal disease worldwide. The prediction of the clinical course of patients with diabetic kidney disease remains difficult, despite the identification of potential biomarkers; therefore, novel biomarkers are needed to predict the progression of the disease. We conducted non-targeted metabolomics using plasma and urine of patients with diabetic kidney disease whose estimated glomerular filtration rate was between 30 and 60 mL/min/1.73 m². We analyzed how the estimated glomerular filtration rate changed over time (up to 30 months) to detect rapid decliners of kidney function. Conventional logistic analysis suggested that only one metabolite, urinary 1-methylpyridin-1-ium (NMP), was a promising biomarker. We then applied a deep learning method to identify potential biomarkers and physiological parameters to predict the progression of diabetic kidney disease in an explainable manner. We narrowed down 3388 variables to 50 using the deep learning method and conducted two regression models, piecewise linear and handcrafted linear regression, both of which examined the utility of biomarker combinations. Our analysis, based on the deep learning method, identified systolic blood pressure and urinary albumin-to-creatinine ratio, six identified metabolites, and three unidentified metabolites including urinary NMP, as potential biomarkers. This research suggests that the machine learning method can detect potential biomarkers that could otherwise escape identification using the conventional statistical method.

Exfoliated Kidney Cells from Urine for Early Diagnosis and Prognostication of CKD: The Way of the Future?

Chronic kidney disease (CKD) is a global health issue, affecting more than 10% of the worldwide population. The current approach for formal diagnosis and prognostication of CKD typically relies on non-invasive serum and urine biomarkers such as serum creatinine and albuminuria. However, histological evidence of tubulointerstitial fibrosis is the 'gold standard' marker of the likelihood of disease progression. The development of novel biomedical technologies to evaluate exfoliated kidney cells from urine for non-invasive diagnosis and prognostication of CKD presents opportunities to avoid kidney biopsy for the purpose of prognostication. Efforts to apply these technologies more widely in clinical practice are encouraged, given their potential as a cost-effective approach, and no risk of post-biopsy complications such as bleeding, pain and hospitalization. The identification of biomarkers in exfoliated kidney cells from urine via western blotting, enzyme-linked immunosorbent assay (ELISA), immunofluorescence techniques, measurement of cell and protein-specific messenger ribonucleic acid (mRNA)/micro-RNA and other techniques have been reported. Recent innovations such as multispectral autofluorescence imaging and single-cell RNA sequencing (scRNA-seq) have brought additional dimensions to the clinical application of exfoliated kidney cells from urine. In this review, we discuss the current evidence regarding the utility of exfoliated proximal tubule cells (PTC), podocytes, mesangial cells, extracellular vesicles and stem/progenitor cells as surrogate markers for the early diagnosis and prognostication of CKD. Future directions for development within this research area are also identified.

The promise of artificial intelligence for kidney pathophysiology

PURPOSE OF REVIEW

We seek to determine recent advances in kidney pathophysiology that have been enabled or enhanced by artificial intelligence. We describe some of the challenges in the field as well as future directions.

RECENT FINDINGS

We first provide an overview of artificial intelligence terminologies and methodologies. We then describe the use of artificial intelligence in kidney diseases to discover risk factors from clinical data for disease progression, annotate whole slide imaging and decipher multiomics data. We delineate key examples of risk stratification and prognostication in acute kidney injury (AKI) and chronic kidney disease (CKD). We contextualize these applications in kidney disease oncology, one of the subfields to benefit demonstrably from artificial intelligence using all if these approaches. We conclude by elucidating technical challenges and ethical considerations and briefly considering future directions.

SUMMARY

The integration of clinical data, patient derived data, histology and proteomics and genomics can enhance the work of clinicians in providing more accurate diagnoses and elevating understanding of disease progression. Implementation research needs to be performed to translate these algorithms to the clinical setting.

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.

Risk Classification and Subphenotyping of Acute Kidney Injury: Concepts and Methodologies

Acute kidney injury (AKI) is a complex syndrome with a paucity of therapeutic development. One aspect that could explain the lack of implementation science in the AKI field is the vast heterogeneity of the AKI syndrome, which hinders precise therapeutic applications for specific AKI subpopulations. In this context, there is a consensual focus of the scientific community toward the development and validation of tools to better subphenotype AKI and therefore facilitate precision medicine approaches. The subphenotyping of AKI requires the use of specific methodologies suitable for interrogation of multimodal data inputs from different sources such as electronic health records, organ support devices, and/or biospecimens and tissues. Over the past years, the surge of artificial intelligence applied to health care has yielded novel machine learning methodologies for data acquisition, harmonization, and interrogation that can assist with subphenotyping of AKI. However, one should recognize that although risk classification and subphenotyping of AKI is critically important, testing their potential applications is even more important to promote implementation science. For example, risk-classification should support actionable interventions that could ameliorate or prevent the occurrence of the outcome being predicted. Furthermore, subphenotyping could be applied to predict therapeutic responses to support enrichment and adaptive platforms for pragmatic clinical trials.

Development and external validation of a machine learning model for progression of Chronic Kidney Disease

Introduction

Methods

Results

Conclusion

Role of artificial intelligence in the diagnosis and management of kidney disease: applications to chronic kidney disease and acute kidney injury

PURPOSE OF REVIEW

Chronic kidney disease (CKD) and acute kidney injury (AKI) are global public health problems associated with a significant burden of morbidity, healthcare resource use, and all-cause mortality. This review explores recently published studies that take a machine learning approach to the diagnosis, management, and prognostication in patients with AKI or CKD.

RECENT FINDINGS

The release of novel therapeutics for CKD has highlighted the importance of accurately identifying patients at the highest risk of progression. Many models have been constructed with reasonable predictive accuracy but have not been extensively externally validated and peer reviewed. Similarly, machine learning models have been developed for prediction of AKI and have found sufficient accuracy. There are issues to implementing these models, however, with conflicting results with respect to the relationship between prediction of an AKI outcome and improvements in the occurrence of other adverse events, and in some circumstances potential harm.

SUMMARY

Artificial intelligence models can help guide management of CKD and AKI, but it is important to ensure that they are broadly applicable and generalizable to various settings and associated with improved clinical decision-making and outcomes.

Soluble forms of cytokine and growth factor receptors: Mechanisms of generation and modes of action in the regulation of local and systemic inflammation

Cytokine and growth factor receptors are usually transmembrane proteins but they can also exist in soluble forms, either through cleavage and release of their ligand-binding extracellular domain, or through secretion of a soluble isoform. As an extension of this concept, transmembrane receptors on exosomes released into the circulation may act similarly to circulating soluble receptors. These soluble receptors add to the complexity of cytokine and growth factor signalling: they can function as decoy receptor that compete for ligand binding with their respective membrane-bound forms thereby attenuating signalling, or stabilize their ligands, or activate additional signalling events through interactions with other cell-surface proteins. Their soluble nature allows for a functional role away from the production sites, in remote cell types and organs. Accumulating evidence demonstrates that soluble receptors participate in the regulation and orchestration of various key cellular processes, particularly inflammatory responses. In this review, we will discuss release mechanisms of soluble cytokine and growth factor receptors, their mechanisms of action, as well as strategies for targeting their pathways in disease.

Clinical Utility of KidneyIntelX in Early Stages of Diabetic Kidney Disease in the CANVAS Trial

INTRODUCTION

KidneyIntelX is a composite risk score, incorporating biomarkers and clinical variables for predicting progression of diabetic kidney disease (DKD). The utility of this score in the context of sodium glucose co-transporter 2 inhibitors and how changes in the risk score associate with future kidney outcomes are unknown.

METHODS

We measured soluble tumor necrosis factor receptor (TNFR)-1, soluble TNFR-2, and kidney injury molecule 1 on banked samples from CANagliflozin cardioVascular Assessment Study (CANVAS) trial participants with baseline DKD (estimated glomerular filtration rate [eGFR] 30-59 mL/min/1.73 m2 or urine albumin-to-creatinine ratio [UACR] ≥30 mg/g) and generated KidneyIntelX risk scores at baseline and years 1, 3, and 6. We assessed the association of baseline and changes in KidneyIntelX with subsequent DKD progression (composite outcome of an eGFR decline of ≥5 mL/min/year [using the 6-week eGFR as the baseline in the canagliflozin group], ≥40% sustained decline in the eGFR, or kidney failure).

RESULTS

We included 1,325 CANVAS participants with concurrent DKD and available baseline plasma samples (mean eGFR 65 mL/min/1.73 m2 and median UACR 56 mg/g). During a mean follow-up of 5.6 years, 131 participants (9.9%) experienced the composite kidney outcome. Using risk cutoffs from prior validation studies, KidneyIntelX stratified patients to low- (42%), intermediate- (44%), and high-risk (15%) strata with cumulative incidence for the outcome of 3%, 11%, and 26% (risk ratio 8.4; 95% confidence interval [CI]: 5.0, 14.2) for the high-risk versus low-risk groups. The differences in eGFR slopes for canagliflozin versus placebo were 0.66, 1.52, and 2.16 mL/min/1.73 m2 in low, intermediate, and high KidneyIntelX risk strata, respectively. KidneyIntelX risk scores declined by 5.4% (95% CI: -6.9, -3.9) in the canagliflozin arm at year 1 versus an increase of 6.3% (95% CI: 3.8, 8.7) in the placebo arm (p < 0.001). Changes in the KidneyIntelX score at year 1 were associated with future risk of the composite outcome (odds ratio per 10 unit decrease 0.80; 95% CI: 0.77, 0.83; p < 0.001) after accounting for the treatment arm, without evidence of effect modification by the baseline KidneyIntelX risk stratum or by the treatment arm.

CONCLUSIONS

KidneyIntelX successfully risk-stratified a large multinational external cohort for progression of DKD, and greater numerical differences in the eGFR slope for canagliflozin versus placebo were observed in those with higher baseline KidneyIntelX scores. Canagliflozin treatment reduced KidneyIntelX risk scores over time and changes in the KidneyIntelX score from baseline to 1 year associated with future risk of DKD progression, independent of the baseline risk score and treatment arm.

Prediction of diabetic kidney disease with machine learning algorithms, upon the initial diagnosis of type 2 diabetes mellitus

INTRODUCTION

Diabetic kidney disease (DKD) accounts for the majority of increased risk of mortality for patients with diabetes, and eventually manifests in approximately half of those patients diagnosed with type 2 diabetes mellitus (T2DM). Although increased screening frequency can avoid delayed diagnoses, this is not uniformly implemented. The purpose of this study was to develop and retrospectively validate a machine learning algorithm (MLA) that predicts stages of DKD within 5 years upon diagnosis of T2DM.

RESEARCH DESIGN AND METHODS

Two MLAs were trained to predict stages of DKD severity, and compared with the Centers for Disease Control and Prevention (CDC) risk score to evaluate performance. The models were validated on a hold-out test set as well as an external dataset sourced from separate facilities.

RESULTS

The MLAs outperformed the CDC risk score in both the hold-out test and external datasets. Our algorithms achieved an area under the receiver operating characteristic curve (AUROC) of 0.75 on the hold-out set for prediction of any-stage DKD and an AUROC of over 0.82 for more severe endpoints, compared with the CDC risk score with an AUROC <0.70 on all test sets and endpoints.

CONCLUSION

This retrospective study shows that an MLA can provide timely predictions of DKD among patients with recently diagnosed T2DM.