Machine Learning to Identify Dialysis Patients at High Death Risk

Personalised prediction of maintenance dialysis initiation in patients with chronic kidney disease stages 3-5: a multicentre study using the machine learning approach

BACKGROUND

Optimal timing for initiating maintenance dialysis in patients with chronic kidney disease (CKD) stages 3-5 is challenging. This study aimed to develop and validate a machine learning (ML) model for early personalised prediction of maintenance dialysis initiation within 1-year and 3-year timeframes among patients with CKD stages 3-5.

METHODS

Retrospective electronic health record data from the Taipei Medical University clinical research database were used. Newly diagnosed patients with CKD stages 3-5 between 2008 and 2017 were identified. The observation period spanned from the diagnosis of CKD stages 3-5 until the maintenance dialysis initiation or a maximum follow-up of 3 years. Predictive models were developed using patient demographics, comorbidities, laboratory data and medications. The dataset was divided into training and testing sets to ensure robust model performance. Model evaluation metrics, including area under the curve (AUC), sensitivity, specificity, positive predictive value, negative predictive value and F1 score, were employed.

RESULTS

A total of 6123 and 5279 patients were included for 1 year and 3 years of the model development. The artificial neural network demonstrated better performance in predicting maintenance dialysis initiation within 1 year and 3 years, with AUC values of 0.96 and 0.92, respectively. Important features such as baseline estimated glomerular filtration rate and albuminuria significantly contributed to the predictive model.

CONCLUSION

This study demonstrates the efficacy of an ML approach in developing a highly predictive model for estimating the timing of maintenance dialysis initiation in patients with CKD stages 3-5. These findings have important implications for personalised treatment strategies, enabling improved clinical decision-making and potentially enhancing patient outcomes.

Designing an Implementable Clinical Prediction Model for Near-Term Mortality and Long-Term Survival in Patients on Maintenance Hemodialysis

RATIONALE & OBJECTIVE

The life expectancy of patients treated with maintenance hemodialysis (MHD) is heterogeneous. Knowledge of life-expectancy may focus care decisions on near-term versus long-term goals. The current tools are limited and focus on near-term mortality. Here, we develop and assess potential utility for predicting near-term mortality and long-term survival on MHD.

STUDY DESIGN

Predictive modeling study.

SETTING & PARTICIPANTS

42,351 patients contributing 997,381 patient months over 11 years, abstracted from the electronic health record (EHR) system of midsize, nonprofit dialysis providers.

NEW PREDICTORS & ESTABLISHED PREDICTORS

Demographics, laboratory results, vital signs, and service utilization data available within dialysis EHR.

OUTCOME

For each patient month, we ascertained death within the next 6 months (ie, near-term mortality) and survival over more than 5 years during receipt of MHD or after kidney transplantation (ie, long-term survival).

ANALYTICAL APPROACH

We used least absolute shrinkage and selection operator logistic regression and gradient-boosting machines to predict each outcome. We compared these to time-to-event models spanning both time horizons. We explored the performance of decision rules at different cut points.

RESULTS

All models achieved an area under the receiver operator characteristic curve of≥0.80 and optimal calibration metrics in the test set. The long-term survival models had significantly better performance than the near-term mortality models. The time-to-event models performed similarly to binary models. Applying different cut points spanning from the 1st to 90th percentile of the predictions, a positive predictive value (PPV) of 54% could be achieved for near-term mortality, but with poor sensitivity of 6%. A PPV of 71% could be achieved for long-term survival with a sensitivity of 67%.

LIMITATIONS

The retrospective models would need to be prospectively validated before they could be appropriately used as clinical decision aids.

CONCLUSIONS

A model built with readily available clinical variables to support easy implementation can predict clinically important life expectancy thresholds and shows promise as a clinical decision support tool for patients on MHD. Predicting long-term survival has better decision rule performance than predicting near-term mortality.

PLAIN-LANGUAGE SUMMARY

Clinical prediction models (CPMs) are not widely used for patients undergoing maintenance hemodialysis (MHD). Although a variety of CPMs have been reported in the literature, many of these were not well-designed to be easily implementable. We consider the performance of an implementable CPM for both near-term mortality and long-term survival for patients undergoing MHD. Both near-term and long-term models have similar predictive performance, but the long-term models have greater clinical utility. We further consider how the differential performance of predicting over different time horizons may be used to impact clinical decision making. Although predictive modeling is not regularly used for MHD patients, such tools may help promote individualized care planning and foster shared decision making.

Mortality prediction with adaptive feature importance recalibration for peritoneal dialysis patients

The study aims to develop AICare, an interpretable mortality prediction model, using electronic medical records (EMR) from follow-up visits for end-stage renal disease (ESRD) patients. AICare includes a multichannel feature extraction module and an adaptive feature importance recalibration module. It integrates dynamic records and static features to perform personalized health context representation learning. The dataset encompasses 13,091 visits and demographic data of 656 peritoneal dialysis (PD) patients spanning 12 years. An additional public dataset of 4,789 visits from 1,363 hemodialysis (HD) patients is also considered. AICare outperforms traditional deep learning models in mortality prediction while retaining interpretability. It uncovers mortality-feature relationships and variations in feature importance and provides reference values. An AI-doctor interaction system is developed for visualizing patients' health trajectories and risk indicators.

Data-driven, two-stage machine learning algorithm-based prediction scheme for assessing 1-year and 3-year mortality risk in chronic hemodialysis patients

Life expectancy is likely to be substantially reduced in patients undergoing chronic hemodialysis (CHD). However, machine learning (ML) may predict the risk factors of mortality in patients with CHD by analyzing the serum laboratory data from regular dialysis routine. This study aimed to establish the mortality prediction model of CHD patients by adopting two-stage ML algorithm-based prediction scheme, combined with importance of risk factors identified by different ML methods. This is a retrospective, observational cohort study. We included 800 patients undergoing CHD between December 2006 and December 2012 in Shin-Kong Wu Ho-Su Memorial Hospital. This study analyzed laboratory data including 44 indicators. We used five ML methods, namely, logistic regression (LGR), decision tree (DT), random forest (RF), gradient boosting (GB), and eXtreme gradient boosting (XGB), to develop a two-stage ML algorithm-based prediction scheme and evaluate the important factors that predict CHD mortality. LGR served as a bench method. Regarding the validation and testing datasets from 1- and 3-year mortality prediction model, the RF had better accuracy and area-under-curve results among the five different ML methods. The stepwise RF model, which incorporates the most important factors of CHD mortality risk based on the average rank from DT, RF, GB, and XGB, exhibited superior predictive performance compared to LGR in predicting mortality among CHD patients over both 1-year and 3-year periods. We had developed a two-stage ML algorithm-based prediction scheme by implementing the stepwise RF that demonstrated satisfactory performance in predicting mortality in patients with CHD over 1- and 3-year periods. The findings of this study can offer valuable information to nephrologists, enhancing patient-centered decision-making and increasing awareness about risky laboratory data, particularly for patients with a high short-term mortality risk.

An integrated machine learning predictive scheme for longitudinal laboratory data to evaluate the factors determining renal function changes in patients with different chronic kidney disease stages

Background and objectives

Chronic kidney disease (CKD) is a global health concern. This study aims to identify key factors associated with renal function changes using the proposed machine learning and important variable selection (ML&IVS) scheme on longitudinal laboratory data. The goal is to predict changes in the estimated glomerular filtration rate (eGFR) in a cohort of patients with CKD stages 3-5.

Design

A retrospective cohort study.

Setting and participants

A total of 710 outpatients who presented with stable nondialysis-dependent CKD stages 3-5 at the Shin-Kong Wu Ho-Su Memorial Hospital Medical Center from 2016 to 2021.

Methods

This study analyzed trimonthly laboratory data including 47 indicators. The proposed scheme used stochastic gradient boosting, multivariate adaptive regression splines, random forest, eXtreme gradient boosting, and light gradient boosting machine algorithms to evaluate the important factors for predicting the results of the fourth eGFR examination, especially in patients with CKD stage 3 and those with CKD stages 4-5, with or without diabetes mellitus (DM).

Main outcome measurement

Subsequent eGFR level after three consecutive laboratory data assessments.

Results

Our ML&IVS scheme demonstrated superior predictive capabilities and identified significant factors contributing to renal function changes in various CKD groups. The latest levels of eGFR, blood urea nitrogen (BUN), proteinuria, sodium, and systolic blood pressure as well as mean levels of eGFR, BUN, proteinuria, and triglyceride were the top 10 significantly important factors for predicting the subsequent eGFR level in patients with CKD stages 3-5. In individuals with DM, the latest levels of BUN and proteinuria, mean levels of phosphate and proteinuria, and variations in diastolic blood pressure levels emerged as important factors for predicting the decline of renal function. In individuals without DM, all phosphate patterns and latest albumin levels were found to be key factors in the advanced CKD group. Moreover, proteinuria was identified as an important factor in the CKD stage 3 group without DM and CKD stages 4-5 group with DM.

Conclusion

The proposed scheme highlighted factors associated with renal function changes in different CKD conditions, offering valuable insights to physicians for raising awareness about renal function changes.

Predict, diagnose, and treat chronic kidney disease with machine learning: a systematic literature review

OBJECTIVES

In this systematic review we aimed at assessing how artificial intelligence (AI), including machine learning (ML) techniques have been deployed to predict, diagnose, and treat chronic kidney disease (CKD). We systematically reviewed the available evidence on these innovative techniques to improve CKD diagnosis and patient management.

METHODS

We included English language studies retrieved from PubMed. The review is therefore to be classified as a "rapid review", since it includes one database only, and has language restrictions; the novelty and importance of the issue make missing relevant papers unlikely. We extracted 16 variables, including: main aim, studied population, data source, sample size, problem type (regression, classification), predictors used, and performance metrics. We followed the Preferred Reporting Items for Systematic Reviews (PRISMA) approach; all main steps were done in duplicate.

RESULTS

From a total of 648 studies initially retrieved, 68 articles met the inclusion criteria. Models, as reported by authors, performed well, but the reported metrics were not homogeneous across articles and therefore direct comparison was not feasible. The most common aim was prediction of prognosis, followed by diagnosis of CKD. Algorithm generalizability, and testing on diverse populations was rarely taken into account. Furthermore, the clinical evaluation and validation of the models/algorithms was perused; only a fraction of the included studies, 6 out of 68, were performed in a clinical context.

CONCLUSIONS

Machine learning is a promising tool for the prediction of risk, diagnosis, and therapy management for CKD patients. Nonetheless, future work is needed to address the interpretability, generalizability, and fairness of the models to ensure the safe application of such technologies in routine clinical practice.

Evaluate prognostic accuracy of SOFA component score for mortality among adults with sepsis by machine learning method

INTRODUCTION

Sepsis has the characteristics of high incidence, high mortality of ICU patients. Early assessment of disease severity and risk stratification of death in patients with sepsis, and further targeted intervention are very important. The purpose of this study was to develop machine learning models based on sequential organ failure assessment (SOFA) components to early predict in-hospital mortality in ICU patients with sepsis and evaluate model performance.

METHODS

Patients admitted to ICU with sepsis diagnosis were extracted from MIMIC-IV database for retrospective analysis, and were randomly divided into training set and test set in accordance with 2:1. Six variables were included in this study, all of which were from the scores of 6 organ systems in SOFA score. The machine learning model was trained in the training set and evaluated in the validation set. Six machine learning methods including linear regression analysis, least absolute shrinkage and selection operator (LASSO), Logistic regression analysis (LR), Gaussian Naive Bayes (GNB) and support vector machines (SVM) were used to construct the death risk prediction models, and the accuracy, area under the receiver operating characteristic curve (AUROC), Decision Curve Analysis (DCA) and K-fold cross-validation were used to evaluate the prediction performance of developed models.

RESULT

A total of 23,889 patients with sepsis were enrolled, of whom 3659 died in hospital. Three feature variables including renal system score, central nervous system score and cardio vascular system score were used to establish prediction models. The accuracy of the LR, GNB, SVM were 0.851, 0.844 and 0.862, respectively, which were better than linear regression analysis (0.123) and LASSO (0.130). The AUROCs of LR, GNB and SVM were 0.76, 0.76 and 0.67, respectively. K-fold cross validation showed that the average AUROCs of LR, GNB and SVM were 0.757 ± 0.005, 0.762 ± 0.006, 0.630 ± 0.013, respectively. For the probability threshold of 5-50%, LY and GNB models both showed positive net benefits.

CONCLUSION

The two machine learning-based models (LR and GNB models) based on SOFA components can be used to predict in-hospital mortality of septic patients admitted to ICU.

Machine Learning Models Predicting Cardiovascular and Renal Outcomes and Mortality in Patients with Hyperkalemia

Hyperkalemia is associated with increased risks of mortality and adverse clinical outcomes. The treatment of hyperkalemia often leads to the discontinuation or restriction of beneficial but potassium-increasing therapy such as renin-angiotensin-aldosterone inhibitors (RAASi) and high-potassium diet including fruits and vegetables. To date, limited evidence is available for personalized risk evaluation in this heterogeneous and multifactorial pathophysiological condition. We developed risk prediction models using extreme gradient boosting (XGB), multiple logistic regression (LR), and deep neural network. Models were derived from a retrospective cohort of hyperkalemic patients with either heart failure or chronic kidney disease stage ≥3a from a Japanese nationwide database (1 April 2008−30 September 2018). Studied outcomes included all-cause death, renal replacement therapy introduction (RRT), hospitalization for heart failure (HHF), and cardiovascular events within three years after hyperkalemic episodes. The best performing model was further validated using an external cohort. A total of 24,949 adult hyperkalemic patients were selected for model derivation and internal validation. A total of 1452 deaths (16.6%), 887 RRT (10.1%), 1,345 HHF (15.4%), and 621 cardiovascular events (7.1%) were observed. XGB outperformed other models. The area under receiver operator characteristic curves (AUROCs) of XGB vs. LR (95% CIs) for death, RRT, HHF, and cardiovascular events were 0.823 (0.805−0.841) vs. 0.809 (0.791−0.828), 0.957 (0.947−0.967) vs. 0.947 (0.936−0.959), 0.863 (0.846−0.880) vs. 0.838 (0.820−0.856), and 0.809 (0.784−0.834) vs. 0.798 (0.772−0.823), respectively. In the external dataset including 86,279 patients, AUROCs (95% CIs) for XGB were: death, 0.747 (0.742−0.753); RRT, 0.888 (0.882−0.894); HHF, 0.673 (0.666−0.679); and cardiovascular events, 0.585 (0.578−0.591). Kaplan−Meier curves of the high-risk predicted group showed a statistically significant difference from that of the low-risk predicted groups for all outcomes (p < 0.005; log-rank test). These findings suggest possible use of machine learning models for real-world risk assessment as a guide for observation and/or treatment decision making that may potentially lead to improved outcomes in hyperkalemic patients while retaining the benefit of life-saving therapies.

A Machine Learning Model for Predicting Mortality within 90 Days of Dialysis Initiation

Background

The first 90 days after dialysis initiation are associated with high morbidity and mortality in end-stage kidney disease (ESKD) patients. A machine learning–based tool for predicting mortality could inform patient-clinician shared decision making on whether to initiate dialysis or pursue medical management. We used the eXtreme Gradient Boosting (XGBoost) algorithm to predict mortality in the first 90 days after dialysis initiation in a nationally representative population from the United States Renal Data System.

Methods

A cohort of adults initiating dialysis between 2008–2017 were studied for outcome of death within 90 days of dialysis initiation. The study dataset included 188 candidate predictors prognostic of early mortality that were known on or before the first day of dialysis and was partitioned into training (70%) and testing (30%) subsets. XGBoost modeling used a complete-case set and a dataset obtained from multiple imputation. Model performance was evaluated by c-statistics overall and stratified by subgroups of age, sex, race, and dialysis modality.

Results

The analysis included 1,150,195 patients with ESKD, of whom 86,083 (8%) died in the first 90 days after dialysis initiation. The XGBoost models discriminated mortality risk in the nonimputed (c=0.826, 95% CI, 0.823 to 0.828) and imputed (c=0.827, 95% CI, 0.823 to 0.827) models and performed well across nearly every subgroup (race, age, sex, and dialysis modality) evaluated (c>0.75). Across predicted risk thresholds of 10%–50%, higher risk thresholds showed declining sensitivity (0.69–0.04) with improving specificity (0.79–0.99); similarly, positive likelihood ratio was highest at the 40% threshold, whereas the negative likelihood ratio was lowest at the 10% threshold. After calibration using isotonic regression, the model accurately estimated the probability of mortality across all ranges of predicted risk.

Conclusions

The XGBoost-based model developed in this study discriminated risk of early mortality after dialysis initiation with excellent calibration and performed well across key subgroups.

Artificial Intelligence-Based Ensemble Learning Model for Prediction of Hepatitis C Disease

Machine learning algorithms are excellent techniques to develop prediction models to enhance response and efficiency in the health sector. It is the greatest approach to avoid the spread of hepatitis C, especially injecting drugs, is to avoid these behaviors. Treatments for hepatitis C can cure most patients within 8 to 12 weeks, so being tested is critical. After examining multiple types of machine learning approaches to construct the classification models, we built an AI-based ensemble model for predicting Hepatitis C disease in patients with the capacity to predict advanced fibrosis by integrating clinical data and blood biomarkers. The dataset included a variety of factors related to Hepatitis C disease. The training data set was subjected to three machine-learning approaches and the validated data was then used to evaluate the ensemble learning-based prediction model. The results demonstrated that the proposed ensemble learning model has been observed ad more accurate compared to the existing Machine learning algorithms. The Multi-layer perceptron (MLP) technique was the most precise learning approach (94.1% accuracy). The Bayesian network was the second-most accurate learning algorithm (94.47% accuracy). The accuracy improved to the level of 95.59%. Hepatitis C has a significant frequency globally, and the disease's development can result in irreparable damage to the liver, as well as death. As a result, utilizing AI-based ensemble learning model for its prediction is advantageous in curbing the risks and improving treatment outcome. The study demonstrated that the use of ensemble model presents more precision or accuracy in predicting Hepatitis C disease instead of using individual algorithms. It also shows how an AI-based ensemble model could be used to diagnose Hepatitis C disease with greater accuracy.

Machine learning to predict end stage kidney disease in chronic kidney disease

The purpose of this study was to assess the feasibility of machine learning (ML) in predicting the risk of end-stage kidney disease (ESKD) from patients with chronic kidney disease (CKD). Data were obtained from a longitudinal CKD cohort. Predictor variables included patients' baseline characteristics and routine blood test results. The outcome of interest was the presence or absence of ESKD by the end of 5 years. Missing data were imputed using multiple imputation. Five ML algorithms, including logistic regression, naïve Bayes, random forest, decision tree, and K-nearest neighbors were trained and tested using fivefold cross-validation. The performance of each model was compared to that of the Kidney Failure Risk Equation (KFRE). The dataset contained 748 CKD patients recruited between April 2006 and March 2008, with the follow-up time of 6.3 ± 2.3 years. ESKD was observed in 70 patients (9.4%). Three ML models, including the logistic regression, naïve Bayes and random forest, showed equivalent predictability and greater sensitivity compared to the KFRE. The KFRE had the highest accuracy, specificity, and precision. This study showed the feasibility of ML in evaluating the prognosis of CKD based on easily accessible features. Three ML models with adequate performance and sensitivity scores suggest a potential use for patient screenings. Future studies include external validation and improving the models with additional predictor variables.

Artificial intelligence in peritoneal dialysis: general overview

OBJECTIVE

This article is a general overview about artificial intelligence/machine learning (AI/ML) algorithms in the domain of peritoneal dialysis (PD).

METHODS

We searched studies that used AI/ML in PD, which were classified according to the type of algorithm and PD issue.

RESULTS

Studies were divided into (a) predialytic stratification, (b) peritoneal technique issues, (c) infections, and (d) complications prediction. Most of the studies were observational and majority of them were reported after 2010.

CONCLUSIONS

There is a number of studies proved that AI/ML algorithms can predict better than conventional statistical method and even nephrologists. However, the soundness of AI/ML algorithms in PD still requires large databases and interpretation by clinical experts. In the future, we hope that AI will facilitate the management of PD patients, thus increasing the quality of life and survival.

Big Data in Nephrology

A huge array of data in nephrology is collected through patient registries, large epidemiological studies, electronic health records, administrative claims, clinical trial repositories, mobile health devices and molecular databases. Application of these big data, particularly using machine-learning algorithms, provides a unique opportunity to obtain novel insights into kidney diseases, facilitate personalized medicine and improve patient care. Efforts to make large volumes of data freely accessible to the scientific community, increased awareness of the importance of data sharing and the availability of advanced computing algorithms will facilitate the use of big data in nephrology. However, challenges exist in accessing, harmonizing and integrating datasets in different formats from disparate sources, improving data quality and ensuring that data are secure and the rights and privacy of patients and research participants are protected. In addition, the optimism for data-driven breakthroughs in medicine is tempered by scepticism about the accuracy of calibration and prediction from in silico techniques. Machine-learning algorithms designed to study kidney health and diseases must be able to handle the nuances of this specialty, must adapt as medical practice continually evolves, and must have global and prospective applicability for external and future datasets.

Machine learning directed interventions associate with decreased hospitalization rates in hemodialysis patients

BACKGROUND

An integrated kidney disease company uses machine learning (ML) models that predict the 12-month risk of an outpatient hemodialysis (HD) patient having multiple hospitalizations to assist with directing personalized interdisciplinary interventions in a Dialysis Hospitalization Reduction Program (DHRP). We investigated the impact of risk directed interventions in the DHRP on clinic-wide hospitalization rates.

METHODS

We compared the hospital admission and day rates per-patient-year (ppy) from all hemodialysis patients in 54 DHRP and 54 control clinics identified by propensity score matching at baseline in 2015 and at the end of the pilot in 2018. We also used paired T test to compare the between group difference of annual hospitalization rate and hospitalization days rates at baseline and end of the pilot.

RESULTS

The between group difference in annual hospital admission and day rates was similar at baseline (2015) with a mean difference between DHRP versus control clinics of -0.008 ± 0.09 ppy and -0.05 ± 0.96 ppy respectively. The between group difference in hospital admission and day rates became more distinct at the end of follow up (2018) favoring DHRP clinics with the mean difference being -0.155 ± 0.38 ppy and -0.97 ± 2.78 ppy respectively. A paired t-test showed the change in the between group difference in hospital admission and day rates from baseline to the end of the follow up was statistically significant (t-value = 2.73, p-value < 0.01) and (t-value = 2.29, p-value = 0.02) respectively.

CONCLUSIONS

These findings suggest ML model-based risk-directed interdisciplinary team interventions associate with lower hospitalization rates and hospital day rate in HD patients, compared to controls.

Computational Models Used to Predict Cardiovascular Complications in Chronic Kidney Disease Patients: A Systematic Review

Background and objectives: cardiovascular complications (CVC) are the leading cause of death in patients with chronic kidney disease (CKD). Standard cardiovascular disease risk prediction models used in the general population are not validated in patients with CKD. We aim to systematically review the up-to-date literature on reported outcomes of computational methods such as artificial intelligence (AI) or regression-based models to predict CVC in CKD patients. Materials and methods: the electronic databases of MEDLINE/PubMed, EMBASE, and ScienceDirect were systematically searched. The risk of bias and reporting quality for each study were assessed against transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD) and the prediction model risk of bias assessment tool (PROBAST). Results: sixteen papers were included in the present systematic review: 15 non-randomized studies and 1 ongoing clinical trial. Twelve studies were found to perform AI or regression-based predictions of CVC in CKD, either through single or composite endpoints. Four studies have come up with computational solutions for other CV-related predictions in the CKD population. Conclusions: the identified studies represent palpable trends in areas of clinical promise with an encouraging present-day performance. However, there is a clear need for more extensive application of rigorous methodologies. Following the future prospective, randomized clinical trials, and thorough external validations, computational solutions will fill the gap in cardiovascular predictive tools for chronic kidney disease.

Machine learning in nephrology: scratching the surface

Machine learning shows enormous potential in facilitating decision-making regarding kidney diseases. With the development of data preservation and processing, as well as the advancement of machine learning algorithms, machine learning is expected to make remarkable breakthroughs in nephrology. Machine learning models have yielded many preliminaries to moderate and several excellent achievements in the fields, including analysis of renal pathological images, diagnosis and prognosis of chronic kidney diseases and acute kidney injury, as well as management of dialysis treatments. However, it is just scratching the surface of the field; at the same time, machine learning and its applications in renal diseases are facing a number of challenges. In this review, we discuss the application status, challenges and future prospects of machine learning in nephrology to help people further understand and improve the capacity for prediction, detection, and care quality in kidney diseases.

Predialysis Potassium Variability and Postdialysis Mortality in Patients With Advanced CKD

Introduction

Patients with advanced non–dialysis-dependent chronic kidney disease (NDD-CKD) are prone to potassium (K) imbalances due to reduced kidney function. Both hypo- and hyperkalemia are associated with increased mortality; however, it is unclear if K variability before dialysis initiation is associated with outcomes after dialysis initiation.

Methods

We identified 34,167 US veterans with advanced NDD-CKD transitioning to dialysis between October 1, 2007, through March 31, 2015, who had at least 1 K measurement each year over a 3-year period before transition (3-year prelude). For each patient, a linear mixed-effects model was used to regress K over time (in years) over the 3-year prelude to derive K variability (square root of the average squared distance between the observed and estimated K). The main outcomes of interest were 6-month all-cause and cardiovascular mortality after dialysis initiation. Multivariable Cox and Fine-Gray competing risk regression adjusted for 3-year prelude K intercept, K slope (per year), demographics, smoking status, comorbidities, length of hospitalizations, body mass index, vascular access type, medications, average estimated glomerular filtration rate, and number of K measurements over the 3-year prelude were used to assess the association of K variability (expressed as quartiles) with all-cause and cardiovascular mortality, respectively.

Results

Higher prelude K variability was associated with higher multivariable-adjusted risk of all-cause mortality but not cardiovascular mortality (adjusted hazard/subhazard ratios [95% confidence interval] for highest quartile [vs. lowest] of K variability, 1.14 [1.03–1.25] and 0.99 [0.85–1.16] for all-cause and cardiovascular mortality, respectively).

Conclusion

Higher K variability is associated with higher all-cause mortality after dialysis initiation.

The quest for cardiovascular disease risk prediction models in patients with nondialysis chronic kidney disease

PURPOSE OF REVIEW

Cardiovascular disease (CVD) is the leading cause of death in patients with chronic kidney disease (CKD). However, traditional CVD risk prediction equations do not work well in patients with CKD, and inclusion of kidney disease metrics such as albuminuria and estimated glomerular filtration rate have a modest to no benefit in improving prediction.

RECENT FINDINGS

As CKD progresses, the strength of traditional CVD risk factors in predicting clinical outcomes weakens. A pooled cohort equation used for CVD risk prediction is a useful tool for guiding clinicians on management of patients with CVD risk, but these equations do not calibrate well in patients with CKD, although a number of studies have developed modifications of the traditional equations to improve risk prediction. The reason for the poor calibration may be related to the fact that as CKD progresses, associations of traditional risk factors such as BMI, lipids and blood pressure with CVD outcomes are attenuated or reverse, and other risk factors may become more important.

SUMMARY

Large national cohorts such as the US Veteran cohort with many patients with evolving CKD may be useful resources for the developing CVD prediction models; however, additional considerations are needed for the unique composition of patients receiving care in these healthcare systems, including those with multiple comorbidities, as well as mental health issues, homelessness, posttraumatic stress disorders, frailty, malnutrition and polypharmacy. Machine learning over conventional risk prediction models may be better suited to handle the complexity needed for these CVD prediction models.

Artificial intelligence enabled applications in kidney disease

Artificial intelligence (AI) is considered as the next natural progression of traditional statistical techniques. Advances in analytical methods and infrastructure enable AI to be applied in health care. While AI applications are relatively common in fields like ophthalmology and cardiology, its use is scarcely reported in nephrology. We present the current status of AI in research toward kidney disease and discuss future pathways for AI. The clinical applications of AI in progression to end-stage kidney disease and dialysis can be broadly subdivided into three main topics: (a) predicting events in the future such as mortality and hospitalization; (b) providing treatment and decision aids such as automating drug prescription; and (c) identifying patterns such as phenotypical clusters and arteriovenous fistula aneurysm. At present, the use of prediction models in treating patients with kidney disease is still in its infancy and further evidence is needed to identify its relative value. Policies and regulations need to be addressed before implementing AI solutions at the point of care in clinics. AI is not anticipated to replace the nephrologists' medical decision-making, but instead assist them in providing optimal personalized care for their patients.

Prognostic Machine Learning Models for First-Year Mortality in Incident Hemodialysis Patients: Development and Validation Study

Background

The first-year survival rate among patients undergoing hemodialysis remains poor. Current mortality risk scores for patients undergoing hemodialysis employ regression techniques and have limited applicability and robustness.

Objective

We aimed to develop a machine learning model utilizing clinical factors to predict first-year mortality in patients undergoing hemodialysis that could assist physicians in classifying high-risk patients.

Methods

Training and testing cohorts consisted of 5351 patients from a single center and 5828 patients from 97 renal centers undergoing hemodialysis (incident only). The outcome was all-cause mortality during the first year of dialysis. Extreme gradient boosting was used for algorithm training and validation. Two models were established based on the data obtained at dialysis initiation (model 1) and data 0-3 months after dialysis initiation (model 2), and 10-fold cross-validation was applied to each model. The area under the curve (AUC), sensitivity (recall), specificity, precision, balanced accuracy, and F1 score were used to assess the predictive ability of the models.

Results

In the training and testing cohorts, 585 (10.93%) and 764 (13.11%) patients, respectively, died during the first-year follow-up. Of 42 candidate features, the 15 most important features were selected. The performance of model 1 (AUC 0.83, 95% CI 0.78-0.84) was similar to that of model 2 (AUC 0.85, 95% CI 0.81-0.86).

Conclusions

We developed and validated 2 machine learning models to predict first-year mortality in patients undergoing hemodialysis. Both models could be used to stratify high-risk patients at the early stages of dialysis.

Application of explainable ensemble artificial intelligence model to categorization of hemodialysis-patient and treatment using nationwide-real-world data in Japan

BACKGROUND

Although dialysis patients are at a high risk of death, it is difficult for medical practitioners to simultaneously evaluate many inter-related risk factors. In this study, we evaluated the characteristics of hemodialysis patients using machine learning model, and its usefulness for screening hemodialysis patients at a high risk of one-year death using the nation-wide database of the Japanese Society for Dialysis Therapy.

MATERIALS AND METHODS

The patients were separated into two datasets (n = 39,930, 39,930, respectively). We categorized hemodialysis patients in Japan into new clusters generated by the K-means clustering method using the development dataset. The association between a cluster and the risk of death was evaluated using multivariate Cox proportional hazards models. Then, we developed an ensemble model composed of the clusters and support vector machine models in the model development phase, and compared the accuracy of the prediction of mortality between the machine learning models in the model validation phase.

RESULTS

Average age of the subjects was 65.7±12.2 years; 32.7% had diabetes mellitus. The five clusters clearly distinguished the groups on the basis of their characteristics: Cluster 1, young male, and chronic glomerulonephritis; Cluster 2, female, and chronic glomerulonephritis; Cluster 3, diabetes mellitus; Cluster 4, elderly and nephrosclerosis; Cluster 5, elderly and protein energy wasting. These clusters were associated with the risk of death; Cluster 5 compared with Cluster 1, hazard ratio 8.86 (95% CI 7.68, 10.21). The accuracy of the ensemble model for the prediction of 1-year death was 0.948 and higher than those of logistic regression model (0.938), support vector machine model (0.937), and deep learning model (0.936).

CONCLUSIONS

The clusters clearly categorized patient on their characteristics, and reflected their prognosis. Our real-world-data-based machine learning system is applicable to identifying high-risk hemodialysis patients in clinical settings, and has a strong potential to guide treatments and improve their prognosis.

Leveraging Data Science for a Personalized Haemodialysis

Background

The 2019 Science for Dialysis Meeting at Bellvitge University Hospital was devoted to the challenges and opportunities posed by the use of data science to facilitate precision and personalized medicine in nephrology, and to describe new approaches and technologies. The meeting included separate sections for issues in data collection and data analysis. As part of data collection, we presented the institutional ARGOS e-health project, which provides a common model for the standardization of clinical practice. We also pay specific attention to the way in which randomized controlled trials offer data that may be critical to decision-making in the real world. The opportunities of open source software (OSS) for data science in clinical practice were also discussed.

Summary

Precision medicine aims to provide the right treatment for the right patients at the right time and is deeply connected to data science. Dialysis patients are highly dependent on technology to live, and their treatment generates a huge volume of data that has to be analysed. Data science has emerged as a tool to provide an integrated approach to data collection, storage, cleaning, processing, analysis, and interpretation from potentially large volumes of information. This is meant to be a perspective article about data science based on the experience of the experts invited to the Science for Dialysis Meeting and provides an up-to-date perspective of the potential of data science in kidney disease and dialysis.

Key messages

Healthcare is quickly becoming data-dependent, and data science is a discipline that holds the promise of contributing to the development of personalized medicine, although nephrology still lags behind in this process. The key idea is to ensure that data will guide medical decisions based on individual patient characteristics rather than on averages over a whole population usually based on randomized controlled trials that excluded kidney disease patients. Furthermore, there is increasing interest in obtaining data about the effectiveness of available treatments in current patient care based on pragmatic clinical trials. The use of data science in this context is becoming increasingly feasible in part thanks to the swift developments in OSS.

Prediction modeling-part 1: regression modeling

Risk prediction models are statistical models that estimate the probability of individuals having a certain disease or clinical outcome based on a range of characteristics, and they can be used in clinical practice to stratify disease severity and characterize the risk of disease or disease prognosis. With technological advancements and the proliferation of clinical and biological data, prediction models are increasingly being developed in many areas of nephrology practice. This article guides the reader through the process of creating a prediction model, including (i) defining the clinical question and type of model, (ii) data collection and data cleaning, (iii) model building and variable selection, (iv) model performance, (v) model validation, (vi) model presentation and reporting, and (vii) impact evaluation. An example of developing a prediction model to predict mortality after intensive care unit admission for patients with end-stage kidney disease is also provided to illustrate the model development process.

Role of Artificial Intelligence in Kidney Disease

Artificial intelligence (AI), as an advanced science technology, has been widely used in medical fields to promote medical development, mainly applied to early detections, disease diagnoses, and management. Owing to the huge number of patients, kidney disease remains a global health problem. Challenges remain in its diagnosis and treatment. AI could take individual conditions into account, produce suitable decisions and promise to make great strides in kidney disease management. Here, we review the current studies of AI applications in kidney disease in alerting systems, diagnostic assistance, guiding treatment and evaluating prognosis. Although the number of studies related to AI applications in kidney disease is small, the potential of AI in the management of kidney disease is well recognized by clinicians; AI will greatly enhance clinicians' capacity in their clinical practice in the future.