Artificial intelligence outperforms experienced nephrologists to assess dry weight in pediatric patients on chronic hemodialysis

Unlocking the potential of big data and AI in medicine: insights from biobanking

Big data and artificial intelligence are key elements in the medical field as they are expected to improve accuracy and efficiency in diagnosis and treatment, particularly in identifying biomedically relevant patterns, facilitating progress towards individually tailored preventative and therapeutic interventions. These applications belong to current research practice that is data-intensive. While the combination of imaging, pathological, genomic, and clinical data is needed to train algorithms to realize the full potential of these technologies, biobanks often serve as crucial infrastructures for data-sharing and data flows. In this paper, we argue that the 'data turn' in the life sciences has increasingly re-structured major infrastructures, which often were created for biological samples and associated data, as predominantly data infrastructures. These have evolved and diversified over time in terms of tackling relevant issues such as harmonization and standardization, but also consent practices and risk assessment. In line with the datafication, an increased use of AI-based technologies marks the current developments at the forefront of the big data research in life science and medicine that engender new issues and concerns along with opportunities. At a time when secure health data environments, such as European Health Data Space, are in the making, we argue that such meta-infrastructures can benefit both from the experience and evolution of biobanking, but also the current state of affairs in AI in medicine, regarding good governance, the social aspects and practices, as well as critical thinking about data practices, which can contribute to trustworthiness of such meta-infrastructures.

Effects of machine learning-based clinical decision support systems on decision-making, care delivery, and patient outcomes: a scoping review

OBJECTIVE

This study aims to summarize the research literature evaluating machine learning (ML)-based clinical decision support (CDS) systems in healthcare settings.

MATERIALS AND METHODS

We conducted a review in accordance with the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta Analyses extension for Scoping Review). Four databases, including PubMed, Medline, Embase, and Scopus were searched for studies published from January 2016 to April 2021 evaluating the use of ML-based CDS in clinical settings. We extracted the study design, care setting, clinical task, CDS task, and ML method. The level of CDS autonomy was examined using a previously published 3-level classification based on the division of clinical tasks between the clinician and CDS; effects on decision-making, care delivery, and patient outcomes were summarized.

RESULTS

Thirty-two studies evaluating the use of ML-based CDS in clinical settings were identified. All were undertaken in developed countries and largely in secondary and tertiary care settings. The most common clinical tasks supported by ML-based CDS were image recognition and interpretation (n = 12) and risk assessment (n = 9). The majority of studies examined assistive CDS (n = 23) which required clinicians to confirm or approve CDS recommendations for risk assessment in sepsis and for interpreting cancerous lesions in colonoscopy. Effects on decision-making, care delivery, and patient outcomes were mixed.

CONCLUSION

ML-based CDS are being evaluated in many clinical areas. There remain many opportunities to apply and evaluate effects of ML-based CDS on decision-making, care delivery, and patient outcomes, particularly in resource-constrained settings.

Machine learning models to predict post-dialysis blood pressure in children and young adults on maintenance hemodialysis

Hypertension is associated with significant cardiovascular morbidity. Blood pressure (BP) control on maintenance hemodialysis (HD) is strongly impacted by volume status. The objective of this study was to assess whether machine learning (ML) is effective in predicting post-HD BP in children and young adults on HD. We collected data on BP, IDWG, pulse, and weights for patients on maintenance HD (> 3 months). Input features included DW, pre-post weight difference, IDWG and pre-HD BP. Seven models were trained and tuned using open-source libraries. Model performance was evaluated using time-series cross-validation on a rolling basis (3-12 month training, 1-day testing). Various regression scores were compared between models. Data for 35 patients (14,375 HD sessions) were analyzed. Extreme gradient boosting (XGB) and vector autoregression with exogenous regressors (VARX) achieved better accuracy in predicting post-dialysis systolic BP than K-nearest neighbor, support vector regression (SVR) with radial basis function kernel and random forest (p < 0.001 for each). The differences in accuracy between XGB, VARX, SVR with linear kernel, random forest and linear regression were not significant. Using clinical parameters, ML models may be useful in predicting post-HD BP, which may help guide DW adjustment and optimizing BP control for maintenance HD patients.

ESKD Risk Prediction Model in a Multicenter Chronic Kidney Disease Cohort in China: A Derivation, Validation, and Comparison Study

BACKGROUND AND OBJECTIVES

In light of the growing burden of chronic kidney disease (CKD), it is of particular importance to create disease prediction models that can assist healthcare providers in identifying cases of CKD individual risk and integrate risk-based care for disease progress management. The objective of this study was to develop and validate a new pragmatic end-stage kidney disease (ESKD) risk prediction utilizing the Cox proportional hazards model (Cox) and machine learning (ML).

DESIGN, SETTING, PARTICIPANTS, AND MEASUREMENTS

The Chinese Cohort Study of Chronic Kidney Disease (C-STRIDE), a multicenter CKD cohort in China, was employed as the model's training and testing datasets, with a split ratio of 7:3. A cohort from Peking University First Hospital (PKUFH cohort) served as the external validation dataset. The participants' laboratory tests in those cohorts were conducted at PKUFH. We included individuals with CKD stages 1~4 at baseline. The incidence of kidney replacement therapy (KRT) was defined as the outcome. We constructed the Peking University-CKD (PKU-CKD) risk prediction model employing the Cox and ML methods, which include extreme gradient boosting (XGBoost) and survival support vector machine (SSVM). These models discriminate metrics by applying Harrell's concordance index (Harrell's C-index) and Uno's concordance (Uno's C). The calibration performance was measured by the Brier score and plots.

RESULTS

Of the 3216 C-STRIDE and 342 PKUFH participants, 411 (12.8%) and 25 (7.3%) experienced KRT with mean follow-up periods of 4.45 and 3.37 years, respectively. The features included in the PKU-CKD model were age, gender, estimated glomerular filtration rate (eGFR), urinary albumin-creatinine ratio (UACR), albumin, hemoglobin, medical history of type 2 diabetes mellitus (T2DM), and hypertension. In the test dataset, the values of the Cox model for Harrell's C-index, Uno's C-index, and Brier score were 0.834, 0.833, and 0.065, respectively. The XGBoost algorithm values for these metrics were 0.826, 0.825, and 0.066, respectively. The SSVM model yielded values of 0.748, 0.747, and 0.070, respectively, for the above parameters. The comparative analysis revealed no significant difference between XGBoost and Cox, in terms of Harrell's C, Uno's C, and the Brier score (p = 0.186, 0.213, and 0.41, respectively) in the test dataset. The SSVM model was significantly inferior to the previous two models (p < 0.001), in terms of discrimination and calibration. The validation dataset showed that XGBoost was superior to Cox, regarding Harrell's C, Uno's C, and the Brier score (p = 0.003, 0.027, and 0.032, respectively), while Cox and SSVM were almost identical concerning these three parameters (p = 0.102, 0.092, and 0.048, respectively).

CONCLUSIONS

We developed and validated a new ESKD risk prediction model for patients with CKD, employing commonly measured indicators in clinical practice, and its overall performance was satisfactory. The conventional Cox regression and certain ML models exhibited equal accuracy in predicting the course of CKD.

Wearables in Nephrology: Fanciful Gadgetry or Prêt-à-Porter?

Telemedicine and digitalised healthcare have recently seen exponential growth, led, in part, by increasing efforts to improve patient flexibility and autonomy, as well as drivers from financial austerity and concerns over climate change. Nephrology is no exception, and daily innovations are underway to provide digitalised alternatives to current models of healthcare provision. Wearable technology already exists commercially, and advances in nanotechnology and miniaturisation mean interest is also garnering clinically. Here, we outline the current existing wearable technology pertaining to the diagnosis and monitoring of patients with a spectrum of kidney disease, give an overview of wearable dialysis technology, and explore wearables that do not yet exist but would be of great interest. Finally, we discuss challenges and potential pitfalls with utilising wearable technology and the factors associated with successful implementation.

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.

Narrative update of clinical trials with antihypertensive drugs in children and adolescents

INTRODUCTION

To date, our knowledge on antihypertensive pharmacological treatment in children and adolescents is still limited because there are few randomized clinical trials (CTs), hampering appropriate management. The objective was to perform a narrative review of the most relevant aspects of clinical trials carried out in primary and secondary hypertension.

METHODS

Studies published in PubMed with the following descriptors: clinical trial, antihypertensive drug, children, adolescents were selected. A previous Cochrane review of 21 randomized CTs pointed out the difficulty that statistical analysis could not assess heterogeneity because there were not enough data. A more recent meta-analysis, that applied more stringent inclusion criteria and selected 13 CTs, also concluded that heterogeneity, small sample size, and short follow-up time, as well as the absence of studies comparing drugs of different classes, limit the utility.

RESULTS

In the presented narrative review, including 30 studies, there is a paucity of CTs focusing only on children with primary or secondary, mainly renoparenchymal, hypertension. In trials on angiotensin converting enzyme inhibitors (ACEI), angiotensin receptor blockers (ARBs), calcium channel blockers (CCBs) and diuretics, a significant reduction of both SBP and DBP in mixed cohorts of children with primary and secondary hypertension was achieved. However, few studies assessed the effect of antihypertensive drugs on hypertensive organ damage.

CONCLUSIONS

Given the increasing prevalence and undertreatment of hypertension in this age group, innovative solutions including new design, such as 'n-of-1', and optimizing the use of digital health technologies could provide more precise and faster information about the efficacy of each antihypertensive drug class and the potential benefits according to patient characteristics.

Artificial intelligence and digital health for volume maintenance in hemodialysis patients

Chronic fluid overload is associated with morbidity and mortality in hemodialysis patients. Optimizing the diagnosis and treatment of fluid overload remains a priority for the nephrology community. Although current methods of assessing fluid status, such as bioimpedance and lung ultrasound, have prognostic and diagnostic value, no single system or technique can be used to maintain euvolemia. The difficulty in maintaining and assessing fluid status led to a publication by the Kidney Health Initiative in 2019 aimed at fostering innovation in fluid management therapies. This review article focuses on the current limitations in our assessment of extracellular volume, and the novel technology and methods that can create a new paradigm for fluid management. The cardiology community has published research on multiparametric wearable devices that can create individualized predictions for heart failure events. In the future, similar wearable technology may be capable of tracking fluid changes during the interdialytic period and enabling behavioral change. Machine learning methods have shown promise in the prediction of volume-related adverse events. Similar methods can be leveraged to create accurate, automated predictions of dry weight that can potentially be used to guide ultrafiltration targets and interdialytic weight gain goals.

Machine Learning for Renal Pathologies: An Updated Survey

Within the literature concerning modern machine learning techniques applied to the medical field, there is a growing interest in the application of these technologies to the nephrological area, especially regarding the study of renal pathologies, because they are very common and widespread in our society, afflicting a high percentage of the population and leading to various complications, up to death in some cases. For these reasons, the authors have considered it appropriate to collect, using one of the major bibliographic databases available, and analyze the studies carried out until February 2022 on the use of machine learning techniques in the nephrological field, grouping them according to the addressed pathologies: renal masses, acute kidney injury, chronic kidney disease, kidney stone, glomerular disease, kidney transplant, and others less widespread. Of a total of 224 studies, 59 were analyzed according to inclusion and exclusion criteria in this review, considering the method used and the type of data available. Based on the study conducted, it is possible to see a growing trend and interest in the use of machine learning applications in nephrology, becoming an additional tool for physicians, which can enable them to make more accurate and faster diagnoses, although there remains a major limitation given the difficulty in creating public databases that can be used by the scientific community to corroborate and eventually make a positive contribution in this area.

Clinical Applications of Artificial Intelligence-An Updated Overview

Artificial intelligence has the potential to revolutionize modern society in all its aspects. Encouraged by the variety and vast amount of data that can be gathered from patients (e.g., medical images, text, and electronic health records), researchers have recently increased their interest in developing AI solutions for clinical care. Moreover, a diverse repertoire of methods can be chosen towards creating performant models for use in medical applications, ranging from disease prediction, diagnosis, and prognosis to opting for the most appropriate treatment for an individual patient. In this respect, the present paper aims to review the advancements reported at the convergence of AI and clinical care. Thus, this work presents AI clinical applications in a comprehensive manner, discussing the recent literature studies classified according to medical specialties. In addition, the challenges and limitations hindering AI integration in the clinical setting are further pointed out.

Implementing a fluid volume management program to decrease intra-dialytic hypotensive events in a paediatric in-centre haemodialysis unit: a quality improvement project

BACKGROUND

Intra-dialytic hypotension (IDH) is the most common serious adverse event in paediatric haemodialysis (HD). Repeated IDH results in chronic multi-organ damage and increased mortality. At the Hospital for Sick Children, Toronto, retrospective data from all in-centre HD sessions revealed frequently occurring IDH events (16.5 ± 5.6% of HD sessions per week). Based on literature review and clinical expertise, fluid volume management was selected as a potential modifiable risk factor to decrease IDH. Root causes identified as contributing to IDH were incorporated into a Paediatric haemodialysis fluid volume management (PedHDfluid) program using the Model for Improvement methodology including rapid cycles of change.

METHODS

Multiple measures were evaluated including (i) Outcome: IDH events per number of HD sessions per week; (ii) Process: number of changes to estimated dry weight per number of HD sessions per week; (iii) Balancing: time spent on dry weight meeting per week. Data was analysed using statistical process control charts. We aimed to decrease IDH in our dialysis unit to < 10% of HD sessions per week over a 6-month period by implementing a PedHDfluid program, including a multifaceted dry weight assessment protocol, multidisciplinary meetings and electronic health records "Dry Weight Evaluation flow sheet/synopsis".

RESULTS

The project resulted in a decline in IDH events from 16.5 ± 5.6% to 8.8 ± 3.3% of HD sessions per week. More frequent dry weight changes and increased awareness of fluid removal goals were noted.

CONCLUSIONS

A multidisciplinary approach including regular assessment, guidelines and systematic discussion, with an embedded electronic health record assessment and data gathering tool may sustainably reduce IDH events. A higher resolution version of the Graphical abstract is available as Supplementary information.

Predicting the Risk of Hypertension Based on Several Easy-to-Collect Risk Factors: A Machine Learning Method

Hypertension is a widespread chronic disease. Risk prediction of hypertension is an intervention that contributes to the early prevention and management of hypertension. The implementation of such intervention requires an effective and easy-to-implement hypertension risk prediction model. This study evaluated and compared the performance of four machine learning algorithms on predicting the risk of hypertension based on easy-to-collect risk factors. A dataset of 29,700 samples collected through a physical examination was used for model training and testing. Firstly, we identified easy-to-collect risk factors of hypertension, through univariate logistic regression analysis. Then, based on the selected features, 10-fold cross-validation was utilized to optimize four models, random forest (RF), CatBoost, MLP neural network and logistic regression (LR), to find the best hyper-parameters on the training set. Finally, the performance of models was evaluated by AUC, accuracy, sensitivity and specificity on the test set. The experimental results showed that the RF model outperformed the other three models, and achieved an AUC of 0.92, an accuracy of 0.82, a sensitivity of 0.83 and a specificity of 0.81. In addition, Body Mass Index (BMI), age, family history and waist circumference (WC) are the four primary risk factors of hypertension. These findings reveal that it is feasible to use machine learning algorithms, especially RF, to predict hypertension risk without clinical or genetic data. The technique can provide a non-invasive and economical way for the prevention and management of hypertension in a large population.

Bedside sonographic assessments for predicting predialysis fluid overload in children with end-stage kidney disease

Although the number of studies evaluating methods to predict fluid overload is increasing, the assessment of fluid status in children on dialysis is still fraught with inaccuracies. We aimed to evaluate the predictive capability of lung ultrasounds and the inferior vena cava collapsibility index (cIVC) in predialysis overhydration in children with end-stage kidney disease. Ten children with end-stage kidney disease who were on an intermittent hemodialysis program were included. The hydration status of the patients was clinically evaluated. Moreover, 30 predialysis and 30 postdialysis lung ultrasound, cIVC, and bioimpedance spectroscopy (BIS) measurements were performed. The median age of the participants was 14 (IQR, 13-15) years, and two (20%) were male. There was a strong positive correlation between the predialysis total number of B-lines and predialysis fluid overload (r=0.764, p<0.001). Additionally, there was a moderate negative correlation between predialysis cIVC and predialysis fluid overload (r=-0.599, p=0.002). Although the moderate correlation was determined between the postdialysis fluid overload and total number of B-lines, no correlation was determined using cIVC. Receiver operating characteristic curves demonstrated that the total number of B-lines and cIVC could successfully predict the predialysis fluid overload (relative hydration >7% derived from the BIS; AUROC 0.82 and 0.80, respectively). When both evaluations were combined, if either the total number of B-lines or the cIVC was outside the corresponding cutoff range (>10.5 and ≤23.5, respectively), it was detected in 16 out of 17 sessions (sensitivity 94%). If either one was outside the corresponding cutoff range (total number of B-lines >10.5 and cIVC ≤18.2), the severe predialysis fluid overload was predicted successfully in all eight (100%) sessions. Conclusion: Randomized controlled studies are needed to prove the reliability of the combined use of lung ultrasounds and cIVC in the assessment of predialysis fluid overload. What is Known: • The association of chronic fluid overload with increased morbidity and mortality raises the need for optimal determination of fluid overload in pediatric patients who are dialysis-dependent at a young age. • The linear correlation between the total number of B-lines on lung ultrasound images and fluid overload by weight has been shown. What is New: • This study evaluates the lung ultrasound and inferior vena cava collapsibility index combined in predicting fluid overload in dialytic children. • If either the total number of B-lines or the cIVC was outside the corresponding cutoff range (>10.5 and cIVC ≤18.2, respectively), the severe predialysis fluid overload was predicted successfully in all eight (100%) sessions.

Dialysis adequacy predictions using a machine learning method

Dialysis adequacy is an important survival indicator in patients with chronic hemodialysis. However, there are inconveniences and disadvantages to measuring dialysis adequacy by blood samples. This study used machine learning models to predict dialysis adequacy in chronic hemodialysis patients using repeatedly measured data during hemodialysis. This study included 1333 hemodialysis sessions corresponding to the monthly examination dates of 61 patients. Patient demographics and clinical parameters were continuously measured from the hemodialysis machine; 240 measurements were collected from each hemodialysis session. Machine learning models (random forest and extreme gradient boosting [XGBoost]) and deep learning models (convolutional neural network and gated recurrent unit) were compared with multivariable linear regression models. The mean absolute percentage error (MAPE), root mean square error (RMSE), and Spearman's rank correlation coefficient (Corr) for each model using fivefold cross-validation were calculated as performance measurements. The XGBoost model had the best performance among all methods (MAPE = 2.500; RMSE = 2.906; Corr = 0.873). The deep learning models with convolutional neural network (MAPE = 2.835; RMSE = 3.125; Corr = 0.833) and gated recurrent unit (MAPE = 2.974; RMSE = 3.230; Corr = 0.824) had similar performances. The linear regression models had the lowest performance (MAPE = 3.284; RMSE = 3.586; Corr = 0.770) compared with other models. Machine learning methods can accurately infer hemodialysis adequacy using continuously measured data from hemodialysis machines.

Wearable Bioimpedance Monitoring: Viewpoint for Application in Chronic Conditions

Currently, nearly 6 in 10 US adults are suffering from at least one chronic condition. Wearable technology could help in controlling the health care costs by remote monitoring and early detection of disease worsening. However, in recent years, there have been disappointments in wearable technology with respect to reliability, lack of feedback, or lack of user comfort. One of the promising sensor techniques for wearable monitoring of chronic disease is bioimpedance, which is a noninvasive, versatile sensing method that can be applied in different ways to extract a wide range of health care parameters. Due to the changes in impedance caused by either breathing or blood flow, time-varying signals such as respiration and cardiac output can be obtained with bioimpedance. A second application area is related to body composition and fluid status (eg, pulmonary congestion monitoring in patients with heart failure). Finally, bioimpedance can be used for continuous and real-time imaging (eg, during mechanical ventilation). In this viewpoint, we evaluate the use of wearable bioimpedance monitoring for application in chronic conditions, focusing on the current status, recent improvements, and challenges that still need to be tackled.

On the potential of wearable bioimpedance for longitudinal fluid monitoring in end-stage kidney disease

Bioimpedance spectroscopy (BIS) has proven to be a promising non-invasive technique for fluid monitoring in HD patients. While current BIS-based monitoring of pre- and post-dialysis fluid status utilizes benchtop devices, designed for intramural use, advancements in micro-electronics have enabled the development of wearable bioimpedance systems. Wearable systems meanwhile can offer a similar frequency range for current injection as commercially available benchtop devices. This opens opportunities for unobtrusive longitudinal fluid status monitoring, including transcellular fluid shifts, with the ultimate goal of improving fluid management, thereby lowering mortality and improving quality of life for HD patients. Ultra-miniaturized wearable devices can also offer simultaneous acquisition of multiple other parameters, including hemodynamic parameters. Combination of wearable BIS and additional longitudinal multiparametric data may aid in the prevention of both hemodynamic instability as well as fluid overload. The opportunity to also acquire data during interdialytic periods using wearable devices likely will give novel pathophysiological insights and the development of smart (predicting) algorithms could contribute to personalizing dialysis schemes and ultimately to autonomous (nocturnal) home dialysis. This review provides an overview of current research regarding wearable bioimpedance, with special attention to applications in ESKD patients. Furthermore, we present an outlook on the future use of wearable bioimpedance within dialysis practice.

Volume overload in hemodialysis: diagnosis, cardiovascular consequences, and management

Volume overload in haemodialysis (HD) patients associates with hypertension and cardiac dysfunction and is a major risk factor for all-cause and cardiovascular mortality in this population. The diagnosis of volume excess and estimation of dry weight is based largely on clinical criteria and has a notoriously poor diagnostic accuracy. The search for accurate and objective methods to evaluate dry weight and to diagnose subclinical volume overload has been intensively pursued over the last 3 decades. Most methods have not been tested in appropriate clinical trials and their usefulness in clinical practice remains uncertain, except for bioimpedance spectroscopy and lung ultrasound (US). Bioimpedance spectroscopy is possibly the most widely used method to subjectively quantify fluid distributions over body compartments and produces reliable and reproducible results. Lung US provides reliable estimates of extravascular water in the lung, a critical parameter of the central circulation that in large part reflects the left ventricular end-diastolic pressure. To maximize cardiovascular tolerance, fluid removal in volume-expanded HD patients should be gradual and distributed over a sufficiently long time window. This review summarizes current knowledge about the diagnosis, prognosis and treatment of volume overload in HD patients.

Sodium, volume and pressure control in haemodialysis patients for improved cardiovascular outcomes

Chronic volume overload is pervasive in patients on chronic haemodialysis and substantially increases the risk of cardiovascular death. The rediscovery of the three-compartment model in sodium metabolism revolutionizes our understanding of sodium (patho-)physiology and is an effect modifier that still needs to be understood in the context of hypertension and end-stage kidney disease. Assessment of fluid overload in haemodialysis patients is central yet difficult to achieve, because traditional clinical signs of volume overload lack sensitivity and specificity. The highest all-cause mortality risk may be found in haemodialysis patients presenting with high fluid overload but low blood pressure before haemodialysis treatment. The second highest risk may be found in patients with both high blood pressure and fluid overload, while high blood pressure but normal fluid overload may only relate to moderate risk. Optimization of fluid overload in haemodialysis patients should be guided by combining the traditional clinical evaluation with objective measurements such as bioimpedance spectroscopy in assessing the risk of fluid overload. To overcome the tide of extracellular fluid, the concept of time-averaged fluid overload during the interdialytic period has been established and requires possible readjustment of a negative target post-dialysis weight. ²³Na-magnetic resonance imaging studies will help to quantitate sodium accumulation and keep prescribed haemodialytic sodium mass balance on the radar. Cluster-randomization trials (e.g. on sodium removal) are underway to improve our therapeutic approach to cardioprotective haemodialysis management.

Evaluation of Hypervolemia in Children

Hypervolemia is a condition with an excess of total body water and when sodium (Na) intake exceeds output. It can have different causes, such as hypervolemic hyponatremia (often associated with decreased, effective circulating blood volume), hypervolemia associated with metabolic alkalosis, and end-stage renal disease. The degree of hypervolemia in critically ill children is a risk factor for mortality, regardless of disease severity. A child (under 18 years of age) with hypervolemia requires fluid removal and fluid restriction. Diuretics are able to increase or maintain urine output and thus improve fluid and nutrition management, but their benefit in preventing or treating acute kidney injury is questionable.

Using Artificial Intelligence Resources in Dialysis and Kidney Transplant Patients: A Literature Review

BACKGROUND

The purpose of this review is to depict current research and impact of artificial intelligence/machine learning (AI/ML) algorithms on dialysis and kidney transplantation. Published studies were presented from two points of view: What medical aspects were covered? What AI/ML algorithms have been used?

METHODS

We searched four electronic databases or studies that used AI/ML in hemodialysis (HD), peritoneal dialysis (PD), and kidney transplantation (KT). Sixty-nine studies were split into three categories: AI/ML and HD, PD, and KT, respectively. We identified 43 trials in the first group, 8 in the second, and 18 in the third. Then, studies were classified according to the type of algorithm.

RESULTS

AI and HD trials covered: (a) dialysis service management, (b) dialysis procedure, (c) anemia management, (d) hormonal/dietary issues, and (e) arteriovenous fistula assessment. PD studies were divided into (a) peritoneal technique issues, (b) infections, and (c) cardiovascular event prediction. AI in transplantation studies were allocated into (a) management systems (ML used as pretransplant organ-matching tools), (b) predicting graft rejection, (c) tacrolimus therapy modulation, and (d) dietary issues.

CONCLUSIONS

Although guidelines are reluctant to recommend AI implementation in daily practice, there is plenty of evidence that AI/ML algorithms can predict better than nephrologists: volumes, Kt/V, and hypotension or cardiovascular events during dialysis. Altogether, these trials report a robust impact of AI/ML on quality of life and survival in G5D/T patients. In the coming years, one would probably witness the emergence of AI/ML devices that facilitate the management of dialysis patients, thus increasing the quality of life and survival.

Effect of hemodialysis on impedance cardiography (electrical velocimetry) parameters in children

BACKGROUND

Pediatric hemodialysis (HD) patients have a high incidence of cardiovascular morbidity and mortality. The study aim was to investigate whether impedance cardiography (electrical velocimetry, EV) is suitable as a hemodynamic trend monitoring tool in pediatric patients during HD.

METHODS

Measurements by EV were obtained before, during, and after HD in a prospective single-center pediatric observational study. In total, 54 dialysis cycles in four different pediatric patients with end-stage kidney disease on chronic HD were included. EV parameters analyzed were heart rate (HR), stroke volume (SV), stroke volume index (SI), cardiac output (CO), cardiac index (CI), thoracic fluid content (TFC), index of contractility (ICON), stroke volume variation (SVV), variation of ICON (VIC), R-R interval (TRR), pre-ejection period (PEP), left ventricular ejection time (LVET), and systolic time ration (STR). Systemic vascular resistance index (SVRI) was calculated.

RESULTS

EV did measure significant changes in cardiovascular parameters associated with HD. The following parameters increased after HD: HR (9%), SVV (19%), VIC (33%), PEP (8%), and STR (18%). A decrease after HD was measured in SV (18%), SI (18%), CO (10%), CI (10%), TFC (10%), ICON (7%), TRR (7%), LVET (8%), and LVET (8%). SVRI was not affected by HD. The changes were correlated to ultrafiltration. HD cycles without fluid withdrawal also altered cardiovascular parameters.

CONCLUSIONS

Pediatric HD with and without fluid withdrawal changes hemodynamic EV monitoring parameters. Possibly EV may be useful to optimize HD management in pediatric patients.

A Practical Electronic Health Record-Based Dry Weight Supervision Model for Hemodialysis Patients

Objective: Dry Weight (DW) is a typical hemodialysis (HD) prescription for End-Stage Renal Disease (ESRD) patients. However, an accurate DW assessment is difficult due to the complication of body components and individual variations. Our objective is to model a clinically practicable DW estimator. Method: We proposed a time series-based regression method to evaluate the weight fluctuation of HD patients according to Electronic Health Record (EHR). A total of 34 patients with 5100 HD sessions data were selected and partitioned into three groups; in HD-stabilized, HD-intolerant, and near-death. Each group’s most recent 150 HD sessions data were adopted to evaluate the proposed model. Results: Within a 0.5 kg absolute error margin, our model achieved 95.44%, 91.95%, and 83.12% post-dialysis weight prediction accuracies for the HD-stabilized, HD-intolerant, and near-death groups, respectively. Within a 1%relative error margin, the proposed method achieved 97.99%, 95.36%, and 66.38% accuracies. For HD-stabilized patients, the Mean Absolute Error (MAE) of the proposed method was 0.17 kg ± 0.04 kg. In the model comparison experiment, the performance test showed that the quality of the proposed model was superior to those of the state-of-the-art models. Conclusion: The outcome of this research indicates that the proposed model could potentially automate the clinical weight management for HD patients. Clinical Impact: This work can aid physicians to monitor and estimate DW. It can also be a health risk indicator for HD patients.

Artificial Intelligence in Nephrology: Core Concepts, Clinical Applications, and Perspectives

Artificial intelligence is playing an increasingly important role in many fields of medicine, assisting physicians in most steps of patient management. In nephrology, artificial intelligence can already be used to improve clinical care, hemodialysis prescriptions, and follow-up of transplant recipients. However, many nephrologists are still unfamiliar with the basic principles of medical artificial intelligence. This review seeks to provide an overview of medical artificial intelligence relevant to the practicing nephrologist, in all fields of nephrology. We define the core concepts of artificial intelligence and machine learning and cover the basics of the functioning of neural networks and deep learning. We also discuss the most recent clinical applications of artificial intelligence in nephrology and medicine; as an example, we describe how artificial intelligence can predict the occurrence of progressive immunoglobulin A nephropathy. Finally, we consider the future of artificial intelligence in clinical nephrology and its impact on medical practice, and conclude with a discussion of the ethical issues that the use of artificial intelligence raises in terms of clinical decision making, physician-patient relationship, patient privacy, and data collection.

Beyond playing games: nephrologist vs machine in pediatric dialysis prescribing

In a recent article in Pediatric Nephrology, Olivier Niel and colleagues applied an artificial intelligence algorithm to a clinical problem that continues to challenge experienced pediatric nephrologists: optimizing the target weight of children on dialysis. They compared blood pressure, antihypertensive medication and intradialytic symptoms in children whose target weight was prescribed firstly by a nephrologist, then subsequently using a machine learning algorithm. Improvements in all outcome measures are reported. Their innovative approach to tackling this important clinical problem appears promising. In this editorial, we discuss the strengths and weaknesses of their study and consider to what extent machine learning strategies are suited to optimizing pediatric dialysis outcomes.