European Nephrologists' Attitudes toward the Application of Artificial Intelligence in Clinical Practice: A Comprehensive Survey.

INTRODUCTION: The rapid advancement of artificial intelligence and big data analytics, including descriptive, diagnostic, predictive, and prescriptive analytics, has the potential to revolutionize many areas of medicine, including nephrology and dialysis. Artificial intelligence and big data analytics can be used to analyze large amounts of patient medical records, including laboratory results and imaging studies, to improve the accuracy of diagnosis, enhance early detection, identify patterns and trends, and personalize treatment plans for patients with kidney disease. Additionally, artificial intelligence and big data analytics can be used to identify patients' treatment who are not receiving adequate care, highlighting care inefficiencies in the dialysis provider, optimizing patient outcomes, reducing healthcare costs, and consequently creating values for all the involved stakeholders. OBJECTIVES: We present the results of a comprehensive survey aimed at exploring the attitudes of European physicians from eight countries working within a major hemodialysis network (Fresenius Medical Care NephroCare) toward the application of artificial intelligence in clinical practice. METHODS: An electronic survey on the implementation of artificial intelligence in hemodialysis clinics was distributed to 1,067 physicians. Of the 1,067 individuals invited to participate in the study, 404 (37.9%) professionals agreed to participate in the survey. RESULTS: The survey showed that a substantial proportion of respondents believe that artificial intelligence has the potential to support physicians in reducing medical malpractice or mistakes. CONCLUSION: While artificial intelligence's potential benefits are recognized in reducing medical errors and improving decision-making, concerns about treatment plan consistency, personalization, privacy, and the human aspects of patient care persist. Addressing these concerns will be crucial for successfully integrating artificial intelligence solutions in nephrology practice.

Long-term mortality risk associated with citric acid- and acetic acid-based bicarbonate haemodialysis: a historical cohort propensity score-matched study in a large, multicentre, population-based study.

BACKGROUND: Citric acid-based bicarbonate dialysate (CiD) is increasingly used in haemodialysis (HD) to improve haemodynamic tolerance and haemocompatibility associated with acetic acid-based bicarbonate dialysate. Safety concerns over CiD have been raised recently after a French ecological study reported higher mortality hazard in HD clinics with high CiD consumption. Therefore, we evaluated the mortality risk associated with various acidifiers (AcD, CiD) of bicarbonate dialysate. METHODS: In this multicentre, historical cohort study, we included adult incident HD patients (European, Middle-East and Africa Fresenius Medical Care network; 1 January 2014 to 31 October 2018). We recorded acidifiers of bicarbonate dialysis and dialysate composition for each dialysis session. In the primary intention-to-treat analysis, patients were assigned to the exposed group if they received CiD in >70% of sessions during the first 3 months (CiD70%), whereas the non-exposed group received no CiD at all. In the secondary analysis, exposure was assessed on a monthly basis for the whole duration of the follow-up. RESULTS: We enrolled 10 121 incident patients during the study period. Of them, 371 met the criteria for inclusion in CiD70%. After propensity score matching, mortality was 11.43 [95% confidence interval (CI) 8.86-14.75] and 12.04 (95% CI 9.44-15.35) deaths/100 person-years in the CiD0% and CiD70% groups, respectively (P = 0.80). A similar association trend was observed in the secondary analysis. CONCLUSIONS: We did not observe evidence of increased mortality among patients exposed to CiD in a large European cohort of dialysis patients despite the fact that physicians were more inclined to prescribe CiD to subjects with worse medical conditions.

Longitudinal Changes in Body Composition in Patients After Initiation of Hemodialysis Therapy: Results From an International Cohort.

OBJECTIVE: In patients with advanced kidney disease, metabolic and nutritional derangements induced by uremia interact and reinforce each other in a deleterious vicious circle. Literature addressing the effect of dialysis initiation on changes in body composition (BC) is limited and contradictory. The aim of this study was to evaluate changes in BC in a large international cohort of incident hemodialysis patients. METHODS: A total of 8,227 incident adult end-stage renal disease patients with BC evaluation within the initial first 6 months of baseline, defined as 6 months after renal replacement therapy initiation, were considered. BC, including fat tissue index (FTI) and lean tissue index (LTI), were evaluated by Body Composition Monitor (BCM, Fresenius Medical Care, Bad Homburg, Germany). Exclusion criteria at baseline were lack of a BCM measurement before or after baseline, body mass index (BMI) < 18.5 kg/m(2), presence of metastatic solid tumors, treatment with a catheter, and prescription of less or more than 3 treatments per week. Maximum follow-up was 2 years. Descriptive analysis was performed comparing current values with the baseline in each interval (delta analysis). Linear mixed models considering the correlation structure of the repeated measurements were used to evaluate factors associated with different trends in FTI and LTI. RESULTS: BMI increased about 0.6 kg/m(2) over 24 months from baseline. This was associated with increase in FTI of about 0.95 kg/m(2) and a decrease in LTI of about 0.4 kg/m(2). Female gender, diabetic status, and low baseline FTI were associated with a significant greater increase of FTI. Age > 67 years, diabetes, male gender, high baseline LTI, and low baseline FTI were associated with a significant greater decrease of LTI. CONCLUSIONS: With the transition to hemodialysis, end-stage renal disease patients presented with distinctive changes in BC. These were mainly associated with gender, older age, presence of diabetes, low baseline FTI, and high baseline LTI. BMI increases did not fully represent the changes in BC.

Modifiable factors associated with achievement of high-volume post-dilution hemodiafiltration: results from an international study.

BACKGROUND: The aim was to investigate factors associated with the successful achievement of ≥21 l/session of substitution fluid volume in patients on post-dilution hemodiafiltration. METHODS: 3315 patients treated in 6 European countries with the Fresenius 5008 CorDiax machine including the AutoSub Plus feature were considered. Variables that showed a relationship with convection volume were entered in a multivariable logistic regression model. RESULTS: Mean blood flow was 379 ± 68 ml/min. Median substitution volume was 24.7 L (IQR 22.0-27.4 L). Mean filtration fraction was 28.3 ± 4.1%. 81.5% of sessions qualified as high-volume HDF (substitution volumes ≥21 L). Higher age, dialyzer surface area, blood flow and treatment time were positively associated with the achievement of ≥21 L substitution volume; higher body mass index, male gender, higher hematocrit, graft or catheter vs. fistula, and start of week vs. mid-week were negatively associated. CONCLUSIONS: Dialysis center policy in terms of blood flow, treatment time, filter size, and perhaps even hemoglobin targets plays a key role in achieving high-volume HDF. All of these are modifiable factors that can help in prescribing an optimal combination of dialyzer size, achievable blood flows, and treatment times.

Guided optimization of fluid status in haemodialysis patients.

BACKGROUND: Achieving normohydration remains a non-trivial issue in haemodialysis therapy. Guiding the haemodialysis patient on the path between fluid overload and dehydration should be the clinical target, although it can be difficult to achieve this target in practice. Objective and clinically applicable methods for the determination of the normohydration status on an individual basis are needed to help in the identification of an appropriate target weight. METHODS: The aim of this prospective trial was to guide the patient population of a complete dialysis centre towards normohydration over the course of approximately 1 year. Fluid status was assessed frequently (at least monthly) in haemodialysis patients (n = 52) with the body composition monitor (BCM), which is based on whole body bioimpedance spectroscopy. The BCM provides the clinician with an objective target for normohydration. The patient population was divided into three groups: the hyperhydrated group (relative fluid overload >15% of extracellular water (ECW); n = 13; Group A), the adverse event group (patients with more than two adverse events in the last 4 weeks; n = 12; Group B) and the remaining patients (n = 27; Group C). RESULTS: In the hyperhydrated group (Group A), fluid overload was reduced by 2.0 L (P < 0.001) without increasing the occurrence of intradialytic adverse events. This resulted in a reduction in systolic blood pressure of 25 mmHg (P = 0.012). Additionally, a 35% reduction in antihypertensive medication (P = 0.031) was achieved. In the adverse event group (Group B), the fluid status was increased by 1.3 L (P = 0.004) resulting in a 73% reduction in intradialytic adverse events (P < 0.001) without significantly increasing the blood pressure. CONCLUSION: The BCM provides an objective assessment of normohydration that is clinically applicable. Guiding the patients towards this target of normohydration leads to better control of hypertension in hyperhydrated patients, less intradialytic adverse events and improved cardiac function.

Importance of whole-body bioimpedance spectroscopy for the management of fluid balance.

INTRODUCTION: Achieving normohydration remains a non-trivial issue in haemodialysis therapy. Preventing the deleterious effects of fluid overload and dehydration is difficult to achieve. Objective and clinically applicable methods for the determination of a target representing normohydration are needed. METHODS: Whole-body bioimpedance spectroscopy (50 frequencies, 5-1,000 kHz) in combination with a physiologic tissue model can provide an objective target for normohydration based on the concept of excess extracellular volume. We review the efficacy of this approach in a number of recent clinical applications. The accuracy to determine fluid volumes (e.g. extracellular water), body composition (e.g. fat mass) and fluid overload was evaluated in more than 1,000 healthy individuals and patients against available gold standard reference methods (e.g. bromide, deuterium, dual-energy X-ray absorptiometry, air displacement plethysmography, clinical assessment). RESULTS: The comparison with gold standard methods showed excellent accordance [e.g. R(2) (total body water) = 0.88; median +/- SD (total body water) = -0.17 +/- 2.7 litres]. Agreement with high-quality clinical assessment of fluid status was demonstrated in several hundred patients (median +/- SD = -0.23 +/- 1.5 litres). The association between ultrafiltration volume and change in fluid overload was reflected well by the method (median +/- SD = 0.015 +/- 0.8 litres). The predictive value of fluid overload on mortality underlines forcefully the clinical relevance of the normohydration target, being secondary only to the presence of diabetes. The objective normohydration target could be achieved in prevalent haemodialysis patients leading to an improvement in hypertension and reduction of adverse events. CONCLUSION: Whole-body bioimpedance spectroscopy in combination with a physiologic tissue model provides for the first time an objective and relevant target for clinical dry weight assessment.

Towards improved cardiovascular management: the necessity of combining blood pressure and fluid overload.

BACKGROUND: Hypertension and fluid overload (FO) are well-recognized problems in the chronic kidney disease (CKD) population. While the prevalence of hypertension is well documented, little is known about the severity of FO in this population. METHODS: A new bioimpedance spectroscopy device (BCM-Body Composition Monitor) was selected that allows quantitative determination of the deviation in hydration status from normal ranges (DeltaHS). Pre-dialysis systolic blood pressure (BPsys) and DeltaHS was analysed in 500 haemodialysis patients from eight dialysis centres. A graphical tool (HRP-hydration reference plot) was devised allowing DeltaHS to be combined with measurements of BPsys enabling comparison with a matched healthy population (n = 1244). RESULTS: Nineteen percent of patients (n = 95) were found to have normal BPsys and DeltaHS in the normal range. Approximately one-third of patients (n = 133) exhibited reasonable control of BPsys and fluids (BPsys <150 mmHg and DeltaHS <2.5 L). In only 15% of patients (n = 74) was hypertension observed (BPsys >150 mmHg) with a concomitant DeltaHS >2.5 L (possible volume-dependent hypertension). In contrast, 13% of patients (n = 69) were hypertensive with DeltaHS <1.1 L (possible essential hypertension). In 10% of patients (n = 52), BPsys <140 mmHg was recorded despite DeltaHS exceeding 2.5 L. CONCLUSION: Our study illustrated the wide variability in BPsys regardless of the degree of DeltaHS. The HRP provides an invaluable tool for classifying patients in terms of BPsys and DeltaHS and the proximity of these parameters to reference ranges. This represents an important step towards more objective choice of strategies for the optimal treatment of hypertension and FO. Further studies are required to assess the prognostic and therapeutic role of the HRP.