The Use of Anemia Control Model Is Associated with Improved Hemoglobin Target Achievement, Lower Rates of Inappropriate Erythropoietin Stimulating Agents, and Severe Anemia among Dialysis Patients.

INTRODUCTION: The Anemia Control Model (ACM) is a certified medical device suggesting the optimal ESA and iron dosage for patients on hemodialysis. We sought to assess the effectiveness and safety of ACM in a large cohort of hemodialysis patients. METHODS: This is a retrospective study of dialysis patients treated in NephroCare centers between June 1, 2013 and December 31, 2019. We compared patients treated according to ACM suggestions and patients treated in clinics where ACM was not activated. We stratified patients belonging to the reference group by historical target achievement rates in their referral centers (tier 1: <70%; tier 2: 70-80%; tier 3: >80%). Groups were matched by propensity score. RESULTS: After matching, we obtained four groups with 85,512 patient-months each. ACM had 18% higher target achievement rate, 63% smaller inappropriate ESA administration rate, and 59% smaller severe anemia risk compared to Tier 1 centers (all p < 0.01). The corresponding risk ratios for ACM compared to Tier 2 centers were 1.08 (95% CI: 1.08-1.09), 0.49 (95% CI: 0.47-0.51), and 0.64 (95% CI: 0.61-0.68); for ACM compared to Tier 3 centers, 1.01 (95% CI: 1.01-1.02), 0.66 (95% CI: 0.63-0.69), and 0.94 (95% CI: 0.88-1.00), respectively. ACM was associated with statistically significant reductions in ESA dose administration. CONCLUSION: ACM was associated with increased hemoglobin target achievement rate, decreased inappropriate ESA usage and a decreased incidence of severe anemia among patients treated according to ACM suggestion.

From electronic health records to clinical management systems: how the digital transformation can support healthcare services.

Healthcare systems worldwide are currently undergoing significant transformations in response to increasing costs, a shortage of healthcare professionals and the growing complexity of medical needs among the population. Value-based healthcare reimbursement systems are emerging as an attempt to incentivize patient-centricity and cost containment. From a technological perspective, the transition to digitalized services is intended to support these transformations. A Health Information System (HIS) is a technological solution designed to govern the data flow generated and consumed by healthcare professionals and administrative staff during the delivery of healthcare services. However, the exponential growth of digital capabilities and applied advanced analytics has expanded their traditional functionalities and brought the promise of automating administrative procedures and simple repetitive tasks, while enhancing the efficiency and outcomes of healthcare services by incorporating decision support tools for clinical management. The future of HIS is headed towards modular architectures that can facilitate implementation and adaptation to different environments and systems, as well as the integration of various tools, such as artificial intelligence (AI) models, in a seamless way. As an example, we present the experience and future developments of the European Clinical Database (EuCliD®). EuCliD is a multilingual HIS used by 20 000 nurses and physicians on a daily basis to manage 105 000 patients treated in 1100 clinics in 43 different countries. EuCliD encompasses patients' follow-up, automatic reporting and mobile applications while enabling efficient management of clinical processes. It is also designed to incorporate multiagent systems to automate repetitive tasks, AI modules and advanced dynamic dashboards.

The Cardiovascular Literature-Based Risk Algorithm (CALIBRA): Predicting Cardiovascular Events in Patients With Non-Dialysis Dependent Chronic Kidney Disease.

Background and Objectives: Cardiovascular (CV) disease is the main cause of morbidity and mortality in patients suffering from chronic kidney disease (CKD). Although it is widely recognized that CV risk assessment represents an essential prerequisite for clinical management, existing prognostic models appear not to be entirely adequate for CKD patients. We derived a literature-based, naïve-bayes model predicting the yearly risk of CV hospitalizations among patients suffering from CKD, referred as the CArdiovascular, LIterature-Based, Risk Algorithm (CALIBRA). Methods: CALIBRA incorporates 31 variables including traditional and CKD-specific risk factors. It was validated in two independent CKD populations: the FMC NephroCare cohort (European Clinical Database, EuCliD®) and the German Chronic Kidney Disease (GCKD) study prospective cohort. CALIBRA performance was evaluated by c-statistics and calibration charts. In addition, CALIBRA discrimination was compared with that of three validated tools currently used for CV prediction in CKD, namely the Framingham Heart Study (FHS) risk score, the atherosclerotic cardiovascular disease risk score (ASCVD), and the Individual Data Analysis of Antihypertensive Intervention Trials (INDANA) calculator. Superiority was defined as a ΔAUC>0.05. Results: CALIBRA showed good discrimination in both the EuCliD® medical registry (AUC 0.79, 95%CI 0.76-0.81) and the GCKD cohort (AUC 0.73, 95%CI 0.70-0.76). CALIBRA demonstrated improved accuracy compared to the benchmark models in EuCliD® (FHS: ΔAUC=-0.22, p<0.001; ASCVD: ΔAUC=-0.17, p<0.001; INDANA: ΔAUC=-0.14, p<0.001) and GCKD (FHS: ΔAUC=-0.16, p<0.001; ASCVD: ΔAUC=-0.12, p<0.001; INDANA: ΔAUC=-0.04, p<0.001) populations. Accuracy of the CALIBRA score was stable also for patients showing missing variables. Conclusion: CALIBRA provides accurate and robust stratification of CKD patients according to CV risk and allows score calculations with improved accuracy compared to established CV risk scores also in real-world clinical cohorts with considerable missingness rates. Our results support the generalizability of CALIBRA across different CKD populations and clinical settings.

Validation of a Novel Predictive Algorithm for Kidney Failure in Patients Suffering from Chronic Kidney Disease: The Prognostic Reasoning System for Chronic Kidney Disease (PROGRES-CKD).

Current equation-based risk stratification algorithms for kidney failure (KF) may have limited applicability in real world settings, where missing information may impede their computation for a large share of patients, hampering one from taking full advantage of the wealth of information collected in electronic health records. To overcome such limitations, we trained and validated the Prognostic Reasoning System for Chronic Kidney Disease (PROGRES-CKD), a novel algorithm predicting end-stage kidney disease (ESKD). PROGRES-CKD is a naïve Bayes classifier predicting ESKD onset within 6 and 24 months in adult, stage 3-to-5 CKD patients. PROGRES-CKD trained on 17,775 CKD patients treated in the Fresenius Medical Care (FMC) NephroCare network. The algorithm was validated in a second independent FMC cohort (n = 6760) and in the German Chronic Kidney Disease (GCKD) study cohort (n = 4058). We contrasted PROGRES-CKD accuracy against the performance of the Kidney Failure Risk Equation (KFRE). Discrimination accuracy in the validation cohorts was excellent for both short-term (stage 4-5 CKD, FMC: AUC = 0.90, 95%CI 0.88-0.91; GCKD: AUC = 0.91, 95% CI 0.86-0.97) and long-term (stage 3-5 CKD, FMC: AUC = 0.85, 95%CI 0.83-0.88; GCKD: AUC = 0.85, 95%CI 0.83-0.88) forecasting horizons. The performance of PROGRES-CKD was non-inferior to KFRE for the 24-month horizon and proved more accurate for the 6-month horizon forecast in both validation cohorts. In the real world setting captured in the FMC validation cohort, PROGRES-CKD was computable for all patients, whereas KFRE could be computed for complete cases only (i.e., 30% and 16% of the cohort in 6- and 24-month horizons). PROGRES-CKD accurately predicts KF onset among CKD patients. Contrary to equation-based scores, PROGRES-CKD extends to patients with incomplete data and allows explicit assessment of prediction robustness in case of missing values. PROGRES-CKD may efficiently assist physicians' prognostic reasoning in real-life applications.

How to assess the risks associated with the usage of a medical device based on predictive modeling: the case of an anemia control model certified as medical device.

BACKGROUND: The successful application of Machine Learning (ML) to many clinical problems can lead to its implementation as a medical device (MD), which is important to assess the associated risks. METHODS: An anemia control model (ACM), certified as MD, may face adverse events as a result of wrong predictions that are translated into suggestions of doses of erythropoietic stimulating agents to dialysis patients. Risks are assessed as the combination of severity and probability of a given hazard. While severities are typically assessed by clinicians, probabilities are tightly related to the performance of the predictive model. RESULTS: A postmarketing data set formed by all adult patients registered in French, Portuguese, and Spanish clinics, belonging to an international network, was considered; 3876 patients and 11,508 suggestions were eventually included. The achieved results show that there are no statistical differences between the probabilities of adverse events that are estimated in the ACM test set (using only Spanish clinics) and those actually observed in the postmarketing cohort. CONCLUSIONS: The risks of an ACM-MD can be accurately and robustly estimated, thus enhancing patients' safety. The proposed methodology is applicable to other clinical decisions based on predictive models since our proposal does not depend on the particular predictive model.

Predicting mortality in hemodialysis patients using machine learning analysis.

BACKGROUND: Besides the classic logistic regression analysis, non-parametric methods based on machine learning techniques such as random forest are presently used to generate predictive models. The aim of this study was to evaluate random forest mortality prediction models in haemodialysis patients. METHODS: Data were acquired from incident haemodialysis patients between 1995 and 2015. Prediction of mortality at 6 months, 1 year and 2 years of haemodialysis was calculated using random forest and the accuracy was compared with logistic regression. Baseline data were constructed with the information obtained during the initial period of regular haemodialysis. Aiming to increase accuracy concerning baseline information of each patient, the period of time used to collect data was set at 30, 60 and 90 days after the first haemodialysis session. RESULTS: There were 1571 incident haemodialysis patients included. The mean age was 62.3 years and the average Charlson comorbidity index was 5.99. The mortality prediction models obtained by random forest appear to be adequate in terms of accuracy [area under the curve (AUC) 0.68-0.73] and superior to logistic regression models (ΔAUC 0.007-0.046). Results indicate that both random forest and logistic regression develop mortality prediction models using different variables. CONCLUSIONS: Random forest is an adequate method, and superior to logistic regression, to generate mortality prediction models in haemodialysis patients.

Practice Patterns and Outcomes of Online Hemodiafiltration: A Real-World Evidence Study in a Russian Dialysis Network.

BACKGROUND: Evidence suggests that online hemodiafiltration (OL-HDF) is associated with improved survival. Whether the dose-response relationship between convective volume and mortality may be confounded by selection bias or descends from practice patterns is not clear. We sought to evaluate the role of patients' characteristics and practice patterns on OL-HDF dose and mortality in a large private dialysis network in the Republic of Russia. METHODS: In this multicenter, historical cohort study, we included adult incident patients on OL-HDF with at least 90 days of survival on renal replacement therapy in centers belonging to the Russian Federation Fresenius Medical Care network (January 1, 2011, to December 31, 2016). We evaluated predictors and outcomes (survival) of substitution volume target achievement (Qsub > 21 L/session). RESULTS: Among 1,081 enrolled patients, the average Qsub was 22.9 (±3.2) L/session; the mean ultrafiltration volume was 1.6 (±0.8) L/session. The mean age was 55.8 ± 13.2; 42% were woman. Most common comorbidities were congestive heart failure (39.7%) and peripheral vascular disease (21.7%). The average hemoglobin was 9.3 ± 1.3. The case-mix adjusted center effect accounted for 20% of variance in Qsub. The top 10 most important variables associated with higher Qsub were effective Qb, serum protein, Charlson's comorbidity index, hemoglobin, year of dialysis initiation (proxy of high Qsub treatment policy in the clinic network), predialysis heart rate, serum bicarbonate, serum phosphate, age, serum sodium, and dry body weight. In addition, we found that the association of Qb with Qsub is moderated by year of enrollment, intradialytic weight gain, and coronary artery disease, whereas higher hemoglobin concentration moderated the relationship between treatment time and Qsub. Finally, Qsub between 21 and 25 L/session was associated with longer 5-year survival. CONCLUSIONS: Both center-dependent clinical practice standards and patient clinical conditions substantially contributed to the risk of low Qsub. We confirmed previous evidence indicating better survival among patients with Qsub ≥ 21 L/session.

Enhanced prediction of hemoglobin concentration in a very large cohort of hemodialysis patients by means of deep recurrent neural networks.

Erythropoiesis Stimulating Agents (ESAs) have become a standard anemia management tool for End Stage Renal Disease (ESRD) patients. However, dose optimization constitutes an extremely challenging task due to huge inter and intra-patient variability in the responses to ESA administration. Current data-based approaches to anemia control focus on learning accurate hemoglobin prediction models, which can be later utilized for testing competing treatment choices and choosing the optimal one. These methods, despite being proven effective in practice, present several shortcomings which this paper intends to tackle. Namely, they are limited to a small cohort of patients and, even then, they fail to provide suggestions when some strict requirements are not met (such as having a three month history prior to the prediction). Here, recurrent neural networks (RNNs) are used to model whole patient histories, providing predictions at every time step since the very first day. Furthermore, an unprecedented amount of data (∼110,000 patients from many different medical centers in twelve countries, without exclusion criteria) was used to train it, thus allowing it to generalize for every single patient. The resulting model outperforms state-of-the-art Hemoglobin prediction, providing excellent results even when tested on a prospective dataset. Simultaneously, it allows to bring the benefits of algorithmic anemia control to a very large group of patients.

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.

Development of an Artificial Intelligence Model to Guide the Management of Blood Pressure, Fluid Volume, and Dialysis Dose in End-Stage Kidney Disease Patients: Proof of Concept and First Clinical Assessment.

BACKGROUND: Fluid volume and blood pressure (BP) management are crucial endpoints for end-stage kidney disease patients. BP control in clinical practice mainly relies on reducing extracellular fluid volume overload by diminishing targeted postdialysis weight. This approach exposes dialysis patients to intradialytic hypotensive episodes. SUMMARY: Both chronic hypertension and intradialytic hypotension lead to adverse long-term outcomes. Achieving the optimal trade-off between adequate fluid removal and the risk of intradialytic adverse events is a complex task in clinical practice given the multiple patient-related and dialysis-related factors affecting the hemodynamic response to treatment. State-of-the-art artificial intelligence has been adopted in other complex decision-making tasks for dialysis patients and may help personalize the multiple dialysis-related prescriptions affecting patients' intradialytic hemodynamics. As a proof of concept, we developed a multiple-endpoint model predicting session-specific Kt/V, fluid volume removal, heart rate, and BP based on patient characteristics, historic hemodynamic responses, and dialysis-related prescriptions. KEY MESSAGES: The accuracy and precision of this preliminary model is extremely encouraging. Such analytic tools may be used to anticipate patients' reactions through simulation so that the best strategy can be chosen based on clinical judgment or formal utility functions.

Effects of high-volume online mixed-hemodiafiltration on anemia management in dialysis patients.

BACKGROUND: Anemia is a major comorbidity of patients with end-stage renal disease and poses an enormous economic burden to health-care systems. High dose erythropoiesis-stimulating agents (ESAs) have been associated with unfavorable clinical outcomes. We explored whether mixed-dilution hemodiafiltration (Mixed-HDF), based on its innovative substitution modality, may improve anemia outcomes compared to the traditional post-dilution hemodiafiltration (Post-HDF). METHODS: We included 174 adult prevalent dialysis patients (87 on Mixed-HDF, 87 on Post-HDF) treated in 24 NephroCare dialysis centers between January 2010 and August 2016 into this retrospective cohort study. All patients were dialyzed three times per week and had fistula/graft as vascular access. Patients were matched at baseline and followed over a one-year period. The courses of hemoglobin levels (Hb) and monthly ESA consumption were compared between the two groups with linear mixed models. RESULTS: Mean baseline Hb was 11.9±1.3 and 11.8±1.1g/dl in patients on Mixed- and Post-HDF, respectively. While Hb remained stable in patients on Mixed-HDF, it decreased slightly in patients on Post-HDF (at month 12: 11.8±1.2 vs 11.1±1.2g/dl). This tendency was confirmed by our linear mixed model (p = 0.0514 for treatment x time interaction). Baseline median ESA consumption was 6000 [Q1:0;Q3:16000] IU/4 weeks in both groups. Throughout the observation period ESA doses tended to be lower in the Mixed-HDF group (4000 [Q1:0;Q3:16000] vs 8000 [Q1:0;Q3:20000] IU/4 weeks at month 12; p = 0.0791 for treatment x time interaction). Sensitivity analyses, adjusting for differences not covered by matching at baseline, strengthened our results (Hb: p = 0.0124; ESA: p = 0.0687). CONCLUSIONS: Results of our explorative study suggest that patients on Mixed-HDF may have clinical benefits in terms of anemia management. This may also have a beneficial economic impact. Future studies are needed to confirm our hypothesis-generating results and to provide additional evidence on the potential beneficial effects of Mixed-HDF.

Detecting high-risk chronic kidney disease-mineral bone disorder phenotypes among patients on dialysis: a historical cohort study.

BACKGROUND: The clinical management of chronic kidney disease-mineral bone disorder (CKD-MBD) remains extremely challenging, partially due to difficulties in defining high-risk phenotypes based on serum biomarkers. We evaluated the prevalence and outcomes of 27 mutually exclusive CKD-MBD phenotypes in a large, multi-national cohort of chronic dialysis patients over a 5-year follow-up study. METHODS: In this historical cohort study, we enrolled all haemodialysis patients registered in EuCliD® on 1 July 2011 across 28 Europe, the Middle East and Africa (EMEA) and South American countries. We created 27 mutually exclusive phenotypes based on combinations of serum parathyroid hormone (PTH), phosphorus (P) and calcium (Ca) 6-month averages (L, low; T, target; H, high). We tested the association between CKD-MBD phenotypes and 5-year mortality and hospitalization risk by outcome risk score-adjusted proportional hazard regression. RESULTS: We enrolled 35 721 eligible patients. Eastern European and South American countries generally achieved poorer CKD-MBD control when compared with Western European countries (prevalence ratio: 0.79; P < 0.001). There were 15 795 deaths [126.7 deaths/1000 person-years; 95% confidence interval (CI) 124.7-128.7]; 18 014 had at least one hospitalization (203.9 hospitalizations/1000 person-years; 95% CI 201.0-206.9); the incidence of the composite endpoint was 280.0 events/1000 person-years (95% CI 276.6-283.5). In the fully adjusted model, relative mortality risk ranged from hazard ratio (HR) = 1.07 (PTH/Ca/P: TLT) to HR = 1.59 (PTH/Ca/P: LTL), whereas the relative composite endpoint risk ranged from HR = 1.07 (PTH/Ca/P: TTH) to HR = 1.36 (PTH/Ca/P: LTL). CONCLUSION: We identified several CKD-MBD phenotypes associated with reduced hospitalization-free survival and increased mortality. Ranking of relative risk estimates or excess events concurs in informing healthcare priority setting.

El modelo de control de anemia: ¿ayuda al nefrólogo en la decisión terapéutica para el manejo de la anemia? / The anaemia control model: Does it help nephrologists in therapeutic decision-making in the management of anaemia?

INTRODUCCIÓN: La anemia es frecuente en los pacientes en hemodiálisis, y su tratamiento con estimulantes de la eritropoyesis (AEE) resulta complejo debido a múltiples factores. OBJETIVOS: Valorar la utilidad del modelo de control de anemia (MCA) en el tratamiento de la anemia en hemodiálisis. MÉTODOS: El MCA es un software que predice la dosis óptima de darbepoetina y hierro sacarosa para alcanzar niveles de hemoglobina (Hb) y ferritina deseados, emitiendo sugerencias de prescripción. Estudio realizado en clínicas de diálisis de 18 meses de duración en dos fases de intervención (FI) con MCA (FI1, n: 213; FI2, n: 218) separadas por una fase de control (FC, n: 219). El resultado primario fue el porcentaje de Hb en rango y la mediana de dosis de AEE y los resultados secundarios fueron las transfusiones, las hospitalizaciones o los acontecimientos cardiovasculares. Análisis a nivel de clínica y de pacientes valorando la variabilidad de la Hb mediante la desviación estándar (DE) de esta. También se analizaron pacientes con la mayoría de sugerencias confirmadas (grupo MCA cumplidores) RESULTADOS: El MCA aumentó el porcentaje de Hb en rango: 80,9% FI2 frente a 72,7% en FC, y redujo el consumo de darbepoetina (FI1: 20 [70]; FC 30 [80] μg, p = 0,032) con menor fluctuación de la Hb (0,91 ± 0,49 en FC a 0,82 ± 0,37g/dl en FI2; p < 0,05) mejorando en el grupo MCA cumplidores. En cuanto a los resultados secundarios, descendieron con el uso del MCA. CONCLUSIONES: El MCA ayuda a obtener mejores resultados de anemia en los pacientes en hemodiálisis, minimizando los riesgos del tratamiento con AEE y reduciendo costes

INTRODUCTION: Anaemia is common in haemodialysis patients and treating it with erythropoiesis-stimulating agents (ESAs) is complex due to many factors. OBJECTIVES: To assess the usefulness of the Anaemia Control Model (ACM) in the treatment of anaemia in haemodialysis. METHODS: ACM is a software that predicts the optimal dose of darbepoetin and iron sucrose to achieve target haemoglobin (Hb) and ferritin levels, and makes prescription suggestions. Study conducted in dialysis clinics lasting 18months with two intervention phases (IPs) with ACM (IP1, n:213; IP2, n:218) separated by a control phase (CP, n:219). The primary outcome was the percentage of Hb in range and the median dose of ESAs, and the secondary outcomes were transfusion, hospitalisation and cardiovascular events. Clinical and patient analyses were performed. Hb variability was assessed by the standard deviation (SD) of the Hb. We also analysed the patients with most of the suggestions confirmed (ACM compliant group). RESULTS: ACM increased the percentage of Hb in range: 80.9% in IP2, compared with 72.7% in the CP and reduced the intake of darbepoetin (IP1: 20 [70]; CP 30 [80] μg P = 0.032) with less Hb fluctuation (0.91 ± 0.49 in the CP to 0.82 ± 0.37 g/dl in IP2, P < 0.05), improving in the ACM compliant group. The secondary outcomes decreased with the use of ACM. CONCLUSIONS: ACM helps to obtain better anaemia results in haemodialysis patients, minimising the risks of treatment with ESAs and red

The anaemia control model: Does it help nephrologists in therapeutic decision-making in the management of anaemia? / El modelo de control de anemia: ¿ayuda al nefrólogo en la decisión terapéutica para el manejo de la anemia?

INTRODUCTION: Anaemia is common in haemodialysis patients and treating it with erythropoiesis-stimulating agents (ESAs) is complex due to many factors. OBJECTIVES: To assess the usefulness of the Anaemia Control Model (ACM) in the treatment of anaemia in haemodialysis. METHODS: ACM is a software that predicts the optimal dose of darbepoetin and iron sucrose to achieve target haemoglobin (Hb) and ferritin levels, and makes prescription suggestions. Study conducted in dialysis clinics lasting 18months with two intervention phases (IPs) with ACM (IP1, n:213; IP2, n:218) separated by a control phase (CP, n:219). The primary outcome was the percentage of Hb in range and the median dose of ESAs, and the secondary outcomes were transfusion, hospitalisation and cardiovascular events. Clinical and patient analyses were performed. Hb variability was assessed by the standard deviation (SD) of the Hb. We also analysed the patients with most of the suggestions confirmed (ACM compliant group). RESULTS: ACM increased the percentage of Hb in range: 80.9% in IP2, compared with 72.7% in the CP and reduced the intake of darbepoetin (IP1: 20 [70]; CP 30 [80] µg P=0.032) with less Hb fluctuation (0.91±0.49 in the CP to 0.82±0.37g/dl in IP2, P<0.05), improving in the ACM compliant group. The secondary outcomes decreased with the use of ACM. CONCLUSIONS: ACM helps to obtain better anaemia results in haemodialysis patients, minimising the risks of treatment with ESAs and reducing costs.

Artificial Intelligence for the Artificial Kidney: Pointers to the Future of a Personalized Hemodialysis Therapy.

BACKGROUND: Current dialysis devices are not able to react when unexpected changes occur during dialysis treatment or to learn about experience for therapy personalization. Furthermore, great efforts are dedicated to develop miniaturized artificial kidneys to achieve a continuous and personalized dialysis therapy, in order to improve the patient's quality of life. These innovative dialysis devices will require a real-time monitoring of equipment alarms, dialysis parameters, and patient-related data to ensure patient safety and to allow instantaneous changes of the dialysis prescription for the assessment of their adequacy. The analysis and evaluation of the resulting large-scale data sets enters the realm of "big data" and will require real-time predictive models. These may come from the fields of machine learning and computational intelligence, both included in artificial intelligence, a branch of engineering involved with the creation of devices that simulate intelligent behavior. The incorporation of artificial intelligence should provide a fully new approach to data analysis, enabling future advances in personalized dialysis therapies. With the purpose to learn about the present and potential future impact on medicine from experts in artificial intelligence and machine learning, a scientific meeting was organized in the Hospital Universitari Bellvitge (L'Hospitalet, Barcelona). As an outcome of that meeting, the aim of this review is to investigate artificial intel ligence experiences on dialysis, with a focus on potential barriers, challenges, and prospects for future applications of these technologies. SUMMARY AND KEY MESSAGES: Artificial intelligence research on dialysis is still in an early stage, and the main challenge relies on interpretability and/or comprehensibility of data models when applied to decision making. Artificial neural networks and medical decision support systems have been used to make predictions about anemia, total body water, or intradialysis hypotension and are promising approaches for the prescription and monitoring of hemodialysis therapy. Current dialysis machines are continuously improving due to innovative technological developments, but patient safety is still a key challenge. Real-time monitoring systems, coupled with automatic instantaneous biofeedback, will allow changing dialysis prescriptions continuously. The integration of vital sign monitoring with dialysis parameters will produce large data sets that will require the use of data analysis techniques, possibly from the area of machine learning, in order to make better decisions and increase the safety of patients.

Patients' Characteristics Affect the Survival Benefit of Warfarin Treatment for Hemodialysis Patients with Atrial Fibrillation. A Historical Cohort Study.

BACKGROUND: Stroke prevention in dialysis-dependent patients with atrial fibrillation (AF) is an unresolved clinical dilemma. Indeed, no randomized controlled trial evaluating the efficacy and safety of oral anticoagulants in this population, has been conducted so far. Observational research on the use of warfarin in patients on dialysis has shown conflicting results. This uncertainty is mirrored by the wide variations in warfarin prescription patterns across centers. We sought to evaluate the association between the use of vitamin K antagonists (VKAs) and mortality among hemodialysis patient with AF and to assess potential factors affecting the risk-benefit profile of warfarin in this population. METHODS: A total of 91,987 patients registered in the European Clinical Dialysis Database® system from January 2004 to January 2015. Of which, 9,238 patients were identified with a diagnosis of AF. After excluding ineligible patients, a 1:1 propensity score matched cohort of 1,324 warfarin users and non-users were assembled. RESULTS: VKA use was associated with both increased 90-day survival (hazard ratio, HR 0.47, p < 0.01) and 6-year survival (HR 0.76, p < 0.01); however, a trend indicated a stronger early benefit (p for time-interaction <0.01). Moderation analysis showed that patients' age and clinical history of stroke strongly influenced warfarin-related benefits on survival. CONCLUSION: VKA may provide an early survival benefit; however, this is partially offset later during the follow-up. In addition, heterogeneous risk-benefit profiles were observed among subgroups of dialysis-dependent patients with AF, further emphasizing the complexities of tailoring stroke prevention strategies in this population.

An international observational study suggests that artificial intelligence for clinical decision support optimizes anemia management in hemodialysis patients.

Managing anemia in hemodialysis patients can be challenging because of competing therapeutic targets and individual variability. Because therapy recommendations provided by a decision support system can benefit both patients and doctors, we evaluated the impact of an artificial intelligence decision support system, the Anemia Control Model (ACM), on anemia outcomes. Based on patient profiles, the ACM was built to recommend suitable erythropoietic-stimulating agent doses. Our retrospective study consisted of a 12-month control phase (standard anemia care), followed by a 12-month observation phase (ACM-guided care) encompassing 752 patients undergoing hemodialysis therapy in 3 NephroCare clinics located in separate countries. The percentage of hemoglobin values on target, the median darbepoetin dose, and individual hemoglobin fluctuation (estimated from the intrapatient hemoglobin standard deviation) were deemed primary outcomes. In the observation phase, median darbepoetin consumption significantly decreased from 0.63 to 0.46 µg/kg/month, whereas on-target hemoglobin values significantly increased from 70.6% to 76.6%, reaching 83.2% when the ACM suggestions were implemented. Moreover, ACM introduction led to a significant decrease in hemoglobin fluctuation (intrapatient standard deviation decreased from 0.95 g/dl to 0.83 g/dl). Thus, ACM support helped improve anemia outcomes of hemodialysis patients, minimizing erythropoietic-stimulating agent use with the potential to reduce the cost of treatment.

Atrial fibrillation in dialysis patients: time to abandon warfarin?

Atrial fibrillation (AF) is a frequent clinical complication in dialysis patients, and warfarin therapy represents the most common approach for reducing the risk of stroke in this population. However, current evidence based on observational studies, offer conflicting results, whereas no randomized controlled trials have been carried out so far. Additionally, many clinicians are wary of the possible role of warfarin as vascular calcification inducer and its potential to increase the high risk of bleeding among patients on dialysis. Ideally the most promising therapy would be based on direct inhibitors of factor IIa or Xa; however, at the moment, none of these drugs can be safely prescribed in dialysis patients, because of their potentially dangerous accumulation, and the lack of sufficient experience with apixaban or rivaroxaban, two drugs showing a favorable pharmacokinetic profile in end-stage renal disease. Hence, the use of vitamin K inhibitors is currently the only pharmacological option for stroke prevention in dialysis patients with atrial fibrillation, leaving the clinicians in a management conundrum.This review discusses the trade-offs implicated in warfarin use for this population, the promises of newly developed drugs, the role of dialysis as atrial fibrillation trigger, as well as potential non-pharmacological management options suitable in selected clinical situations.

Performance of a Predictive Model for Long-Term Hemoglobin Response to Darbepoetin and Iron Administration in a Large Cohort of Hemodialysis Patients.

Anemia management, based on erythropoiesis stimulating agents (ESA) and iron supplementation, has become an increasingly challenging problem in hemodialysis patients. Maintaining hemodialysis patients within narrow hemoglobin targets, preventing cycling outside target, and reducing ESA dosing to prevent adverse outcomes requires considerable attention from caregivers. Anticipation of the long-term response (i.e. at 3 months) to the ESA/iron therapy would be of fundamental importance for planning a successful treatment strategy. To this end, we developed a predictive model designed to support decision-making regarding anemia management in hemodialysis (HD) patients treated in center. An Artificial Neural Network (ANN) algorithm for predicting hemoglobin concentrations three months into the future was developed and evaluated in a retrospective study on a sample population of 1558 HD patients treated with intravenous (IV) darbepoetin alfa, and IV iron (sucrose or gluconate). Model inputs were the last 90 days of patients' medical history and the subsequent 90 days of darbepoetin/iron prescription. Our model was able to predict individual variation of hemoglobin concentration 3 months in the future with a Mean Absolute Error (MAE) of 0.75 g/dL. Error analysis showed a narrow Gaussian distribution centered in 0 g/dL; a root cause analysis identified intercurrent and/or unpredictable events associated with hospitalization, blood transfusion, and laboratory error or misreported hemoglobin values as the main reasons for large discrepancy between predicted versus observed hemoglobin values. Our ANN predictive model offers a simple and reliable tool applicable in daily clinical practice for predicting the long-term response to ESA/iron therapy of HD patients.