Personalized prediction of intradialytic hypotension in clinical practice: Development and evaluation of a novel AI dashboard incorporating risk factors from previous and current dialysis sessions.

BACKGROUND: Intradialytic hypotension (IDH) is one of the most common and critical complications of hemodialysis. Despite many proven factors associated with IDH, accurately predicting it before it occurs for individual patients during dialysis sessions remains a challenge. PURPOSE: To establish artificial intelligence (AI) predictive models for IDH, which consider risk factors from previous and ongoing dialysis to optimize model performance. We then implement a novel digital dashboard with the best model for continuous monitoring of patients' status undergoing hemodialysis. The AI dashboard can display the real-time probability of IDH for each patient in the hemodialysis center providing an objective reference for care members for monitoring IDH and treating it in advance. METHODS: Eight machine learning (ML) algorithms, including Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), K Nearest Neighbor (KNN), Light Gradient Boosting Machine (LightGBM), Multilayer Perception (MLP), eXtreme Gradient Boosting (XGBoost), and NaiveBayes, were used to establish the predictive model of IDH to determine if the patient will acquire IDH within 60 min. In addition to real-time features, we incorporated several features sourced from previous dialysis sessions to improve the model's performance. The electronic medical records of patients who had undergone hemodialysis at Chi Mei Medical Center between September 1, 2020 and December 31, 2020 were included in this research. Impact evaluation of AI assistance was conducted by IDH rate. RESULTS: The results showed that the XGBoost model had the best performance (accuracy: 0.858, sensitivity: 0.858, specificity: 0.858, area under the curve: 0.936) and was chosen for AI dashboard implementation. The care members were delighted with the dashboard providing real-time scientific probabilities for IDH risk and historic predictive records in a graphic style. Other valuable functions were appended in the dashboard as well. Impact evaluation indicated a significant decrease in IDH rate after the application of AI assistance. CONCLUSION: This AI dashboard provides high-quality results in IDH risk prediction during hemodialysis. High-risk patients for IDH will be recognized 60 min earlier, promoting individualized preventive interventions as part of the treatment plan. Our approachis believed to promise an excellent way for IDH management.

Atomoxetine for Intradialytic Hypotension in a Patient on Hemodialysis: A Case Report.

Intradialytic hypotension significantly affects patient safety and clinical outcomes during hemodialysis. Despite various pharmacological and nonpharmacological interventions, effective management remains elusive. In this report, we detail a case of intradialytic hypotension in a male patient in his 40s, undergoing hemodialysis with a history of polycystic kidney disease. Eight years ago, the patient underwent bilateral nephrectomy because of a severe cystic infection, after which his systolic blood pressure (BP) persistently remained at 50-70 mm Hg during dialysis sessions. The initial treatment strategy for hypotension included fludrocortisone, midodrine, and prednisolone, leading to a slight temporary increase in BP, which subsequently declined. As the patient's condition deteriorated, the administration of norepinephrine or dopamine became necessary to sustain BP during dialysis. Given the patient's resistance to these treatments, a daily dose of 25 mg of atomoxetine was introduced. Following this treatment, there was a gradual improvement in the patient's vertigo, weakness, and BP. This case illustrates that low-dose atomoxetine can alleviate symptoms and elevate BP in patients experiencing severe intradialytic hypotension during hemodialysis.

Hypertensive Emergency During Dialysis: A Paradoxical Physiologic Response.

Most end-stage renal disease patients experience a reduction in blood pressure during their hemodialysis session compared to predialysis. Surprisingly, a small subset of patients will experience an unusual physiological response to dialysis that results in a paradoxical increase in blood pressure. We discuss a case that involved an exaggerated elevation in blood pressure, ultimately requiring immediate cessation of dialysis and admission to the intensive care unit for intravenous treatment of a hypertensive emergency. This case serves as a framework to introduce the infrequently discussed concept of intradialytic hypertension. The underlying pathogenesis is poorly understood with multiple theoretical etiologies including activation of the renin-angiotensin-aldosterone system, imbalances in circulating levels of endothelium-derived mediators, clearance of antihypertensive medications, increased cardiac output, and changes in arterial thickness. It is important to be cognizant of this phenomenon as emerging evidence suggests that patients with any elevation in blood pressure during hemodialysis have increased rates of both short-term and long-term mortality.

Usefulness of the heart rate variability test in predicting intradialytic hypotension in patients undergoing chronic haemodialysis.

Background: Intradialytic hypotension (IDH) is the primary complication of haemodialysis (HD); however, its diverse pathophysiology and inconsistent definitions complicate its prediction. Despite attempts using the heart rate variability (HRV) test for IDH prediction, studies on its usefulness for predicting IDH diagnosed per the nadir 90 criterion are lacking. We aimed to evaluate HRV test efficacy and reproducibility in predicting IDH based on the nadir 90 criterion. Methods: Seventy patients undergoing HD participated in this multicentre prospective observational study. The HRV test was performed during non-HD periods and IDH was monitored during 12 HD sessions. IDH was diagnosed according to the nadir 90 criterion, defined as a decrease in systolic blood pressure of ≤90 mmHg during HD. After monitoring, the HRV test was repeated. An HRV-IDH index was developed using multivariate logistic regression analysis employing HRV test parameters. The predictive power of the HRV-IDH index was analysed using the area under the receiver operating characteristics curve (AUROC). Reproducibility was evaluated using correlation analysis of two HRV tests on the same patient. Results: There were 37 and 33 patients in the IDH and non-IDH groups, respectively. The HRV-IDH index predicted IDH occurrence with AUROCs of 0.776 and 0.803 for patients who had experienced at least one or repeated IDH episodes, respectively. Spearman's correlation coefficient for HRV-IDH indices was 0.859 for the first and second HRV tests. Conclusions: The HRV test holds promise for predicting IDH, particularly for patients with recurring IDH diagnosed based on the nadir 90 criterion.

Association of Calcium Channel Blocker Use With Intradialytic Hypotension in Maintenance Hemodialysis.

Introduction: Calcium channel blockers (CCBs) are common antihypertensive agents among patients receiving hemodialysis (HD). Despite this, the association of CCBs with intradialytic hypotension (IDH), an important adverse outcome that is associated with cardiovascular morbidity and mortality, remains largely unexplored. Methods: Using kinetic modeling sessions data from the Hemodialysis (HEMO) Study, random effects regression models were fit to assess the association of CCB use versus nonuse with IDH (defined as systolic blood pressure [SBP] < 90 mm Hg if pre-HD SBP < 160 mm Hg or < 100 mm Hg if pre-HD SBP ≥160 mm Hg). Models were adjusted for age, biological sex (distinguishing between males and females), race, randomized Kt/V and flux assignments, heart failure, ischemic heart disease, peripheral vascular disease, diabetes mellitus, blood urea nitrogen, ultrafiltration rate, access type, pre-HD SBP, and other antihypertensives. Results: Data were available for 1838 patients and 64,538 sessions. At baseline, 49% of patients were prescribed CCBs. The overall frequency of IDH was 14% with a mean decline from pre- to nadir-SBP of 33 ± 15 mm Hg. CCB use was associated with lower adjusted risk of IDH, compared with no use (incidence rate ratio [IRR]: 0.84; 95% confidence interval [CI]: 0.78-0.89). The association was most pronounced for those in the pre-HD SBP lowest quartile (IRR: 0.77; 95% CI: 0.70-0.85); compared with the highest quartile (IRR: 0.86; 95% CI: 0.77-0.97; P-interaction < 0.001). Conclusion: Among patients receiving HD, CCB use was associated with a lower risk of developing IDH, independent of pre-HD SBP and other antihypertensives use. Mechanistic studies are needed to better understand the effects of CCB and other antihypertensives on peridialytic blood pressure (BP) parameters among patients receiving HD.

Continuous Monitoring of Advanced Hemodynamic Parameters during Hemodialysis Demonstrated Early Variations in Patients Experiencing Intradialytic Hypotension.

Intradialytic hypotension (IDH) is a severe complication of hemodialysis (HD) with a significant impact on morbidity and mortality. In this study, we used a wearable device for the continuous monitoring of hemodynamic vitals to detect hemodynamic changes during HD and attempted to identify IDH. End-stage kidney disease patients were continuously monitored 15 min before starting the session and until 15 min after completion of the session, measuring heart rate (HR), noninvasive cuffless systolic and diastolic blood pressure (SBP and DBP), stroke volume (SV), cardiac output (CO), and systemic vascular resistance (SVR). Data were analyzed retrospectively and included comparing BP measured by the wearable devices (recorded continuously every 5 s) and the cuff-based devices. A total of 98 dialysis sessions were included in the final analysis, and IDH was identified in 22 sessions (22.5%). Both SBP and DBP were highly correlated (r > 0.62, p < 0.001 for all) between the wearable device and the cuff-based measurements. Based on the continuous monitoring, patients with IDH had earlier and more profound reductions in SBP and DBP during the HD treatment. In addition, nearly all of the advanced vitals differed between groups. Further studies should be conducted in order to fully understand the potential of noninvasive advanced continuous monitoring in the prediction and prevention of IDH events.

Outcomes with inpatient use of midodrine in patients with heart failure and kidney failure on maintenance dialysis.

BACKGROUND: Midodrine, an FDA-approved medication for orthostatic hypotension, is also used off-label to manage hypotension in dialysis patients, including those with heart failure. However, in patients with reduced ejection fraction (HFrEF) and/or right heart failure, midodrine is potentially harmful. No known studies examine the safety of midodrine in hospitalised kidney failure patients with HF. METHODS: The TriNetX database was queried for hospitalised kidney failure patients with HFrEF and/or right heart failure who experienced hypotension (SBP < 110 mm Hg or MAP < 70 mm Hg). Excluding those needing critical care or vasopressors, we compared cohorts based on midodrine use, matching for comorbidities. RESULTS: Analysis showed patients on midodrine had a higher 6-month mortality risk ratio (RR 1.53, 95% CI 1.037 to 2.246) and Hazard Ratio (HR 1.54, 95% CI 1.022 to 2.317) compared to those not on midodrine, indicating an association with increased mortality. CONCLUSION: This study illuminates the complexities in treating hospitalised patients with kidney failure and HF. Our findings, drawn from an exploratory analysis, indicate that inpatient midodrine use is associated with increased 6-month mortality. This may reflect deleterious effects from vasoconstriction and/or unmeasured confounders in this vulnerable population. This investigation, utilising TriNetX, was limited by access to deidentified aggregate data, preventing detailed exploration of specifics such as timing, dosage, and indications for midodrine use. Moreover, given its observational nature, cause-effect relationship cannot be established. Our findings indicate an increased mortality associated with midodrine use for hypotension, underscoring the need for further research and consideration of alternative strategies.

Hepatic Oxygenation Changes and Symptomatic Intradialytic Hypotension.

INTRODUCTION: Clinical studies on differences among changes in cerebral and hepatic oxygenation during hemodialysis (HD) in patients with and without intradialytic hypotension (IDH) are limited. We investigated changes in intradialytic cerebral and hepatic oxygenation before systolic blood pressure (SBP) reached the nadir during HD and compared these differences between patients with and without symptomatic IDH. METHODS: We analyzed data from 109 patients with (n = 23) and without (n = 86) symptomatic IDH who were treated with HD. Cerebral and hepatic regional oxygen saturation (rSO2), as a marker of tissue oxygenation and circulation, was monitored during HD using an INVOS 5100c oxygen saturation monitor. Changes in cerebral or hepatic rSO2 when SBP reached the nadir during HD were compared between the groups of patients. RESULTS: The cerebral rSO2 before HD in patients with and without symptomatic IDH was 49.7 ± 11.2% and 51.3 ± 9.1% (p = 0.491). %Changes in cerebral rSO2 did not significantly differ between the two groups from 60 min before the SBP nadir during HD. Hepatic rSO2 before HD in patients with and without symptomatic IDH was 58.5 ± 15.4% and 57.8 ± 15.9% (p = 0.869). The %changes in hepatic rSO2 were significantly lower in patients with symptomatic IDH than in those without throughout the observational period (p < 0.001). We calculated the area under the receiver operating characteristic curve (AUC) and estimated cutoff values for changes in hepatic rSO2 as a symptomatic IDH predictor. The predictive ability at 5 and 40 min before symptomatic IDH onset was excellent, with AUCs and cutoff values of 0.847 and 0.841, and -10.9% and -5.0%, respectively. CONCLUSIONS: Hepatic oxygenation significantly decreased more in patients with symptomatic IDH before its onset, than in those without symptomatic IDH, whereas changes in cerebral oxygenation did not differ. Evaluating changes in hepatic oxygenation during HD might help to predict symptomatic IDH.

Effect of absolute blood volume measurement-guided fluid management on the incidence of intradialytic hypotension-associated events: a randomised controlled trial.

Background: Ultrafiltration to target weight during haemodialysis is complicated by intradialytic hypotension-associated adverse events (IHAAEs) in 10-30% of dialysis treatments. IHAAEs are caused by critical reductions in absolute blood volume (ABV), due to the interaction of ultrafiltration, refill and compensatory mechanisms. Non-randomised studies have suggested that ABV-guided treatment, using an indicator dilution technique employing the blood volume monitor on the dialysis machine, could reduce the incidence of IHAAEs. Methods: We performed an open-label randomised controlled trial. Patients were randomly assigned to adjustment of target weight guided by ABV measurements or standard care. The primary outcome was the change in the incidence of IHAAEs from baseline, defined as the percentage of treatment episodes in a 4-week period where the patient had a systolic blood pressure <90 mmHg or symptoms of impending hypotension. ABV measurements were compared with anthropomorphometric estimation and the gold standard using isotope dilution. Results: A total of 56 patients were randomised, of whom 29 were allocated to ABV-guided treatment and 27 to standard care. Overall baseline incidence of IHAAEs was 26.0%. ABV-guided treatment significantly reduced the incidence of IHAAEs compared with standard care, with a mean change from baseline of -9.6% [95% confidence interval (CI) -17.3 to -1.8) versus 2.4% (95% CI -2.3-7.2). The adjusted difference between the groups was 10.5% (95% CI 1.3-19.8; P = .026). ABV measurement had moderate agreement with other methods to estimate blood volume. The sensitivity for the previously suggested threshold of a post-dialysis normalised blood volume of 65 ml/kg was observed to be 74% in this study. Conclusions: ABV-guided volume management significantly reduced IHAAEs compared with standard care. The clinical relevance of the previously suggested threshold of 65 ml/kg cannot be firmly concluded on the basis of our results. If confirmed in a larger trial, this intervention could potentially change dialysis practice and impact patient care in a clinically meaningful way.

Does intradialytic oral nutrition impact hemodialysis patients' quality of life, appetite, and safety? a pilot study of a crossover clinical trial / ¿La nutrición oral intradialítica impacta en la calidad de vida, el apetito y la seguridadde los pacientes en hemodiálisis? Estudio piloto de un ensayo clínico cruzado

Introduction: due to the catabolic characteristics of hemodialysis (HD), patients should consume foods or supplements during this treatment to meet their energy requirements and maintain a neutral nitrogen balance; however, there are some outcomes in which the effect of intradialytic oral nutrition (ION) is scarcely known. Objectives: this study aims to evaluate the effect of two types of ION (liquid and solid) on Quality of Life (QoL), appetite, and safety in HD patients. Methods: a pilot randomized, crossover clinical trial was performed in 18 patients on chronic HD. One group received ION for 18 HD sessions, after the crossover continued for 18 more sessions in the control group, and vice versa. We recorded QoL, appetite, systolic blood pressure (SBP), and intradialytic hypotension (IH) events. Results: clinical improvement was observed for most QoL components. Regardless of the consistency of supplementation, SBP increased to 4.10 mmHg. Both study groups reported a “very good-to-good” appetite. Conclusion: favorable clinical changes were observed in QoL scores during the study. Five of six IH events were reported for patients in the ION group, and SBP increased within the safe range (≤ 10 mmHg); appetite remained stable in both groups. Therefore, we concluded that this strategy, regardless of implementation consistency, is safe to be used in stable patients.(AU)

Introducción: debido a las características catabólicas de la hemodiálisis (HD), los pacientes deben consumir alimentos o suplementos durante este tratamiento para cubrir sus requerimientos energéticos y mantener un balance nitrogenado neutro; sin embargo, existen algunos desenlaces en los que el efecto de la nutrición oral intradialítica (NOID) es poco conocido.Objetivo: este estudio tiene como objetivo evaluar el efecto de dos tipos de NOID (líquido y sólido) sobre la calidad de vida, el apetito y la seguridad en pacientes en HD. Métodos: se realizó un estudio piloto en forma de ensayo clínico aleatorizado y cruzado con 18 pacientes en HD crónica. Un grupo recibió NOID durante 18 sesiones de HD, después del cruzamiento continuaron durante 18 sesiones más en el grupo de control, y viceversa. Se registraron la calidad de vida, el apetito, la presión arterial sistólica (PAS) y la hipotensión intradialítica (HI).Resultados: se observó mejoría clínica en la mayoría de los componentes de la calidad de vida. Independientemente de la consistencia de la suplementación, la PAS aumentó hasta 4,10 mmHg. Ambos grupos de estudio informaron de un apetito "muy bueno-bueno". Conclusiones: se observaron cambios clínicos favorables en las puntuaciones de calidad de vida durante el estudio. Cinco de seis eventos de HI se reportaron en pacientes del grupo de NOID y la PAS aumentó dentro del rango seguro (≤ 10 mmHg); el apetito se mantuvo estable en ambos grupos. Por lo tanto, se puede concluir que esta estrategia, independientemente de la consistencia implementada, es segura para ser utilizada en pacientes estables.(AU)

Comparison of blood volume biofeedback hemodialysis and conventional hemodialysis on cardiovascular stability and blood pressure control in hemodialysis patients: a systematic review and meta-analysis of randomized controlled trials.

BACKGROUND: Despite the improvements in hemodialysis (HD) technology, 20-30% of sessions are still complicated by hypotension or hypotension-related symptoms. Biofeedback systems have proven to reduce the occurrence of such events, but no conclusive findings can lead to wider adoption of these systems. We conducted this systematic review and meta-analysis of randomized clinical trials to establish whether the use of blood volume tracking systems compared to conventional hemodialysis (C-HD) reduces the occurrence of intradialytic hypotension. METHODS: The PRISMA guidelines were used to carry out this systematic review. Randomized clinical trials that evaluated the incidence of intradialytic hypotension during C-HD and blood volume tracking-HD were searched in the current literature. PROSPERO registration number: CRD42023426328. RESULTS: Ninety-seven randomized clinical trials were retrieved. Nine studies, including 347 participants and 13,274 HD treatments were considered eligible for this systematic review. The results showed that the use of biofeedback systems reduces the risk of intradialytic hypotension (log odds ratio = 0.63, p = 0.03) in hypotension-prone patients (log odds ratio = 0.54, p = 0.04). When analysis was limited to fluid overloaded or hypertensive patients, it did not show the same effect (log odds ratio = 0.79, p = 0.38). No correlation was found in systolic blood pressure drop during dialysis and in post-dialysis blood pressure. CONCLUSIONS: The use of blood volume tracking systems may be effective in reducing the incidence of intradialytic hypotension and allowing for easier attainment of the patients' ideal dry body weight. New studies to examine the long-term effects of the use of blood volume tracking systems on real hard endpoints are needed.

A bagging approach for improved predictive accuracy of intradialytic hypotension during hemodialysis treatment.

The primary objective of this study is to enhance the prediction accuracy of intradialytic hypotension in patients undergoing hemodialysis. A significant challenge in this context arises from the nature of the data derived from the monitoring devices and exhibits an extreme class imbalance problem. Traditional predictive models often display a bias towards the majority class, compromising the accuracy of minority class predictions. Therefore, we introduce a method called UnderXGBoost. This novel methodology combines the under-sampling, bagging, and XGBoost techniques to balance the dataset and improve predictive accuracy for the minority class. This method is characterized by its straightforward implementation and training efficiency. Empirical validation in a real-world dataset confirms the superior performance of UnderXGBoost compared to existing models in predicting intradialytic hypotension. Furthermore, our approach demonstrates versatility, allowing XGBoost to be substituted with other classifiers and still producing promising results. Sensitivity analysis was performed to assess the model's robustness, reinforce its reliability, and indicate its applicability to a broader range of medical scenarios facing similar challenges of data imbalance. Our model aims to enable medical professionals to provide preemptive treatments more effectively, thereby improving patient care and prognosis. This study contributes a novel and effective solution to a critical issue in medical prediction, thus broadening the application spectrum of predictive modeling in the healthcare domain.

Intradialytic Hypotension and Mortality in Adolescents and Young Adults With Kidney Failure Receiving Maintenance Hemodialysis.

Rationale & Objective: Intradialytic hypotension (IDH) is associated with mortality in adults with kidney failure requiring hemodialysis (HD); however, large-scale pediatric studies are lacking. Moreover, there is no evidence-based consensus definition of IDH in pediatric literature. We aimed to examine the association of commonly used definitions of IDH with mortality in adolescents and young adults. Study Design: This was a retrospective observational cohort study. Setting & Participants: In total, 1,199 adolescents and young adults (N = 320, aged 10-18 years and N = 879, aged 19-21 years) who initiated HD in a large dialysis organization were included. Exposures: This study used different definitions of IDH. Outcome: The study outcome was 2-year all-cause mortality. Analytical Approach: Several definitions of IDH were selected a priori based on a literature review. Patients were classified as having IDH if it was present in at least 30% of HD treatments during the first 90 days after dialysis initiation. Cox proportional hazards regression was used to test whether IDH associated with 2-year all-cause mortality. Results: Over a 2-year follow-up period, 54 (4.5%) patients died. Dependent on its definition, IDH was present in 2.9%-61.1% of patients. After the multivariable adjustment for sociodemographic and clinical characteristics, we found no association of IDH with mortality. Results were consistent across subgroups stratified by age (aged <18 and 19-21 years) and predialysis systolic blood pressure (<120, 120-150, and >150 mm Hg). We also examined IDH as occurring in <5%, 5%-29%, 30%-50%, and >50% of baseline treatments, and did not find a dose-response association with mortality (P > 0.05). Limitations: Owing to low event rates, our current sample size may have been too small to detect a difference in mortality. Conclusions: Our study found that IDH was not associated with mortality in adolescents and young adults.

Intradialytic hypotension (IDH), or hypotension experienced during dialysis, is common among children and young adults with kidney failure requiring hemodialysis. We examined the association of commonly used definitions of IDH with death in adolescents and young adults with kidney failure receiving hemodialysis. Intradialytic hypotension was present in 2.9%-61.1% of patients, depending on the definition, and over a 2-year follow-up period, 4.5% of the patients died. We found no association of IDH with mortality.

Intradialytic hypotension and worse outcomes in patients with acute kidney injury requiring intermittent hemodialysis.

Background: Intradialytic hypotension (IDH) is a critical complication related to worse outcomes in patients undergoing maintenance hemodialysis. Herein, we addressed the impact of IDH on mortality and other outcomes in patients with severe acute kidney injury (AKI) requiring intermittent hemodialysis. Methods: We retrospectively reviewed 1,009 patients who underwent intermittent hemodialysis due to severe AKI. IDH was defined as either dialysis discontinuation due to hemodynamic instability or a decrease in systolic blood pressure (BP) of ≥30 mmHg, with or without a nadir systolic BP of <90 mmHg during the first session. The primary outcome was all-cause mortality, and transfer to the intensive care unit (ICU) due to unstable status was additionally analyzed. Hazard ratios (HRs) of outcomes were calculated using a Cox regression model after adjusting for multiple variables. Risk factors for IDH were evaluated using a logistic regression model. Results: IDH occurred in 449 patients (44.5%) during the first hemodialysis session. Patients with IDH had a higher mortality rate than those without IDH (40% vs. 23%; HR, 1.30; 95% confidence interval [CI], 1.02-1.65). The rate of ICU transfer was higher in patients experiencing IDH than in those without IDH (17% vs. 11%; HR, 1.43; 95% CI, 1.02-2.02). Factors such as old age, high BP and pulse rate, active malignancy, cirrhosis, and hypoalbuminemia were associated with an increased risk of IDH episodes. Conclusion: The occurrence of IDH is associated with worse outcomes in patients with AKI requiring intermittent hemodialysis. Therefore, careful monitoring and early intervention of IDH may be necessary in this patient subset.

Association of frequent intradialytic hypotension with the clinical outcomes of patients on hemodialysis: a prospective cohort study.

Intradialytic hypotension (IDH) is a common complication of hemodialysis (HD), but there is no consensus on its definition. In 2015, Flythe proposed a definition of IDH (Definition 1 in this study): nadir systolic blood pressure (SBP) <90 mmHg during hemodialysis for patients with pre-dialysis SBP <159 mmHg, and nadir SBP <100 mmHg during hemodialysis for patients with pre-dialysis SBP ≥160 mmHg. This prospective observational cohort study investigated the association of frequent IDH based on Definition 1 with clinical outcomes and compared Definition 1 with a commonly used definition (nadir SBP <90 mmHg during hemodialysis, Definition 2). The incidence of IDH was observed over a 3-month exposure assessment period. Patients with IDH events ≥30% were classified as 'frequent IDH'; the others were 'infrequent IDH'. All-cause mortality, cardiovascular mortality, and all-cause hospitalization events were followed up for 36 months. This study enrolled 163 HD patients. The incidence of IDH was 11.1% according to Definition 1 and 10.5% according to Definition 2. The Kaplan-Meier curves showed that frequent IDH patients had higher risks of all-cause mortality (p = 0.009, Definition 1; p = 0.002, Definition 2) and cardiovascular mortality (p = 0.021, Definition 1). Multivariable Cox regression analysis indicated that frequent IDH was independently associated with a higher risk of all-cause mortality (Model 1: HR = 2.553, 95%CI 1.334-4.886, p = 0.005; Model 2: HR = 2.406, 95%CI 1.253-4.621, p = 0.008). In conclusion, HD patients classified as frequent IDH are at a greater risk of all-cause mortality. This highlights the significance of acknowledging and proactively managing frequent IDH within the HD patients.

Ambient temperature and the occurrence of intradialytic hypotension in patients receiving hemodialysis.

Background: Intradialytic hypotension (IDH) is a common hemodialysis complication causing adverse outcomes. Despite the well-documented associations of ambient temperatures with fluid removal and pre-dialysis blood pressure (BP), the relationship between ambient temperature and IDH has not been adequately studied. Methods: We conducted a cohort study at a tertiary hospital in southern Taiwan between 1 January 2016 and 31 October 2021. The 24-h pre-hemodialysis mean ambient temperature was determined using hourly readings from the weather station closest to each patient's residence. IDH was defined using Fall40 [systolic BP (SBP) drop of ≥40 mmHg] or Nadir90/100 (SBP <100 if pre-dialysis SBP was ≥160, or SBP <90 mmHg). Multivariate logistic regression with generalizing estimating equations and mediation analysis were utilized. Results: The study examined 110 400 hemodialysis sessions from 182 patients, finding an IDH prevalence of 11.8% and 10.4% as per the Fall40 and Nadir90/100 criteria, respectively. It revealed a reverse J-shaped relationship between ambient temperature and IDH, with a turning point around 27°C. For temperatures under 27°C, a 4°C drop significantly increased the odds ratio of IDH to 1.292 [95% confidence interval (CI) 1.228 to 1.358] and 1.207 (95% CI 1.149 to 1.268) under the Fall40 and Nadir90/100 definitions, respectively. Lower ambient temperatures correlated with higher ultrafiltration, accounting for about 23% of the increased IDH risk. Stratified seasonal analysis indicated that this relationship was consistent in spring, autumn and winter. Conclusion: Lower ambient temperature is significantly associated with an increased risk of IDH below the threshold of 27°C, irrespective of the IDH definition. This study provides further insight into environmental risk factors for IDH in patients undergoing hemodialysis.

Is intradialytic oral nutritional supplementation safe and effective on clinical outcomes? A systematic review with conventional meta-analysis and network meta-analysis.

AIM: determine the effect of intradialytic oral nutrition (ION) on clinical and safety outcomes. DESIGN: Systematic Review with conventional Meta-analysis, and a Network Meta-analysis (NMA) as sensitivity analysis. We searched on MEDLINE, LILACS, CENTRAL, and EMBASE in June 2020, and the last update was until August 2022. We selected observational and randomized controlled trials with ION for at least four weeks. Primary outcomes were all-cause mortality and quality of life (QoL); adverse events, physical performance, and appetite were secondary outcomes. RESULTS: Seven clinical trials and three observational studies were selected. Even when we did not obtain significant differences in physical performance and gastrointestinal symptoms, we identified a clinical improvement in the QoL's physical role, bodily pain, and physical performance domains. After pooling the data on mortality, a protection rate trend was observed in the ION group without statistical significance. The home-prepared ION was the best nutritional supplementation when assessing the appetite outcome through NMA. CONCLUSIONS: ION seems to have a protective trend in mortality risk; the current evidence is insufficient to establish a relationship with adverse events or other clinical outcomes. The lack of homogeneity in the trials makes it difficult to generalize these results. PROSPERO REGISTRATION: CRD42020186311.

Construction of an Early Alert System for Intradialytic Hypotension before Initiating Hemodialysis Based on Machine Learning.

Introduction: Intradialytic hypotension (IDH) is prevalent and associated with high hospitalization and mortality rates. The purpose of this study was to explore the risk factors for IDH and use artificial intelligence to establish an early alert system before hemodialysis sessions to identify patients at high risk of IDH. Materials and Methods: We obtained data on 314,534 hemodialysis sessions conducted at Sichuan Provincial People's Hospital from the renal disease treatment information system. IDH was defined as a systolic blood pressure drop ≥20 mm Hg, a mean arterial pressure drop ≥10 mm Hg during dialysis, or the occurrence of clinical hypotensive events requiring nursing intervention. After pre-processing, the data were randomly divided into training (80%) and testing (20%) sets. Four interpolation methods, three feature selection methods, and 18 machine learning algorithms were used to construct predictive models. The area under the receiver operating characteristic curve (AUC) was the main indicator for evaluating the performance of the models, while Shapley Additive ExPlanation was used to explain the contribution of each variable to the best predictive model. Results: A total of 3,906 patients and 314,534 dialysis sessions were included, of which 142,237 cases showed IDH (incidence rate, 45.2%). Nineteen parameters were identified through artificial intelligence feature screening. They included age, pre-dialysis weight, dry weight, pre-dialysis blood pressure, heart rate, prescribed ultrafiltration, blood cell counts (neutrophil, lymphocyte, monocyte, eosinophil, lymphocyte, and platelet counts), hematocrit, serum calcium, creatinine, urea, glucose, and uric acid. Random forest, gradient boosting, and logistic regression were the three best models, and the AUCs were 0.812 (95% confidence interval [CI], 0.811-0.813), 0.748 (95% CI, 0.747-0.749), and 0.743 (95% CI, 0.742-0.744), respectively. Conclusion: Our dialysis software-based artificial intelligence alert system can be used to predict IDH occurrence, enabling the initiation of relevant interventions.

Current Knowledge of Beta-Blockers in Chronic Hemodialysis Patients.

Beta-blockers include a large spectrum of drugs with various specific characteristics, and a well-known cardioprotective efficacy. They are recommended in heart failure, hypertension and arrhythmia. Their use in chronic hemodialysis patients is still controversial, mainly because of the lack of specific randomized clinical trials. Large observational studies and two important clinical trials have reported almost unanimously their efficacy in chronic hemodialysis patients, which seems to be related to their levels of dialyzability and cardioselectivity. A recent meta-analysis suggested that high dialyzable beta-blockers are correlated to a reduced risk of all-cause mortality and cardiovascular complications compared with low dialyzable beta-blockers. Despite their benefits, beta-blockers may have adverse effects, such as intradialytic hypotension with low dialyzability beta-blockers or the risk of sub-therapeutic plasma concentration of high dialyzable ones during dialysis sessions. Both cases are linked to adverse cardiovascular events. A solution for both high and low dialyzable drugs could be their administration after dialysis sessions. Futhermore, the bulk of existing literature seems to favor cardioselective beta-blockers with moderate-to-high dialyzability as the ideal agents in dialysis patients, but further, larger studies are needed. This review aims to analyze beta-blockers' characteristics, indications and evidence-based role in chronic hemodialysis patients.