Precision Dialysis: Leveraging Big Data and Artificial Intelligence.

The long-term mortality of patients with kidney failure remains unacceptably high. There are a multitude of reasons for the unfavorable status quo of dialysis care, such as the inadequate and suboptimal pattern of uremic toxin removal resulting in a metabolic and hemodynamic "roller coaster" induced by thrice-weekly in-center hemodialysis. Innovation in dialysis delivery systems is needed to build an adaptive and self-improving process to change the status quo of dialysis care with the aim of transforming it from being reactive to being proactive. The introduction of more physiologic and smart dialysis systems using artificial intelligence (AI) incorporating real-time data into the process of dialysis delivery is a realistic target. This would enable machine learning from both individual and collective patient treatment data. This has the potential to shift the paradigm from the practice of population-driven, evidence-based data to precision medicine. In this review, we describe the different components of an AI system, discuss the studied applications of AI in the field of dialysis, and outline parameters that can be used for future smart, adaptive dialysis delivery systems. The desired output is precision dialysis; a self-improving process that has the ability to prognosticate and develop instant and individualized predictive models.

Ultrafiltration Patterns during Automated Peritoneal Dialysis: Findings and Insights to Peritoneal Physiology.

BACKGROUND: With the growing use of automated peritoneal dialysis (APD), it is important to improve our knowledge of the clinical patterns and physiology of APD treatment sessions. The ultrafiltration (UF) achieved during each cycle of an APD treatment is assumed to be relatively linear if the delivered prescription is the same. We set out to determine if that is indeed the case. METHODS: Single-center, cross-sectional study of prevalent PD patients. All adult APD patients (> 18 years of age), who had been on PD for >3 months, and >3 months on APD were included. Continuous ambulatory PD patients or those with peritonitis within 3 months of the consent date were excluded. Individual treatment data from 7 consecutive APD treatment sessions with consistent dialysate composition for each cycler exchange were collected for each subject. RESULTS: Thirty-nine subjects met the inclusion criteria and were enrolled. The probability of yielding a positive UF was 48.9% for cycle 1, rising to 90.5% by cycle 6. Adjusting for average dextrose concentration, dwell time, fill volume, solute transfer rate, and number of cycles, we observed that cycles 2 through 6 achieved progressively higher UF volumes than cycle 1 (p < 0.001). The first and last cycles demonstrated significantly different cycle UF volumes compared to a middle cycle (-230 ml and 277 ml, respectively, p < 0.001). CONCLUSIONS: We observed a consistent increase in UF volumes achieved per cycle over the course of an APD treatment session with numerous clinical and physiologic implications. This provides the foundation for future studies investigating peritoneal inter-cycle variations and membrane physiology.

Patient-Centered Home Hemodialysis: Approaches and Prescription.

Writing a home hemodialysis (HD) prescription is a complex, multifactorial process that requires the incorporation of patient values, preferences, and lifestyle. Knowledge of the different options available for home HD modality (conventional, nocturnal, short daily, and alternate nightly) is also important when customizing a prescription. Finally, an understanding of the different home HD machines currently approved for use at home and their different attributes and limitations helps guide providers when formulating their prescriptions. In this review article, we set out to address these different aspects to help guide providers in providing a patient-centered home HD approach.

Fluid management protocols in hemodialysis patients using bioimpedance validation: time to look elsewhere?

The management of volume status in dialysis patients is an important determinant of the rate of decline of residual kidney function. The implementation of clinical protocols to guide volume management in the in-center hemodialysis unit resulted in comparable rates of development of anuria and decline in residual kidney function when compared with bioimpedance spectroscopy-guided volume management. Clinical judgment and experience are important drivers of patient outcomes. The importance and applicability of bioimpedance spectroscopy in other clinical settings, such as units without clear volume management protocols or in home dialysis units, remain to be seen.

Utilization of Peritoneal Dialysis in the United States: Progress in Tackling Obstacles to Expansion.

To facilitate the desired increase in home dialysis utilization in the United States, multiple factors need to be taken into consideration in order to achieve this complex task. Through policy-level facilitators such as the Advancing American Kidney Health Initiative and the expansion of telehealth utilization, adjustments to the existing payment models, providing health equity incentives, increasing number of provider education materials on home therapies, and allaying patient fears with the expansion of home dialysis education nationwide, we have taken several steps in the right direction. There is still a long way to go, and further improvements can be made while utilizing lessons learned from some of our international peers who have been successful in their implementation of large-scale home dialysis programs.

Comparing the effect of peritoneal dialysis cycler type on patient-reported satisfaction, support needs and treatments.

BACKGROUND: Most patients on peritoneal dialysis (PD) in the United States choose automated PD via cyclers. Cyclers have evolved considerably over time with older versions (e.g. HomeChoice Pro) replaced by more sophisticated and technologically advanced versions (e.g. Amia). Understanding the effect that different cyclers and their features have on patient treatments and support needs is important.  METHODS: Single center study with retrospective and prospective arms. Retrospective arm: Patients > 18 years old, on Amia or HomeChoice Pro (HC) for ≥ 3 months between 8/1/17 and 1/31/18. Number of office/telephone encounters, PD-related emergency room visits/hospitalizations, PD training days, and dialysis adequacy (Kt/V) were recorded. Prospective arm: Patients > 18 years old, on Amia or HC for ≥ 3 months between 9/1/19 and 2/29/20 were surveyed on their comfort, troubleshooting, satisfaction and reported assistance needed with their cyclers. RESULTS: Retrospective arm: 43 patients on AMIA and 27 patients on HC. Number of PD training days, Kt/Vs achieved, PD-related telephone/office encounters, and PD-related emergency room visits/hospitalizations were all similar. Prospective Arm: 32 patients on AMIA and 6 patients on HC. Higher rate of patient comfort with AMIA, but similar overall patient satisfaction with both cyclers. No difference in terms of patient-reported troubleshooting issues requiring assistance. CONCLUSIONS: Despite the difference in features provided between the 2 cyclers, patient overall satisfaction rates were high irrespective of the PD cycler. The HomeChoice Pro and AMIA cycler patients had a similar number of PD training days, PD-related telephone/office encounters, and PD-related emergency room visits/hospitalizations. TRIAL REGISTRATION: This study was approved by the Icahn School of Medicine at Mount Sinai Institutional Review Board (IRB-17-02704).

Reverse pseudohyperkalemia is more than leukocytosis: a retrospective study.

BACKGROUND: Hyperkalemia is a potentially life-threatening electrolyte abnormality that often requires urgent treatment. Clinicians should distinguish true hyperkalemia from pseudohyperkalemia and reverse pseudohyperkalemia (RPK). RPK has exclusively been described in case reports of patients with hematologic malignancies (HMs) and extreme leukocytosis [white blood cell (WBC) count >200 × 103/mL]. METHODS: This single-center retrospective study analyzed laboratory data from the Mount Sinai Data Warehouse between 1 January 2010 and 31 December 2016 for plasma potassium and serum potassium samples drawn within 1 h of each other, with plasma potassium ≥1 mEq/L of the serum potassium. Only plasma potassium ≥5 mEq/L were included. Samples that were documented to be hemolyzed or contaminated were excluded. Clinical history and laboratory data were collected from the identified cases. RESULTS: After applying the inclusion/exclusion criteria to 485 potential cases, the final cohort included 45 cases from 41 patients. There were 24 men and 17 women with a mean age of 52 years. The median plasma potassium was 6.1 mEq/L and serum potassium was 4.4 mEq/L. The median WBC count was 9.35 × 103/mL (interquartile range 6.5-19.7 × 103/mL). Only 44% of the samples had leukocytosis, defined as WBC >11 × 103/mL.Seven patients had a HM and comprised 11 of the cases (24%) with a median WBC of 181.8 × 103µL. There was no difference in their plasma and serum potassium levels when compared with the total cohort, despite a higher median WBC count. Thirty-eight percent of the cases required medical management. CONCLUSIONS: The literature on RPK is limited to case reports and series associated with extreme leukocytosis. This is the first study characterizing RPK predominantly associated with normal leukocyte counts. Further investigation is required to more precisely characterize factors associated with RPK and to elucidate RPK mechanisms.

DACH1 protects podocytes from experimental diabetic injury and modulates PTIP-H3K4Me3 activity.

Dachshund homolog 1 (DACH1), a key cell-fate determinant, regulates transcription by DNA sequence-specific binding. We identified diminished Dach1 expression in a large-scale screen for mutations that convert injury-resistant podocytes into injury-susceptible podocytes. In diabetic kidney disease (DKD) patients, podocyte DACH1 expression levels are diminished, a condition that strongly correlates with poor clinical outcomes. Global Dach1 KO mice manifest renal hypoplasia and die perinatally. Podocyte-specific Dach1 KO mice, however, maintain normal glomerular architecture at baseline, but rapidly exhibit podocyte injury after diabetes onset. Furthermore, podocyte-specific augmentation of DACH1 expression in mice protects from DKD. Combined RNA sequencing and in silico promoter analysis reveal conversely overlapping glomerular transcriptomic signatures between podocyte-specific Dach1 and Pax transactivation-domain interacting protein (Ptip) KO mice, with upregulated genes possessing higher-than-expected numbers of promoter Dach1-binding sites. PTIP, an essential component of the activating histone H3 lysine 4 trimethylation (H3K4Me3) complex, interacts with DACH1 and is recruited by DACH1 to its promoter-binding sites. DACH1-PTIP recruitment represses transcription and reduces promoter H3K4Me3 levels. DACH1 knockdown in podocytes combined with hyperglycemia triggers target gene upregulation and increases promoter H3K4Me3. These findings reveal that in DKD, diminished DACH1 expression enhances podocyte injury vulnerability via epigenetic derepression of its target genes.

Use of peritoneal dialysis for acute kidney injury during the COVID-19 pandemic in New York City: a multicenter observational study.

To demonstrate feasibility of acute peritoneal dialysis (PD) for acute kidney injury during the coronavirus disease 2019 (COVID-19) pandemic, we performed a multicenter, retrospective, observational study of 94 patients who received acute PD in New York City in the spring of 2020. Patient comorbidities, severity of disease, laboratory values, kidney replacement therapy, and patient outcomes were recorded. The mean age was 61 ± 11 years; 34% were women; 94% had confirmed COVID-19; 32% required mechanical ventilation on admission. Compared to the levels prior to initiation of kidney replacement therapy, the mean serum potassium level decreased from 5.1 ± 0.9 to 4.5 ± 0.7 mEq/L on PD day 3 and 4.2 ± 0.6 mEq/L on day 7 (P < 0.001 for both); mean serum bicarbonate increased from 20 ± 4 to 21 ± 4 mEq/L on PD day 3 (P = 0.002) and 24 ± 4 mEq/L on day 7 (P < 0.001). After a median follow-up of 30 days, 46% of patients died and 22% had renal recovery. Male sex and mechanical ventilation on admission were significant predictors of mortality. The rapid implementation of an acute PD program was feasible despite resource constraints and can be lifesaving during crises such as the COVID-19 pandemic.

Home Dialysis: A Majority Chooses It, a Minority Gets It.

INTRODUCTION: When choosing a modality for outpatient renal replacement therapy, patients and medical providers have 3 options to choose from in-center hemodialysis (HD), home HD (HHD), and peritoneal dialysis (PD). In 2017, just over 10% of incident ESKD patients were on a home dialysis modality. We set out to determine outcomes of dialysis modality education in both pre-dialysis and dialysis patients. Moreover, we examined barriers that preclude patients from choosing home dialysis. METHODS: This was a single-center, retrospective study looking at patients who were referred to the CKD educator for dialysis modality education between January 1, 2019, and March 31, 2020. Patient demographics, preferred language of communication, stage of renal disease, and reasons for patients' refusal to undertake a home dialysis modality were recorded. Patients' average household income and driving distance to our home dialysis unit were calculated using their home zip code. RESULTS: 167 patients were referred for CKD education. Mean age was 60 years, and 59% male, 42% African American, 22% White, 7% Asian, and 28% were Hispanic or Latino. Only 23% of the total cohort chose in-center HD, while 74% chose a home dialysis modality (59% PD and 15% HHD), and the remaining patients remained undecided. 56% of in-center HD patients chose a home dialysis modality. The most commonly cited barriers to home dialysis were lack of a care partner, lack of home space, and patient preference. LIMITATIONS: Over 90% of our patients reside in NY City where home space is limited. We require in our home HD program that patients have a trained care partner present during their treatments. We cannot assume that all CKD stage-4 patients or higher were either referred for CKD education or followed through on the referral. CONCLUSIONS: A large discrepancy between informed patients' choices and the reality of the current dialysis landscape. Absence of a care partner, lack of home space, and patients not deemed appropriate surgical candidates were the main driving forces in their not opting for a home modality.

The Association between Prevalence of Peritoneal Dialysis versus Hemodialysis and Patients' Distance to Dialysis-Providing Facilities.

Background: Accessibility to dialysis facilities plays a central role when deciding on a patient's long-term dialysis modality. Studies investigating the effect of distance to nearest dialysis-providing unit on modality choice have yielded conflicting results. We set out to investigate the association between patients' dialysis modality and both the driving and straight-line distances to the closest HD- and PD-providing units. Methods: All patients with ESKD who initiated in-center HD and PD in 2017, were 18-90 years old, and were on dialysis for ≥30 days were included. Patients in residence zip codes in nonconterminous United States or lived >90 miles from the nearest HD-providing unit were excluded. Results: A total of 102,247 patients in the United States initiated in-center HD and PD in 2017. Compared with patients on HD, patients on PD had longer driving distances to their nearest PD unit (4.4 versus 3.4 miles; P<0.001). Patients who lived >30 miles from the nearest HD unit were more likely to be on PD if the nearest PD unit was a distance equal to/less than that of the HD unit. PD utilization increased with increasing distance from patients' homes to the nearest HD unit. No change in this association was found regardless of if the PD unit was farther from/closer than the nearest HD unit. This association was not seen with straight-line distance analysis. Conclusions: With increasing distances from the nearest dialysis-providing units (HD or PD), PD utilization increased. Using driving distance rather than straight-line distance affects data analysis and outcomes. Increasing the number of PD units may have a limited effect on increasing PD utilization.