Machine learning directed interventions associate with decreased hospitalization rates in hemodialysis patients.

BACKGROUND: An integrated kidney disease company uses machine learning (ML) models that predict the 12-month risk of an outpatient hemodialysis (HD) patient having multiple hospitalizations to assist with directing personalized interdisciplinary interventions in a Dialysis Hospitalization Reduction Program (DHRP). We investigated the impact of risk directed interventions in the DHRP on clinic-wide hospitalization rates. METHODS: We compared the hospital admission and day rates per-patient-year (ppy) from all hemodialysis patients in 54 DHRP and 54 control clinics identified by propensity score matching at baseline in 2015 and at the end of the pilot in 2018. We also used paired T test to compare the between group difference of annual hospitalization rate and hospitalization days rates at baseline and end of the pilot. RESULTS: The between group difference in annual hospital admission and day rates was similar at baseline (2015) with a mean difference between DHRP versus control clinics of -0.008 ± 0.09 ppy and -0.05 ± 0.96 ppy respectively. The between group difference in hospital admission and day rates became more distinct at the end of follow up (2018) favoring DHRP clinics with the mean difference being -0.155 ± 0.38 ppy and -0.97 ± 2.78 ppy respectively. A paired t-test showed the change in the between group difference in hospital admission and day rates from baseline to the end of the follow up was statistically significant (t-value = 2.73, p-value < 0.01) and (t-value = 2.29, p-value = 0.02) respectively. CONCLUSIONS: These findings suggest ML model-based risk-directed interdisciplinary team interventions associate with lower hospitalization rates and hospital day rate in HD patients, compared to controls.

Association of all-cause mortality with pre-dialysis systolic blood pressure and its peridialytic change in chronic hemodialysis patients.

BACKGROUND: Pre-dialysis systolic blood pressure (pre-HD SBP) and peridialytic SBP change have been associated with morbidity and mortality among hemodialysis (HD) patients in previous studies, but the nature of their interaction is not well understood. METHODS: We analyzed pre-HD SBP and peridialytic SBP change (calculated as post-HD SBP minus pre-HD SBP) between January 2001 and December 2012 in HD patients treated in US Fresenius Medical Care facilities. The baseline period was defined as Months 4-6 after HD initiation, and all-cause mortality was noted during follow-up. Only patients who survived baseline and had no missing covariates were included. Censoring events were renal transplantation, modality change or study end. We fitted a Cox proportional hazard model with a bivariate spline functions for the primary predictors (pre-HD SBP and peridialytic SBP change) with adjustment for age, gender, race, diabetes, access-type, relative interdialytic weight gain, body mass index, albumin, equilibrated normalized protein catabolic rate and ultrafiltration rate. RESULTS: A total of 172 199 patients were included. Mean age was 62.1 years, 61.6% were white and 55% were male. During a median follow-up of 25.0 months, 73 529 patients (42.7%) died. We found that a peridialytic SBP rise combined with high pre-HD SBP was associated with higher mortality. In contrast, when concurrent with low pre-HD SBP, a peridialytic SBP rise was associated with better survival. CONCLUSION: The association of pre-HD and peridialytic SBP change with mortality is complex. Our findings call for a joint, not isolated, interpretation of pre-HD SBP and peridialytic SBP change.

Remote Treatment Monitoring on Hospitalization and Technique Failure Rates in Peritoneal Dialysis Patients.

Background: An integrated kidney disease healthcare company implemented a peritoneal dialysis (PD) remote treatment monitoring (RTM) application in 2016. We assessed if RTM utilization associates with hospitalization and technique failure rates. Methods: We used data from adult (age ≥18 years) patients on PD treated from October 2016 through May 2019 who registered online for the RTM. Patients were classified by RTM use during a 30-day baseline after registration. Groups were: nonusers (never entered data), moderate users (entered one to 15 treatments), and frequent users (entered >15 treatments). We compared hospital admission/day and sustained technique failure (required >6 consecutive weeks of hemodialysis) rates over 3, 6, 9, and 12 months of follow-up using Poisson and Cox models adjusted for patient/clinical characteristics. Results: Among 6343 patients, 65% were nonusers, 11% were moderate users, and 25% were frequent users. Incidence rate of hospital admission was 22% (incidence rate ratio [IRR]=0.78; P=0.002), 24% (IRR=0.76; P<0.001), 23% (IRR=0.77; P≤0.001), and 26% (IRR=0.74; P≤0.001) lower in frequent users after 3, 6, 9, and 12 months, respectively, versus nonusers. Incidence rate of hospital days was 38% (IRR=0.62; P=0.013), 35% (IRR=0.65; P=0.001), 34% (IRR=0.66; P≤0.001), and 32% (IRR=0.68; P<0.001) lower in frequent users after 3, 6, 9, and 12 months, respectively, versus nonusers. Sustained technique failure risk at 3, 6, 9, and 12 months was 33% (hazard ratio [HR]=0.67; P=0.020), 31% (HR=0.69; P=0.003), 31% (HR=0.69; P=0.001), and 27% (HR=0.73; P=0.001) lower, respectively, in frequent users versus nonusers. Among a subgroup of survivors of the 12-month follow-up, sustained technique failure risk was 26% (HR=0.74; P=0.023) and 21% (HR=0.79; P=0.054) lower after 9 and 12 months, respectively, in frequent users versus nonusers. Conclusions: Our findings suggest frequent use of an RTM application associates with less hospital admissions, shorter hospital length of stay, and lower technique failure rates. Adoption of RTM applications may have the potential to improve timely identification/intervention of complications.

Longitudinal patterns of health-related quality of life and dialysis modality: a national cohort study.

BACKGROUND: Health-related quality of life (HrQoL) varies among dialysis patients. However, little is known about the association of dialysis modality with HrQoL over time. We describe longitudinal patterns of HrQoL among chronic dialysis patients by treatment modality. METHODS: National retrospective cohort study of adult patients who initiated in-center dialysis or a home modality (peritoneal or home hemodialysis) between 1/2013 and 6/2015. Patients remained on the same modality for the first 120 days of the first two years. HrQoL was assessed by the Kidney Disease and Quality of Life-36 (KDQOL) survey in the first 120 days of the first two years after dialysis initiation. Home modality patients were matched to in-center patients in a 1:5 fashion. RESULTS: In-center (n=4234) and home modality (n=880) patients had similar demographic and clinical characteristics. In-center dialysis patients had lower mean KDQOL scores across several domains compared to home modality patients. For patients who remained on the same modality, there was no change in HrQoL. However, there were trends towards clinically meaningful changes in several aspects of HrQoL for patients who switched modalities. Specifically, physical functioning decreased for patients who switched from home to in-center dialysis (p< 0.05). CONCLUSIONS: Among a national cohort of chronic dialysis patients, there was a trend towards different patterns of HrQoL life that were only observed among patients who changed modality. Patients who switched from home to in-center modalities had significant lower physical functioning over time. Providers and patients should be mindful of HrQoL changes that may occur with dialysis modality change.

TRANSITION PERIOD CLINICAL TRAJECTORIES FOR PD VERSUS HD STARTERS.

BACKGROUND: Peritoneal dialysis (PD) starters generally have a better outcome compared with hemodialysis (HD) starters, perhaps related to treatment characteristics or case mix. We previously showed that pre- and post-dialysis start clinical parameter trajectories are related to outcomes. The aim of this study was to investigate these trajectories in PD and HD starters. METHODS: This retrospective observational study analyzing data from the Fresenius Medical Care-chronic kidney disease (CKD) Registry from January 2009 to March 2018 examines trends in key clinical parameters through the transition period covering 12 months before to 12 months after dialysis start in 8,088 HD and 1,015 PD starters. RESULTS: Hemodialysis starters differed from PD starters by a significantly greater decline in estimated glomerular filtration rate (eGFR) slope (-0.64 vs -0.45 mL/min/1.73 m2/month) before and higher eGFR (9.85 vs 7.84 mL/min/1.73 m2) at dialysis start. Relatedly, differences in phosphorus (0.07 vs 0.05 mg/dL/month) and hemoglobin (-0.08 vs -0.01 g/dL/month) slopes before the transition to dialysis therapy were observed. After dialysis start, HD starters experienced a greater increase in albumin (0.01 vs 0 g/dL/month) whereas PD starters experienced a decline in serum sodium and higher white blood cell counts compared with HD starters. CONCLUSION: For nephrology practice CKD patients, HD and PD starters appear clinically comparable in the year before dialysis start although HD starters exhibit a more rapid pre-dialytic eGFR decline. Ideally, studies comparing incident HD and PD outcomes should also consider CKD eGFR trajectories. In the first dialysis year, divergence occurs in albumin, white blood cell count, sodium and hemoglobin trends, which may be partly treatment-related.

Cycles, Arrows and Turbulence: Time Patterns in Renal Disease, a Path from Epidemiology to Personalized Medicine?

Patients with end-stage renal disease (ESRD) experience unique patterns in their lifetime, such as the start of dialysis and renal transplantation. In addition, there is also an intricate link between ESRD and biological time patterns. In terms of cyclic patterns, the circadian blood pressure (BP) rhythm can be flattened, contributing to allostatic load, whereas the circadian temperature rhythm is related to the decline in BP during hemodialysis (HD). Seasonal variations in BP and interdialytic-weight gain have been observed in ESRD patients in addition to a profound relative increase in mortality during the winter period. Moreover, nonphysiological treatment patters are imposed in HD patients, leading to an excess mortality at the end of the long interdialytic interval. Recently, new evidence has emerged on the prognostic impact of trajectories of common clinical and laboratory parameters such as BP, body temperature, and serum albumin, in addition to single point in time measurements. Backward analysis of changes in cardiovascular, nutritional, and inflammatory parameters before the occurrence as hospitalization or death has shown that changes may already occur within months to even 1-2 years before the event, possibly providing a window of opportunity for earlier interventions. Disturbances in physiological variability, such as in heart rate, characterized by a loss of fractal patterns, are associated with increased mortality. In addition, an increase in random variability in different parameters such as BP and sodium is also associated with adverse outcomes. Novel techniques, based on time-dependent analysis of variability and trends and interactions of multiple physiological and laboratory parameters, for which machine-learning -approaches may be necessary, are likely of help to the clinician in the future. However, upcoming research should also evaluate whether dynamic patterns observed in large epidemiological studies have relevance for the individual risk profile of the patient.

A History of Leadership in Dialysis: Perspectives From Seasoned Leaders.

The history of chronic dialysis in the United States highlights the impact nephrology leaders have on improving kidney disease care. Belding Scribner and his Seattle team transformed end-stage renal disease from a fatal illness to a treatable condition with use of the first successful Scribner shunt in 1960. Advances in dialysis machines emerged from Les Babb and Richard Drake finding ways to treat more patients. Innovative nephrology leaders foster incremental change leading to the technically complex, life-sustaining treatments that are widely available to end-stage renal disease patients today. The Nephrology Oral History Project consists of interviews with patient, nurse, and nephrologist pioneers who have witnessed and contributed to these advancements in kidney disease care. This article includes Nephrology Oral History Project excerpts illustrating leadership contributions to dialysis machines, peritoneal dialysis catheters, and treatment best practices. In addition to individual contributions, improvements in treatment also come from patient and provider organizations leading the way and collectively advocating for change. Nephrology leaders continue to play a crucial role in improving dialysis outcomes and quality of life.

The Association of Weekly pre-Hemodialysis Systolic Blood Pressure and Following Week Mortality.

BACKGROUND/AIMS: Few studies examine the impact of systolic blood pressure (SBP) on mortality in the incident hemodialysis (HD) period, and throughout the first HD year. This large retrospective observational study analyzes the impact of "current" and cumulative low preSBP <110 mmHg (L), and variations in preSBP on short-term (1 week) mortality over the first HD year. METHODS: Weekly mean preSBP for HD weeks 1 to 51 was categorized into L or high preSBP>=110 mmHg (H) for each patient. A generalized linear model (GLM) was used to compute the probability of death in the following week. The model includes age, gender, race and three preSBP-related parameters: (a) percent of prior weeks with L preSBP; (b) percent of prior weeks with switching between L to H; (c) "current" week's preSBP as a binary variable. Separate models were constructed that include demographics and BP-related parameters (a), (b), and (c) separately. RESULTS: In a model combining (a), (b), and (c) above, "current" week L preSBP is associated with increased odds ratio for following week mortality throughout the first HD year. The percent of prior week's L and more switching between L and H are less significantly associated with short-term mortality. In models including (a), (b), and (c) separately, "current" L preSBP is associated with higher mortality. CONCLUSION: This study confirms an association of L preSBP with increased short-term mortality which is maintained over the first HD year. Percent of L preSBP in prior weeks, switching between L and H, and "current" week L are all associated with short-term mortality risk, but "current" week L preSBP is most significant.

Clinical parameters before and after the transition to dialysis.

INTRODUCTION: The transition from pre-dialysis chronic kidney disease (CKD) to post-dialysis start is a critical period associated with high patient mortality and increased hospital admissions. Little is known about the trends of key clinical and laboratory parameters through this time of transition to start dialysis. METHODS: De-identified data including demographics, vital signs, lab results, and eGFR from the Fresenius Medical Care-CKD Registry were analyzed to determine trends in clinical and laboratory parameters through the time of transition from 12 months pre-dialysis start to 12 months post-dialysis start. Trends in key clinical and laboratory parameters associated with cardiovascular, nutritional, mineral metabolism and inflammatory domains were examined in association with the transition to dialysis start and first year dialysis survival. FINDINGS: All parameters show divergence for patients who survive vs. do not survive the first year of dialysis. Of note, during pre-dialysis CKD the absolute systolic blood pressure (SBP) level is lower and the slope for SBP decline is significantly steeper for patients who do not survive the first year on dialysis. DISCUSSION: This study uniquely demonstrates the trajectories of key parameters though the transition from pre-dialysis to post-dialysis start. Significant differences are noted in the pre-dialysis period for patients who survive vs. those who do not survive the first year of dialysis. Early recognition of adverse trends in the pre-dialysis period may create opportunity to intervene to improve early dialysis outcomes.

Effects of renal care coordinator case management on outcomes in incident dialysis patients.

BACKGROUND: Pre-dialysis chronic kidney disease (CKD) care impacts dialysis start and incident dialysis outcomes. We describe the use of late stage CKD population data coupled with CKD case management to improve dialysis start. METHODS: The Renal Care Coordinator (RCC) program is a nephrology practice and Fresenius Medical Care North America (FMCNA) partnership involving a case manager resource and data analytics. We studied patients starting dialysis between August 1, 2009 and February 28, 2013 in 9 nephrology practices partnering in the RCC program. Propensity score matching (PSM) was used to match patients who had participated in the RCC program to patients who had not. Primary outcomes were use of a permanent access or peritoneal dialysis (PD) at first outpatient dialysis. Serum albumin at the first outpatient dialysis treatment and mortality and hospitalization rates in the first 120 days of dialysis were secondary outcomes. RESULTS: In the nephrology practices studied, 7,626 patients started dialysis. Of these, 738 patients (9.7%) were enrolled in the RCC program; 693 RCC patients (93.9%) were matched with 693 patients who did not participate in the RCC program. Logistic regression analysis indicates that RCC program patients are more likely to start PD or use a permanent vascular access at dialysis start and are more likely to start treatment with a serum albumin level ≥ 4.0 g/ dL. CONCLUSION: Late stage CKD data-driven case management is associated with a higher rate of PD use, lower central venous catheter (CVC) use, and higher albumin levels at first outpatient dialysis.

The benefits of exercise for CKD patients.

People with chronic kidney disease and end-stage renal disease often suffer from multiple related disorders, progressive deconditioning, and loss of functional capacity. Yet increased physical activity has been shown to improve patients' quality of life and nutrition, reduce inflammation and depression, and decrease treatment costs and the need for hospitalization. Exercise training should thus be considered an important part of the overall care of people with CKD, while increased physical activity is beneficial at all stages of the disease and can help empower patients to take more control over their own health.

The role of the medical director: changing with the times.

The role of the dialysis unit Medical Director has evolved over time to an expanded set of roles from one that used to be strictly "medical" to one that is more "managerial." Physicians providing these Medical Director services are facing increasing demands for a leadership role regarding clinical quality improvement and measurement of performance in core areas of care within the dialysis program. The dialysis Medical Director is asked to lead in group decision-making, in analyzing core process and patient outcomes and in stimulating a team approach to Continuous Quality Improvement (CQI) and patient safety. For the end-stage renal disease program, national quality expectations in dialysis care have stimulated the dialysis providers to measure, report and respond consistently in an effort to provide a higher level of cost-efficient care. Medical Directors are usually contractually linked to the dialysis programs for which they provide oversight and their contracts are explicit about the relationship they maintain and the role they are expected to play within dialysis companies (often called "provider organizations"). The evolution of the Medical Director role has led to a close relationship between the company that provides the dialysis services and the physician providing the medical oversight.

Characterizing the ideal clinical office system for nephrology.

Clinical information technology (IT) systems that support nephrology-specific content can facilitate the coordinated, progressive, and comprehensive care of all patients with renal disease including those with each stage of chronic kidney disease (CKD). The ideal clinical IT system should have flexible features to meet the needs of individualized practice patterns, yet also have tools to enhance continuity, measure performance, and deliver decision support features that assist the nephrologist in providing optimal care for the CKD patient. This article provides insight into the complexities of engaging in the process of technology adoption, including selection, integration, and implementation while emphasizing the utility of using a continuous quality improvement paradigm to identify and achieve positive results from the adoption and integration of a clinical IT system into outpatient clinical practice of nephrology.