Predicting First-Year Mortality in Incident Dialysis Patients with End-Stage Renal Disease - The UREA5 Study

Chua, Horng-Ruey; Lau, Titus; Luo, Nan; Ma, Valerie; Teo, Boon Wee; Haroon, Sabrina; Choy, Kwan-Loong; Lim, Y N; Ch'ng, W.P.P.; Ong, Lizhen; Wong, Eddy W.Y.; Lee, Evan

doi:10.1159/000357640

Cited by 34 publications

(44 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…26 However, as our results indicate and previous work has suggested, models to predict mortality based solely on administrative data 6 perform worse than models based on clinical data. 27 An open clinical question is how to assess near-term risk of disease. 28 This work shows how this is possible: through the use of dynamic data.…”

Section: Discussionmentioning

confidence: 99%

Predicting mortality over different time horizons: which data elements are needed?

Goldstein

Pencina

Montez‐Rath

et al. 2016

Journal of the American Medical Informatics Association

View full text Add to dashboard Cite

Objective: Electronic health records (EHRs) are a resource for "big data" analytics, containing a variety of data elements. We investigate how different categories of information contribute to prediction of mortality over different time horizons among patients undergoing hemodialysis treatment. Material and Methods: We derived prediction models for mortality over 7 time horizons using EHR data on older patients from a national chain of dialysis clinics linked with administrative data using LASSO (least absolute shrinkage and selection operator) regression. We assessed how different categories of information relate to risk assessment and compared discrete models to time-to-event models. Results: The best predictors used all the available data (c-statistic ranged from 0.72-0.76), with stronger models in the near term. While different variable groups showed different utility, exclusion of any particular group did not lead to a meaningfully different risk assessment. Discrete time models performed better than time-to-event models. Conclusions: Different variable groups were predictive over different time horizons, with vital signs most predictive for near-term mortality and demographic and comorbidities more important in long-term mortality.Key words: Electronic Health Records, hemodialysis, ESRD, predictive modeling OBJECTIVEThe increasing availability of electronic health records (EHRs) offers vast and unique opportunities for biomedical research, at the core of which are predictive modeling and analytics. The presence of diverse data elements allows for the construction of prediction models using a wealth of predictors that may not all be available in more standard settings. Depending on the EHR and other linkable sources, it is generally possible to ascertain information on patients' demographics, health service utilization, diagnosed comorbidities, prescribed medications, results from laboratory tests, and vital signs. In total, these represent a source of "big data" analytics in clinical research. Owing to these variable data elements, EHRs present the opportunity to develop risk models over a range of time horizons. Studies have predicted events from within the next 12 hours 1 to up to 8 years. 2Examples include predicting the risk of adverse outcomes, including administrative events such as hospital readmission, 3 and discrete clinical events such acute kidney injury. 4 As such, each study has abstracted different pieces of information from its respective EHR.-With this in mind, we sought to explore the role EHR data elements play in predicting mortality over different time horizons. This could inform future model development efforts by prioritizing limited resources toward collecting the predictors that provide the most useful

show abstract

Section: Discussionmentioning

confidence: 99%

Predicting mortality over different time horizons: which data elements are needed?

Goldstein

Pencina

Montez‐Rath

et al. 2016

Journal of the American Medical Informatics Association

View full text Add to dashboard Cite

show abstract

“…In the long term, up to 20% of patients with LN develop an end-stage renal disease (ESRD) that requires renal replacement therapies such as haemo-or peritoneal dialysis or kidney transplantation [24]. ESRD and dialysis are correlated with an increased morbidity and mortality and have a significant impact on the costs of the health system [25]. Immunosuppressive therapies as cyclophosphamide, glucocorticoids, azathioprine, mycophenolate mofetil (MMF) and biologicals have improved the disease outcome in the last decades.…”

Section: Lupus Nephritis (Ln)mentioning

confidence: 99%

CXCL13 as a new biomarker of systemic lupus erythematosus and lupus nephritis – from bench to bedside?

Schiffer

Worthmann

Haller

et al. 2014

Clinical and Experimental Immunology

View full text Add to dashboard Cite

SummaryDifferent studies over the last decade have linked the B cell-attracting chemokine CXC ligand 13 (CXCL13) to the autoimmune disease systemic lupus erythematosus (SLE). A pathogenetic role of this chemokine for disease manifestation in SLE was described initially in mouse models for SLE. Mechanisms of CXCL13 actions were also identified in SLE patients. Moreover, various clinical studies have identified CXCL13 serum levels as a useful biomarker in patients with SLE of different ethnicities for disease activity. In addition, CXCL13 seems to be a promising marker for the diagnosis of lupus nephritis, one of the most severe complications of SLE. However, its exact place within the mechanisms that lead to SLE remains to be defined. Further research is needed to resolve more details of the pathomechanism and the signalling pathway of CXCL13 in SLE. Blocking CXCL13 or the signal pathways of CXCL13 is seen as a promising therapeutic approach for SLE and will be addressed in the near future. This review summarizes all papers that linked CXCL13 to SLE and highlights its importance in the pathogenesis and diagnosis of SLE

show abstract

“…The 32 studies included in this review represent a combined population of 1 083 264 new dialysis starters and 283 277 person‐years of observation for early mortality. The characteristics of these studies are shown in Table .…”

Section: Resultsmentioning

confidence: 99%

“…The characteristics of these studies are shown in Table . Studies originating in North America accounted for the majority of observations (12 studies, population: 831559), while the remaining observations originated in Europe (10 studies, population: 93 815 patients), Asia (four studies, combined population of 46 421 patients), Australia‐New Zealand (one study; population: 23 658), Africa (three studies, population: population of 530 patients), and South America (one study, 395 participants). There was also one multinational study , involving developed countries with 86 886 participants.…”

Section: Resultsmentioning

confidence: 99%

Early Mortality Rates After Commencement of Maintenance Hemodialysis: A Systematic Review and Meta‐Analysis

Hazara

Bhandari

2019

Ther Apher Dial

View full text Add to dashboard Cite

Mortality rates are reported to be high soon after the commencement of maintenance HD for ESRD. Our aim was to estimate early mortality rates (deaths within 180 days of starting therapy), through a systematic review of literature, in this patient population. Medline and EMBASE were searched for publications between 1 January 1985 and 31 December 2017. Observational studies reporting deaths involving adults commencing HD were included. The Quality in Prognosis Studies tool was used to assess risk of bias in studies. Crude mortality rates (expressed in 100 person-years) and age-standardized mortality ratios (SMR) were calculated. Meta-analyses of these rates were conducted for studies with lowest risk of bias (i.e. highest quality). In total, 32 studies were included (combined population: 1 083 264) representing 283 277 person-years of observation; median follow-up: 90 days. Mortality rates ranged between 12.8 and 55.6 per 100 person-years. Cardiovascular causes accounted for the majority of early deaths. Meta-analysis of high-quality studies showed an overall crude mortality rate of 32.6 per 100 person-years (95% CI 32.4-32.8). This equates to 16.3% mortality in first 180 days of starting HD. Six highquality studies contained sufficient data for calculation of SMR. Meta-analysis of SMRs showed that patients starting HD therapy sustain 8.8 times higher mortality rates compared to the general population. We have combined the results of high-quality studies to produce new estimates of early mortality rates after commencement of HD therapy. This information can help relay more reliable prognostic information to this patient population.

show abstract

Predicting First-Year Mortality in Incident Dialysis Patients with End-Stage Renal Disease - The UREA5 Study

Cited by 34 publications

References 48 publications

Predicting mortality over different time horizons: which data elements are needed?

Predicting mortality over different time horizons: which data elements are needed?

CXCL13 as a new biomarker of systemic lupus erythematosus and lupus nephritis – from bench to bedside?

Early Mortality Rates After Commencement of Maintenance Hemodialysis: A Systematic Review and Meta‐Analysis

Contact Info

Product

Resources

About