2015
DOI: 10.1097/tp.0000000000000565
|View full text |Cite
|
Sign up to set email alerts
|

Inclusion of Dynamic Clinical Data Improves the Predictive Performance of a 30-Day Readmission Risk Model in Kidney Transplantation

Abstract: Background 30-day readmissions (30DRA) are a highly scrutinized measure of healthcare quality and relatively frequent among kidney transplants (KTX). Development of predictive risk models are critical to reducing 30DRA and improving outcomes. Current approaches rely on fixed variables derived from administrative data. These models may not capture clinical evolution that is critical to predicting outcomes. Methods We directed a retrospective analysis towards: 1) developing parsimonious risk models for 30DRA a… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
33
0

Year Published

2017
2017
2022
2022

Publication Types

Select...
4
3
1

Relationship

0
8

Authors

Journals

citations
Cited by 36 publications
(33 citation statements)
references
References 33 publications
0
33
0
Order By: Relevance
“…With the explosion in the amounts of patient‐level data available through electronic health records (EHRs), analyses could potentially incorporate dynamically evolving clinically relevant patient‐level data in a meaningful manner that may inform on the care of individual patients or subpopulations of patients at highest risk of GL or death. Using manually extracted EHR data, we have previously demonstrated that addition of dynamic patient‐level data improves predictive accuracy over administrative data for 30‐day readmissions following kidney transplantation (demonstrated by others as a surrogate for subsequent GL) . However, broad applicability of such an approach outside research contexts is limited by practical constraints to achieving near real‐time capture of structured clinical data and more importantly, the need for manual abstraction of unstructured data fields (e.g.…”
Section: Introductionmentioning
confidence: 99%
“…With the explosion in the amounts of patient‐level data available through electronic health records (EHRs), analyses could potentially incorporate dynamically evolving clinically relevant patient‐level data in a meaningful manner that may inform on the care of individual patients or subpopulations of patients at highest risk of GL or death. Using manually extracted EHR data, we have previously demonstrated that addition of dynamic patient‐level data improves predictive accuracy over administrative data for 30‐day readmissions following kidney transplantation (demonstrated by others as a surrogate for subsequent GL) . However, broad applicability of such an approach outside research contexts is limited by practical constraints to achieving near real‐time capture of structured clinical data and more importantly, the need for manual abstraction of unstructured data fields (e.g.…”
Section: Introductionmentioning
confidence: 99%
“…Prevention of hospital readmissions has been a critical topic in health care . Today, health systems continue to seek methods to reduce patients’ hospital LOS while concurrently reducing readmission rates . Kidney transplant recipients are medically complex with various comorbidities.…”
Section: Discussionmentioning
confidence: 99%
“…20,21 Today, health systems continue to seek methods to reduce patients' hospital LOS while concurrently reducing readmission rates. 22 Kidney transplant recipients are medically complex with various comorbidities. Treatment of this population requires unique strategies to reduce hospital LOS following transplantation and prevent readmissions while simultaneously maintaining successful health outcomes.…”
Section: Discussionmentioning
confidence: 99%
“…Models designed for these purposes should have good predictive ability; be deployable in large populations; use reliable data that can be easily obtained; and use variables that are clinically related to and validated in the populations in which use is intended [12], [13]. According to recent review conducted by [24], the utilization outcome of existing readmission prediction models include all-cause admissions such as [25], cardiovascular-related disease including pneumonia such as [26], medical/internal medicine conditions such as [27], surgical conditions such as [28] and mental health conditions such as [29]. There is no model developed for readmission risk for all comorbidity patients.…”
Section: Literature Reviewmentioning
confidence: 99%