scholarly journals Causal variance decompositions for institutional comparisons in healthcare

2019 ◽  
Vol 29 (7) ◽  
pp. 1972-1986
Author(s):  
Bo Chen ◽  
Keith A Lawson ◽  
Antonio Finelli ◽  
Olli Saarela
Keyword(s):  
Random Effect ◽  
Real Data ◽  
Hospital Performance ◽  
Case Mix ◽  
Link Functions ◽  
Variation In Care ◽  
Residual Variation ◽  
Data Application ◽  
Variance Decompositions ◽  
Random Effect Models

There is increasing interest in comparing institutions delivering healthcare in terms of disease-specific quality indicators (QIs) that capture processes or outcomes showing variations in the care provided. Such comparisons can be framed in terms of causal models, where adjusting for patient case-mix is analogous to controlling for confounding, and exposure is being treated in a given hospital, for instance. Our goal here is to help identify good QIs rather than comparing hospitals in terms of an already chosen QI, and so we focus on the presence and magnitude of overall variation in care between the hospitals rather than the pairwise differences between any two hospitals. We consider how the observed variation in care received at patient level can be decomposed into that causally explained by the hospital performance adjusting for the case-mix, the case-mix itself, and residual variation. For this purpose, we derive a three-way variance decomposition, with particular attention to its causal interpretation in terms of potential outcome variables. We propose model-based estimators for the decomposition, accommodating different link functions and either fixed or random effect models. We evaluate their performance in a simulation study and demonstrate their use in a real data application.

Abstract 005: A Comparison of Methods for Identifying Hospital Performance Outliers in Cardiac Surgery

2017 ◽  
Vol 10 (suppl_3) ◽  
Author(s):  
Xiaoting Wu ◽  
Min Zhang ◽  
Richard L Prager ◽  
Donald S Likosky
Keyword(s):  
Logistic Regression ◽  
Regression Models ◽  
Random Effect ◽  
Hospital Performance ◽  
Fixed Effect ◽  
Logistic Regression Models ◽  
Indirect Standardization ◽  
Statistical Approaches ◽  
Random Effect Models ◽  
Direct Standardization

Introduction: A number of statistical approaches have been advocated and implemented to estimate adjusted hospital outcomes for public reporting or reimbursement. Nonetheless, the ability of these methods to identify hospital performance outliers in support of quality improvement has not yet been fully investigated. Methods: We leveraged data from patients undergoing coronary artery bypass grafting surgery between 2012-2015 at 33 hospitals participating in a statewide quality collaborative. We applied 5 different statistical approaches (1: indirect standardization with standard logistic regression models, 2: indirect standardization with fixed effect models, 3: indirect standardization with random effect models, 4: direct standardization with fixed effect models, 5: direct standardization with random effect models) to estimate hospital post-operative pneumonia rates adjusting for patients’ risk. Unlike the standard logistic regression models, both fixed effect and random effect models accounted for hospital effect. We applied each method to each year, and subsequently compared methods in their ability to identify hospital performance outliers. Results: Pneumonia rates ranged from 0 % to 24 %. The standard logistic regression models for 2013-2015 had c-statistics of 0.73-0.75, fixed effect models had c-statistics of 0.81-0.83, and random effect models had c-statistics of 0.80-0.83. Each method differed in its ability to identify performance outliers (Figure 1). In direct standardization, random effect models stabilized the hospital rates by moving the estimated rates toward the average rate, fixed effect models produced larger standard errors of hospital effect (particularly for hospitals with low case volumes). In indirect standardization, the three models showed high agreement on their derived observed: expected ratio (intraclass correlation =0.95). Indirect standardization with fixed effect or random effect models, identified similar hospital performance outliers in each year. Conclusion: The five statistical approaches varied in their ability to identify performance outliers. Given its higher sensitivity to outlier hospitals, indirect standardization methods with fixed or random effect models, may be best suited to support quality improvement activities.

scholarly journals The effect of data aggregation on dispersion estimates in count data models

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Adam Errington ◽  
Jochen Einbeck ◽  
Jonathan Cumming ◽  
Ute Rössler ◽  
David Endesfelder
Keyword(s):  
Count Data ◽  
Data Aggregation ◽  
Random Effect ◽  
Real Data ◽  
Data Sets ◽  
Count Data Models ◽  
Response Curves ◽  
Poisson Models ◽  
Random Effect Models ◽  
Radiation Biodosimetry

Abstract For the modelling of count data, aggregation of the raw data over certain subgroups or predictor configurations is common practice. This is, for instance, the case for count data biomarkers of radiation exposure. Under the Poisson law, count data can be aggregated without loss of information on the Poisson parameter, which remains true if the Poisson assumption is relaxed towards quasi-Poisson. However, in biodosimetry in particular, but also beyond, the question of how the dispersion estimates for quasi-Poisson models behave under data aggregation have received little attention. Indeed, for real data sets featuring unexplained heterogeneities, dispersion estimates can increase strongly after aggregation, an effect which we will demonstrate and quantify explicitly for some scenarios. The increase in dispersion estimates implies an inflation of the parameter standard errors, which, however, by comparison with random effect models, can be shown to serve a corrective purpose. The phenomena are illustrated by γ-H2AX foci data as used for instance in radiation biodosimetry for the calibration of dose-response curves.

scholarly journals Potential of community-based risk estimates for improving hospital performance measures and discharge planning

2021 ◽  
Vol 10 (2) ◽  
pp. e001230
Author(s):  
Michael Reid ◽  
George Kephart ◽  
Pantelis Andreou ◽  
Alysia Robinson
Keyword(s):  
Discharge Planning ◽  
Care Transitions ◽  
Hospital Setting ◽  
Hospital Performance ◽  
Case Mix ◽  
Readmission Rates ◽  
Mixed Effect ◽  
Adjusted Risk ◽  
Community Risk ◽  
Effect Regression

BackgroundRisk-adjusted rates of hospital readmission are a common indicator of hospital performance. There are concerns that current risk-adjustment methods do not account for the many factors outside the hospital setting that can affect readmission rates. Not accounting for these external factors could result in hospitals being unfairly penalized when they discharge patients to communities that are less able to support care transitions and disease management. While incorporating adjustments for the myriad of social and economic factors outside of the hospital setting could improve the accuracy of readmission rates as a performance measure, doing so has limited feasibility due to the number of potential variables and the paucity of data to measure them. This paper assesses a practical approach to addressing this problem: using mixed-effect regression models to estimate case-mix adjusted risk of readmission by community of patients’ residence (community risk of readmission) as a complementary performance indicator to hospital readmission rates.MethodsUsing hospital discharge data and mixed-effect regression models with a random intercept for community, we assess if case-mix adjusted community risk of readmission can be useful as a quality indicator for community-based care. Our outcome of interest was an unplanned repeat hospitalisation. Our primary exposure was community of residence.ResultsCommunity of residence is associated with case-mix adjusted risk of unplanned repeat hospitalisation. Community risk of readmission can be estimated and mapped as indicators of the ability of communities to support both care transitions and long-term disease management.ConclusionContextualising readmission rates through a community lens has the potential to help hospitals and policymakers improve discharge planning, reduce penalties to hospitals, and most importantly, provide higher quality care to the people that they serve.

scholarly journals LO84: The incidence of fall-related intracranial bleeding in older adults taking anticoagulants, antiplatelets and neither medication: a meta-analysis

CJEM ◽  
2020 ◽  
Vol 22 (S1) ◽  
pp. S38-S38
Author(s):  
K. de Wit ◽  
D. Nishijima ◽  
S. Mason ◽  
R. Jeanmonod ◽  
S. Parpia ◽  
...  
Keyword(s):  
Older Adults ◽  
Meta Analysis ◽  
Grey Literature ◽  
Random Effect ◽  
Intracranial Bleeding ◽  
Inclusion Criteria ◽  
Antiplatelet Medication ◽  
Cochrane Database ◽  
Random Effect Models ◽  
Anticoagulant Medication

Introduction: It is unclear whether anticoagulant or antiplatelet medications increase the risk for intracranial bleeding in older adults after a fall. Our aim was to report the incidence of intracranial bleeding among older adults presenting to the emergency department (ED) with a fall, among patients taking anticoagulants, antiplatelet medications, both medications and neither medication. Methods: This was a systematic review and meta-analysis, PROSPERO reference CRD42019122626. Medline, EMBASE (via OVID 1946 - July 2019), Cochrane, Database of Abstracts of Reviews of Effects databases and the grey literature were searched for studies reporting on older adults who were evaluated after a fall. We included prospective studies conducted in the ED where more than 80% of the cohort were 65 years or older and had fallen. We contacted study authors for aggregate data on intracranial bleeding in patients prescribed anticoagulant medication, antiplatelet medication and neither medication. Incidences of intracranial bleeding were pooled using random effect models, and I2 index was used to assess heterogeneity. Results: From 7,240 publication titles, 10 studies met inclusion criteria. The authors of 8 of these 10 studies provided data (on 9,489 patients). All studies scored low or moderate risk of bias. The pooled incidence of intracranial bleeding among patients taking an anticoagulant medication was 5.1% (n = 5,016, 95% Confidence Interval (CI): 4.1 to 6.3%) I2 = 42%, a single antiplatelet 6.4% (n = 2,148, 95% CI: 5.4 to 7.6%) I2 = 75%, both anticoagulant and antiplatelet medications 5.9% (n = 212, 95% CI: 1.3 to 13.5%) I2 = 72%, and neither of these medications 4.8% (n = 1,927, 95% CI: 3.5 to 6.2%) I2 = 50%. A sensitivity analysis restricted to patients who had a head CT in the ED reported incidences of 6.1% (n = 3,561, 95% CI: 3 to 8.3%), 8.4% (n = 1,781, 95% CI: 5.5 to 11.8%), 6.7% (n = 206, 95% CI 1.5 to 15.2%) and 6.6% (n = 1,310, 95% CI: 5.0 to 8.4%) respectively. Conclusion: The incidence of fall-related intracranial bleeding in older ED patients was similar among patients who take anticoagulant medication, antiplatelet medication, both and neither medication, although there was heterogeneity between study findings.

Correlation between Methylenetetrahydrofolate Reductase Polymorphisms and Hepatocellular Carcinoma: A Meta-Analysis

2019 ◽  
Vol 74 (3) ◽  
pp. 251-256 ◽  
Author(s):  
Hailong Su ◽  
Guo Zhang
Keyword(s):  
Hepatocellular Carcinoma ◽  
Gene Polymorphisms ◽  
Methylenetetrahydrofolate Reductase ◽  
Meta Analysis ◽  
Random Effect ◽  
Recessive Model ◽  
Mthfr Gene ◽  
Systematic Research ◽  
The Relationship ◽  
Random Effect Models

Background: The correlation between methylenetetrahydrofolate reductase (MTHFR) gene polymorphisms and hepatocellular carcinoma (HCC) remains controversial. Objectives: We performed this study to better assess the relationship between MTHFR gene polymorphisms and the likelihood of HCC. Methods: A systematic research of PubMed, Medline, and Embase was performed to retrieve relevant articles. ORs and 95% CIs were calculated. Results: A total of 15 studies with 8,378 participants were analyzed. In overall analyses, a significant association with the likelihood of HCC was detected for the rs1801131 polymorphism with fixed-effect models (FEMs) in recessive comparison (p = 0.002, OR 0.62, 95% CI 0.43–0.82). However, no positive results were detected for the rs1801133 polymorphism in any comparison. Further subgroup analyses revealed that the rs1801131 polymorphism was significantly associated with the likelihood of HCC in Asians with both FEMs (recessive model: p < 0.0001, OR 0.42, 95% CI 0.29–0.62; allele model: p = 0.004, OR 1.20, 95% CI 1.06–1.35) and random-effect models (recessive model: p = 0.002, OR 0.47, 95% CI 0.29–0.75). Nevertheless, we failed to detect any significant correlation between the rs1801133 polymorphism and HCC. Conclusions: Our findings indicated that the rs1801131 polymorphism may serve as a genetic biomarker of HCC in Asians.

scholarly journals Multivariate random effect models with complete and incomplete data

2012 ◽  
Vol 109 ◽  
pp. 146-155 ◽  
Author(s):  
James O. Chipperfield ◽  
David G. Steel
Keyword(s):  
Incomplete Data ◽  
Random Effect ◽  
Random Effect Models

scholarly journals Slash Truncation Positive Normal Distribution and Its Estimation Based on the EM Algorithm

Symmetry ◽  
2021 ◽  
Vol 13 (11) ◽  
pp. 2164
Author(s):  
Héctor J. Gómez ◽  
Diego I. Gallardo ◽  
Karol I. Santoro
Keyword(s):  
Expectation Maximization Algorithm ◽  
Likelihood Estimation ◽  
Real Data ◽  
Simulation Studies ◽  
R Software ◽  
Data Application ◽  
The Em Algorithm ◽  
Kurtosis Parameter ◽  
Computational Implementation ◽  
Moments Method

In this paper, we present an extension of the truncated positive normal (TPN) distribution to model positive data with a high kurtosis. The new model is defined as the quotient between two random variables: the TPN distribution (numerator) and the power of a standard uniform distribution (denominator). The resulting model has greater kurtosis than the TPN distribution. We studied some properties of the distribution, such as moments, asymmetry, and kurtosis. Parameter estimation is based on the moments method, and maximum likelihood estimation uses the expectation-maximization algorithm. We performed some simulation studies to assess the recovery parameters and illustrate the model with a real data application related to body weight. The computational implementation of this work was included in the tpn package of the R software.

Sign in / Sign up

Export Citation Format

Share Document