Search

Model selection in the presence of interaction terms is challenging as the final model must maintain a hierarchy between main effects and interaction terms. This work presents two stagewise estimation approaches to appropriately select models with interaction terms that can utilize generalized estimating equations to model clustered data. The first proposed technique is a hierarchical lasso stagewise estimating equations approach, which is shown to directly correspond to the hierarchical lasso penalized regression. The second is a stagewise active set approach, which enforces the variable hierarchy by conforming the selection to a properly growing active set in each stagewise estimation step. The effectiveness in interaction selection and the superior computational efficiency of the proposed techniques are assessed in simulation studies. The new methods are applied to a study of hospitalization rates attributed to suicide attempts among 15 to 19 year old at the school district level in Connecticut. [ABSTRACT FROM AUTHOR]

Objective: Preventable hospitalizations for heart failure result in a large proportion of hospitalizations. The primary objective of this study was to describe longitudinal trends in the association of race/ethnicity with preventable hospitalizations for heart failure in Connecticut and differences in disparities by age. Methods: We analyzed data on hospitalizations in all civilian acute-care hospitals in Connecticut during a 7-year period, 2009 through 2015. We used raking methodology to weight the nonhospitalized population to create a reference population representative of the state's general population. Multivariate regression models examined racial/ethnic disparities among adults aged 35-64, controlling for age, sex, and type of health insurance. For adults aged ≥65, regression models controlled for age and sex. Results: After controlling for age and sex, the non-Hispanic black to non-Hispanic white odds ratio for preventable hospitalizations for heart failure ranged from 5.2-6.4 during the study period among adults aged 35-64. Among adults aged ≥65, non-Hispanic black adults had significantly higher odds (range, 1.2-1.8) of preventable hospitalizations than non-Hispanic white adults. Rates among Hispanic adults were significantly higher than rates among non-Hispanic adults after controlling for age and sex among adults aged ≥65 in 2014 and 2015. Conclusions: This research provides information for clinical and population-based interventions targeting racial/ethnic gaps in heart failure hospitalizations. Demonstrating the persistent black–white disparity and age differences in racial/ethnic disparities, this study emphasizes the need for focused prevention among vulnerable populations. Raking methodology is an innovative approach to eliminating selection bias in hospital discharge data. [ABSTRACT FROM AUTHOR]

The geographic distribution of nonprofit antipoverty organizations has important implications for economic development, social services, public health, and policy efforts. With counts of antipoverty nonprofits at the census tract level in Greater Hartford, Connecticut, we examine whether these organizations are located in areas with high levels of poverty with a spatial zero-inflated-Poisson model. Covariates that measure need, resources, urban structure, and demographic characteristics are incorporated into both the zero-inflation component and the Poisson component of the model. Variation not explained by the covariates is captured by the combination of a spatial random effect and an unstructured random effect. Statistical inferences are done within the Bayesian framework. Model comparison with the conditional predictive ordinate suggests that the random effects and the zero-inflation are both important components in fitting the data. All three need measures—proportion of people below the poverty line, unemployment rate, and rental occupancy—are found to have significantly positive effect on the mean of the count, providing evidence that antipoverty nonprofits tend to locate where they are needed. The dataset and R/OpenBUGS code are available in supplementary materials online. [ABSTRACT FROM AUTHOR]

Background: Racial and ethnic disparities in hospital readmissions following total joint arthroplasty present opportunities for reducing cost and improving health equity. Despite efforts to reduce readmissions following total joint arthroplasty in the general population, no studies have documented the impact of these efforts on racial and ethnic disparities in total joint arthroplasty readmissions. The purpose of this study was to determine whether comprehensive efforts to reduce hospital readmissions following total joint arthroplasty have impacted racial and ethnic disparities in readmission rates during the period from 2005 to 2015., Methods: We conducted a retrospective analysis comparing patients readmitted and not readmitted to the hospital within 30 days of a total joint arthroplasty by estimating logistic regression models for clustered data using generalized estimating equations (GEEs) in R. Connecticut hospital discharge data for patients admitted for International Classification of Diseases, Ninth Revision (ICD-9) procedure codes 81.51 and 81.54 (Current Procedural Terminology [CPT] codes 27130 and 27447) during the 2005 to 2015 U.S. Centers for Medicare & Medicaid Services (CMS) fiscal years were analyzed. Models included quadratic terms to capture nonlinear time trends in readmissions, as well as terms for the statistical interaction between race or ethnicity and both the linear and quadratic time trends in predicting the odds of readmission., Results: There were 102,510 total admissions to Connecticut hospitals for total joint arthroplasty from 2005 to 2015. The 30-day (all-cause) readmission rate declined from 5.1% in 2005 to 3.6% in 2015, with a steeper downward trend observed from 2009 to 2015. The results from logistic models indicated that black patients (odds ratio [OR], 1.68; p < 0.0001) and Hispanic patients (OR, 1.48; p < 0.0001) were significantly more likely to be readmitted within 30 days of discharge following a total joint arthroplasty than white patients over the study period. The significant interaction of black race and the quadratic time trend in models capturing nonlinear trends in readmission over time indicated that the readmission rates for black patients increased compared with those for white patients from 2005 through 2008 and decreased relative to those for white patients from 2009 to 2015 (OR, 0.24; p = 0.030)., Conclusions: Data from Connecticut hospitals show that 30-day readmissions following a total joint arthroplasty declined by 1.5 percentage points from 2005 to 2015, and that this decline was much more pronounced among black patients, resulting in the narrowing of racial disparities in readmission following a surgical procedure., Clinical Relevance: Racial and ethnic minorities have historically been at increased risk for complications and readmission following hospital-based surgical care. This analysis of readmission following total joint arthroplasty reveals that such disparities are remediable and should foster further research on the primary drivers of and remedies for readmission disparities.

Objective: To examine 30-day readmission rates after vaginal and cesarean delivery by race-ethnicity and insurance status., Methods: We analyzed hospital discharge data contained in a statewide database maintained by the Connecticut Department of Public Health. Discharge data for patients admitted for vaginal delivery without complication (n=167,857) and cesarean delivery without complication (n=75,552) from 2005 to 2012 were analyzed using marginal logistic models for clustered data with generalized estimating equations., Results: Results from logistic models indicated that 30-day readmission rates per 1,000 patients were significantly higher among black (28.9/1,000; confidence interval [CI] 25.5-32.7) and Hispanic women (21.4/1,000; CI 18.9-24.2) than among white women (12.9/1,000; CI 11.9-14.0) after cesarean delivery. Similarly higher rates of readmission were observed for black (14.6/1,000; CI 13.0-16.5) and Hispanic women (10.7/1,000; CI 9.6-12.0) relative to white women (7.5/1,000; CI 7.0-8.1) after vaginal delivery. Rates of 30-day readmission were significantly higher (odds ratio 1.27-1.30) among those covered by Medicaid. Controlling for patient socioeconomic status, comorbidities, and payer did not substantially reduce race and ethic differences in the odds of readmission., Conclusion: Significant racial and ethnic disparities in readmissions were observed for procedures related to childbirth using a statewide database capturing all payers across all acute care hospital settings. Compared with white women, black women were twice as likely and Hispanic women 40-50% more likely to be readmitted within 30 days of vaginal or cesarean delivery., Level of Evidence: II.

Background: Racial and ethnic disparities in hospital readmissions for several major illnesses and conditions are well-documented. However, due to the data typically used to assess readmission disparities little is known regarding the interplay between race/ethnicity and payer in fostering readmissions. This study used a statewide database of acute-care hospital admissions to examine 30-day readmission rates following hospitalization for chest pain and heart failure byrace/ethnicity and insurance status., Methods: Connecticut hospital discharge data for patients admitted for Chest Pain-DRG 313 (n = 23,450) and Heart Failure and Shock-DRG 291 and 292 (n = 39,985) from 2008 - 2012 were analyzed using marginal logistic models for clustered data with generalized estimating equations., Results: Results from logistic models indicated that Black patients were significantly more likely to be readmitted within 30 days of discharge following hospitalization for chest pain (OR = 1.19, CI = 1.04, 1.37) than were White patients. Hispanics, but not Blacks, were significantly more likely to be readmitted within 30 days of discharge following hospitalization for heart failure (OR = 1.30, CI = 1.15, 1.47). Rates of 30-day readmission across these conditions were between 50-100% higher among those covered by Medicaid compared to those covered by private payer. Controlling for patient socioeconomic status, patient comorbidities, and payer substantially reduced Black/White differences in the odds of readmission for chest pain but did not reduce Hispanic-White differences for heart failure., Conclusions: Racial and ethnic disparities were seen in hospital readmission rates for Chest Pain (DRG 313) and Heart Failure and Shock (DRG 291 and 292) when a statewide database that captures all acute care hospital admissions was analyzed. When controlling for patient socioeconomic status, comorbidities, and payer status, the difference in the odds of readmission for chest pain, but not heart failure, was reduced.