Search

Emergency general surgery (EGS) is a critical component of emergency care in the United States. Due to the time sensitiveness of EGS conditions, ensuring adequate spatial access to EGS services is paramount for reducing patient morbidity and mortality. Past studies have used travel time to measure spatial access to EGS services, which has its limitations. The major purpose of this paper is to evaluate the utility of a gravity-based spatial access model in measuring spatial access to EGS services in California. Our data sources include the American Hospital Association 2015 Annual Survey, the American Community Survey 2013–2017 five-year average dataset, and background geospatial datasets. We implemented both the gravity-based model and the shortest travel time method and compared them in measuring spatial access to EGS-capable hospitals in California at the census block group level. We analyzed each metric's ability to identify disparities in spatial access for the population as a whole, and subsequently to identify socio-demographic disparities. Overall, we found that both methods identified similar geographic and socio-demographic patterns of the spatial access. Native Americans and rural residents experienced the greatest disadvantage in spatial access to both general EGS services and advanced EGS services. However, the gravity-based model revealed more disparities in spatial access to EGS services than the travel time model, suggesting that using travel cost alone to measure spatial access to EGS services may underestimate the magnitude of disparities. These findings call for the use of gravity-based models that incorporate measures of population demand and hospital capacity when assessing spatial access to surgical services, and have implications for reallocating surgery resources to address disparities in spatial access. [ABSTRACT FROM AUTHOR]

At the 2020 International Conference on Health Policy Statistics held in San Diego, Thomas (Tom) R. Belin was awarded the Long-Term Excellence Award from the Health Policy Statistics Section of the American Statistical Association. Dr. Belin was exceptionally and uniquely qualified for this award. Highlights include his innovative statistical applications for health care research and his substantial contributions to the statistics and health policy communities through mentoring and service. In this interview, we asked Tom to share stories about his upbringing, schooling, and career phases to gain insights into his numerous achievements. [ABSTRACT FROM AUTHOR]

The quality of propensity scores is traditionally measured by assessing how well they make the distributions of covariates in the treatment and control groups match, which we refer to as 'good balance'. Good balance guarantees less biased estimates of the treatment effect. However, the cost of achieving good balance is that the variance of the estimates increases due to a reduction in effective sample size, either through the introduction of propensity score weights or dropping cases when propensity score matching. In this paper, we investigate whether it is best to optimize the balance or to settle for a less than optimal balance and use double robust estimation to adjust for remaining differences. We compare treatment effect estimates from regression, propensity score weighting, and double robust estimation with varying levels of effort expended to achieve balance using data from a study about the differences in outcomes by HIV status in heterosexually active homeless men residing in Los Angeles. Because of how costly data collection efforts are for this population, it is important to find an alternative estimation method that does not reduce effective sample size as much as methods that aggressively aim to optimize balance. Results from a simulation study suggest that there are instances in which we can obtain more precise treatment effect estimates without increasing bias too much by using a combination of regression and propensity score weights that achieve a less than optimal balance. There is a bias-variance tradeoff at work in propensity score estimation; every step toward better balance usually means an increase in variance and at some point a marginal decrease in bias may not be worth the associated increase in variance. [ABSTRACT FROM AUTHOR]

The Consent-to-Contact (C2C) registry at the University of California, Irvine collects data from community participants to aid in the recruitment to clinical research studies. Self-selection into the C2C likely leads to bias due in part to enrollees having more years of education relative to the US general population. Salazar et al. (Alzheimer's Dementia Transl Res Clin Interv 6(1):e120023, 2020, https://doi.org/10.1002/trc2.12023) recently used the C2C to examine associations of race/ethnicity with participant willingness to be contacted about research studies. To obtain representative estimates from C2C we use weighted estimation of associations of interest where the weights are related to the probability of self-selection into the convenience sample. The selection probabilities are estimated using data from the National Health and Nutrition Examination Survey (NHANES). We create a combined dataset of C2C and NHANES subjects and evaluate the trade-offs of different approaches (logistic regression, covariate balancing propensity score, entropy balancing, and random forest) for estimating the probability of membership in C2C relative to NHANES. We further propose methods to estimate the variance of parameter estimates that account for uncertainty that arises from estimating propensity weights. Simulation studies explore the impact of propensity weight estimation on uncertainty. We demonstrate the approach by repeating the analysis by Salazar et al. (Alzheimer's Dementia Transl Res Clin Interv 6(1):e120023, 2020, https://doi.org/10.1002/trc2.12023) with the deduced propensity weights for the C2C subjects and contrast the results of the two analyses. This method can be implemented using our estweight package in R available on GitHub. [ABSTRACT FROM AUTHOR]

This study evaluates the statistical relationship between hospital lung cancer surgery volume and mortality among 14,456 lung cancer resection patients in 330 California hospitals from 1996–1999. The actual volume of lung cancer surgery performed in each hospital during the 12 months before a patient’s surgery is compared to average annual volume, which is a measure of volume commonly used in prior studies. Multivariable logistic regression with restricted cubic splines is used to model nonlinearity using highly flexible functional forms for the volume-outcome relationship. Prior 12 month volume and average annual volume had nearly equivalent relationships to mortality. The non-linear components of these relationships were not statistically significant. This study provides additional evidence for a statistically significant inverse relationship between hospital lung cancer resection volume and patient mortality, using methods that correctly account for temporal order and that more precisely address the potential for nonlinearity. Though statistically significant, very large decreases in hospital surgical volume were associated with small absolute increases in mortality risk. [ABSTRACT FROM AUTHOR]