This article is concerned with evaluating the association between two event times without specifying the joint distribution parametrically. This is particularly challenging when the observations on ...the event times are subject to informative censoring due to a terminating event such as death. There are few methods suitable for assessing covariate effects on association in this context. We link the joint distribution of the two event times and the informative censoring time using a nested copula function. We use flexible functional forms to specify the covariate effects on both the marginal and joint distributions. In a semiparametric model for the bivariate event time, we estimate simultaneously the association parameters, the marginal survival functions, and the covariate effects. A byproduct of the approach is a consistent estimator for the induced marginal survival function of each event time conditional on the covariates. We develop an easy-to-implement pseudolikelihood-based inference procedure, derive the asymptotic properties of the estimators, and conduct simulation studies to examine the finite-sample performance of the proposed approach. For illustration, we apply our method to analyze data from the breast cancer survivorship study that motivated this research.
Supplementary materials
for this article are available online.
Objectives
Repeated presentations to emergency departments (EDs) may indicate a lack of access to other health care resources. Age is an important predictor of frequent ED use; however, age-varying ...effects are not generally investigated. This study examines the age-specific effects of predictors on ED presentation frequency for children in Alberta and Ontario, Canada.
Methods
This retrospective study used population-based data during April 2010 to March 2017. Data were extracted from the National Ambulatory Care Reporting System for children aged <18 who were members of the top 10% of ED users in any one of the fiscal years 2011/2012 to 2015/2016 along with a comparison sample from the bottom 90%. A marginal regression model studied the age-varying associations on the frequency of ED presentations with province, sex, access to primary health care provider (for Ontario only), area of residence and lowest neighbourhood income quintile.
Results
There were 2,481,172 patients who made 9,229,156 ED presentations. The effects of sex, lowest income quintile, rural residence, access to primary health care provider and province on the frequency of presentations varied by age. Notably, boys go from having more frequent presentations than girls when aged ≤5 (i.e. adjusted intensity ratio IR=1.04 at age 5, 95% confidence interval CI = 1.03,1.06) to less frequent for ages 8–11 years and beyond 14 (i.e. IR = 0.80 at age 15, 95% CI = 0.78,0.81). Adolescents aged ≥15 without access to a primary care provider had more frequent presentations compared to those with a primary care provider.
Conclusions
When examining the frequency of ED presentations in children, age-varying effects of predictors should be considered. Our more nuanced examination of age provides insights into how health services might better target programmes for different ages to potentially reduce unnecessary ED use by providing other health care alternatives.
Since the beginning of the global pandemic of Coronavirus (SARS-COV-2), there has been many studies devoted to predicting the COVID-19 related deaths/hospitalizations. The aim of our work is to (1) ...explore the lagged dependence between the time series of case counts and the time series of death counts; and (2) utilize such a relationship for prediction. The proposed approach can also be applied to other infectious diseases or wherever dynamics in lagged dependence are of primary interest. Different from the previous studies, we focus on time-varying coefficient models to account for the evolution of the coronavirus. Using two different types of time-varying coefficient models, local polynomial regression models and piecewise linear regression models, we analyze the province-level data in Canada as well as country-level data using cumulative counts. We use out-of-sample prediction to evaluate the model performance. Based on our data analyses, both time-varying coefficient modeling strategies work well. Local polynomial regression models generally work better than piecewise linear regression models, especially when the pattern of the relationship between the two time series of counts gets more complicated (e.g., more segments are needed to portray the pattern). Our proposed methods can be easily and quickly implemented via existing R packages.
Fall-related injuries exert an enormous health burden on older adults in long-term care (LTC). Softer landing surfaces, such as those provided by low-stiffness "compliant" flooring, may prevent ...fall-related injuries by decreasing the forces applied to the body during fall impact. Our primary objective was to assess the clinical effectiveness of compliant flooring at preventing serious fall-related injuries among LTC residents.
The Flooring for Injury Prevention (FLIP) Study was a 4-year, randomized superiority trial in 150 single-occupancy resident rooms at a single Canadian LTC site. In April 2013, resident rooms were block randomized (1:1) to installation of intervention compliant flooring (2.54 cm SmartCells) or rigid control flooring (2.54 cm plywood) covered with identical hospital-grade vinyl. The primary outcome was serious fall-related injury over 4 years that required an emergency department visit or hospital admission and a treatment procedure or diagnostic evaluation in hospital. Secondary outcomes included minor fall-related injury, any fall-related injury, falls, and fracture. Outcomes were ascertained by blinded assessors between September 1, 2013 and August 31, 2017 and analyzed by intention to treat. Adverse outcomes were not assessed. During follow-up, 184 residents occupied 74 intervention rooms, and 173 residents occupied 76 control rooms. Residents were 64.3% female with mean (SD) baseline age 81.7 (9.5) years (range 51.1 to 104.6 years), body mass index 25.9 (7.7) kg/m2, and follow-up 1.64 (1.39) years. 1,907 falls were reported; 23 intervention residents experienced 38 serious injuries (from 29 falls in 22 rooms), while 23 control residents experienced 47 serious injuries (from 34 falls in 23 rooms). Compliant flooring did not affect odds of ≥1 serious fall-related injury (12.5% intervention versus 13.3% control, odds ratio OR: 0.98, 95% CI: 0.52 to 1.84, p = 0.950) or ≥2 serious fall-related injuries (5.4% versus 7.5%, OR: 0.74, 95% CI: 0.31 to 1.75, p = 0.500). Compliant flooring did not affect rate of serious fall-related injuries (0.362 versus 0.422 per 1,000 bed nights, rate ratio RR: 1.04, 95% CI: 0.45 to 2.39, p = 0.925; 0.038 versus 0.053 per fall, RR: 0.81, 95% CI: 0.38 to 1.71, p = 0.560), rate of falls with ≥1 serious fall-related injury (0.276 versus 0.303 per 1,000 bed nights, RR: 0.97, 95% CI: 0.52 to 1.79, p = 0.920), or time to first serious fall-related injury (0.237 versus 0.257, hazard ratio HR: 0.92, 95% CI: 0.52 to 1.62, p = 0.760). Compliant flooring did not affect any secondary outcome in this study. Study limitations included the following: findings were specific to 2.54 cm SmartCells compliant flooring installed in LTC resident rooms, standard fall and injury prevention interventions were in use throughout the study and may have influenced the observed effect of compliant flooring, and challenges with concussion detection in LTC residents may have prevented estimation of the effect of compliant flooring on fall-related concussions.
In contrast to results from previous retrospective and nonrandomized studies, this study found that compliant flooring underneath hospital-grade vinyl was not effective at preventing serious fall-related injuries in LTC. Future studies are needed to identify effective methods for preventing fall-related injuries in LTC.
ClinicalTrials.gov: NCT01618786.
This paper presents a Bayesian adaptive group least absolute shrinkage and selection operator method to conduct simultaneous model selection and estimation under semiparametric hidden Markov models. ...We specify the conditional regression model and the transition probability model in the hidden Markov model into additive nonparametric functions of covariates. A basis expansion is adopted to approximate the nonparametric functions. We introduce multivariate conditional Laplace priors to impose adaptive penalties on regression coefficients and different groups of basis expansions under the Bayesian framework. An efficient Markov chain Monte Carlo algorithm is then proposed to identify the nonexistent, constant, linear, and nonlinear forms of covariate effects in both conditional and transition models. The empirical performance of the proposed methodology is evaluated via simulation studies. We apply the proposed model to analyze a real data set that was collected from the Alzheimer's Disease Neuroimaging Initiative study. The analysis identifies important risk factors on cognitive decline and the transition from cognitive normal to Alzheimer's disease.
In an attempt to provide a statistical tool for disease screening and prediction, we propose a semiparametric approach to analysis of the Cox proportional hazards cure model in situations where the ...observations on the event time are subject to right censoring and some covariates are missing not at random. To facilitate the methodological development, we begin with semiparametric maximum likelihood estimation (SPMLE) assuming that the (conditional) distribution of the missing covariates is known. A variant of the EM algorithm is used to compute the estimator. We then adapt the SPMLE to a more practical situation where the distribution is unknown and there is a consistent estimator based on available information. We establish the consistency and weak convergence of the resulting pseudo-SPMLE, and identify a suitable variance estimator. The application of our inference procedure to disease screening and prediction is illustrated via empirical studies. The proposed approach is used to analyze the tuberculosis screening study data that motivated this research. Its finite-sample performance is examined by simulation.
Dans le but de fournir des outils pour la détection et la prévision de maladies, les auteures proposent une méthode semi-paramétrique pour l’analyse du modèle de cure aux risques proportionnels de Cox lorsque les observations des temps aux événements sont censurés à droite et que certaines covariables sont manquantes de façon non aléatoire. Afin de faciliter le développement méthodologique, elles utilisent d’abord l’estimateur au maximum de vraisemblance semi-paramétrique (EMVSP) sous l’hypothèse que la distribution conditionnelle des valeurs manquantes est connue. Elles exploitent une version de l’algorithme EM pour calculer l’estimateur, puis adaptent l’EMVSP à une situation plus plausible où cette distribution est inconnue et où il existe un estimateur convergent basé sur l’information connue. Les auteures établissent la convergence en probabilité et la convergence faible du pseudo-EMVSP résultant, puis identifient un estimateur approprié de sa variance. Elles illustrent leur procédure empiriquement sur les données réelles de détection de la tuberculose à l’origine de cet article. Elles examinent également la performance de la méthode par des simulations.
Abstract
Background
Efforts to reduce emergency department (ED) volumes often target frequent users. We examined transitions in care across ED, hospital, and community settings, and in-hospital ...death, for high system users (HSUs) compared to controls.
Methods
Population-based databases provided ED visits and hospitalizations in Alberta and Ontario, Canada. The retrospective cohort included the top 10% of all the ED users during 2015/2016 (termed HSUs) and a random sample of controls (4 per each HSU) from the bottom 90% per province. Rates of transitions among ED, hospitalization, community settings, and in-hospital mortality were adjusted for sociodemographic and ED variables in a multistate statistical model.
Results
There were 2,684,924 patients and 579,230 (21.6%) were HSUs. Patient characteristics associated with shorter community to ED transition times for HSUs included Alberta residence (ratio of hazard ratio RHR = 1.11, 95% confidence interval CI 1.11,1.12), living in areas in the lower income quintile (RHR = 1.06, 95%CI 1.06,1.06), and Ontario residents without a primary health care provider (RHR = 1.13, 95%CI 1.13,1.14). Once at the ED, characteristics associated with shorter ED to hospital transition times for HSUs included higher acuity (e.g., RHR = 1.70, 95% CI 1.61, 1.81 for emergent), and for many diagnoses including chest pain (RHR = 1.71, 95%CI 1.65,1.76) and gastrointestinal (RHR = 1.66, 95%CI 1.62,1.71). Once admitted to hospital, HSUs did not necessarily have longer stays except for conditions such as chest pain (RHR = 0.90, 95% CI 0.86, 0.95). HSUs had shorter times to death in the ED if they presented for cancer (RHR = 2.51), congestive heart failure (RHR = 1.93), myocardial infarction (RHR = 1.53), and stroke (RHR = 1.84), and shorter times to death in-hospital if they presented with cancer (RHR = 1.29).
Conclusions
Differences between HSUs and controls in predictors of transitions among care settings were identified. Co-morbidities and limitations in access to primary care are associated with more rapid transitions from community to ED and hospital among HSUs. Interventions targeting these challenges may better serve patients across health systems..
Trial registration
Not applicable.
Understanding the distribution of an event duration time is essential in many studies. The exact time to the event is often unavailable, and thus so is the full event duration. By linking relevant ...longitudinal measures to the event duration, we propose to estimate the duration distribution via the first-hitting-time model (e.g. Lee and Whitmore in Stat Sci 21(4):501–513, 2006). The longitudinal measures are assumed to follow a Wiener process with random drift. We apply a variant of the MCEM algorithm to compute likelihood-based estimators of the parameters in the longitudinal process model. This allows us to adapt the well-known empirical distribution function to estimate the duration distribution in the presence of missing time origin. Estimators with smooth realizations can then be obtained by conventional smoothing techniques. We establish the consistency and weak convergence of the proposed distribution estimator and present its variance estimation. We use a collection of wildland fire records from Alberta, Canada to motivate and illustrate the proposed approach. The finite-sample performance of the proposed estimator is examined by simulation. Viewing the available data as interval-censored times, we show that the proposed estimator can be more efficient than the well-established Turnbull estimator, an alternative that is often applied in such situations.
This paper describes and compares patient flow characteristics of adult high system users (HSUs) and control groups in Alberta and Ontario emergency departments (EDs), Canada.
Annual cohorts of HSUs ...were created by identifying patients who made up the top 10% of ED users (by count of ED presentations) in the National Ambulatory Care Reporting System during 2011-2016. Random samples of patients not in the HSU groups were selected as controls. Presentation (e.g., acuity) and ED times (e.g., time to physician initial assessment PIA, length of stay) data were extracted and described. The length of stay for 2015/2016 data was decomposed into stages and Cox models compared time between stages.
There were 20,343,230 and 18,222,969 ED presentations made by 7,032,655 and 1,923,462 individuals in the control and HSU groups, respectively. The Ontario groups had higher acuity than the Alberta groups: about 20% in the Ontario groups were from the emergent level whereas Alberta had 11-15%. Time to PIA was similar across provinces and groups (medians of 60 min to 67 min). Lengths of stay were longest for Ontario HSUs (median = 3 h) and shortest for Alberta HSUs (median = 2.2 h). HSUs had shorter times to PIA (hazard ratio HR = 1.03; 95% confidence interval CI 1.02,1.03), longer times from PIA to decision (HR = 0.84; 95%CI 0.84,0.84), and longer times from decision to leaving the ED (HR = 0.91; 95%CI 0.91,0.91).
Ontario HSUs had higher acuity and longer ED lengths of stay than the other groups. In both provinces, HSU had shorter times to PIA and longer times after assessment.
Administrative databases offer vast amounts of data that provide opportunities for cost-effective insights. They simultaneously pose significant challenges to statistical analysis such as the ...redaction of data because of privacy policies and the provision of data that may not be at the level of detail required. For example, ages in years rather than birthdates available at event dates can pose challenges to the analysis of recurrent event data.
Hu and Rosychuk provided a strategy for estimating age-varying effects in a marginal regression analysis of recurrent event times when birthdates are all missing. They analyzed emergency department (ED) visits made by children and youth and privacy rules prevented all birthdates to be released, and justified their approach via a simulation and asymptotic study. With recent changes in data access rules, we requested a new extract of data for April 2010 to March 2017 that includes patient birthdates. This allows us to compare the estimates using the Hu and Rosychuk (HR) approach for coarsened ages with estimates under the true, known ages to further examine their approach numerically. The performance of the HR approach under five scenarios is considered: uniform distribution for missing birthdates, uniform distribution for missing birthdates with supplementary data on age, empirical distribution for missing birthdates, smaller sample size, and an additional year of data.
Data from 33,299 subjects provided 58,166 ED visits. About 67% of subjects had one ED visit and less than 9% of subjects made over three visits during the study period. Most visits (84.0%) were made by teenagers between 13 and 17 years old. The uniform distribution and the HR modeling approach capture the main trends over age of the estimates when compared to the known birthdates. Boys had higher ED visit frequencies than girls in the younger ages whereas girls had higher ED visit frequencies than boys for the older ages. Including additional age data based on age at end of fiscal year did not sufficiently narrow the widths of potential birthdate intervals to influence estimates. The empirical distribution of the known birthdates was close to a uniform distribution and therefore, use of the empirical distribution did not change the estimates provided by assuming a uniform distribution for the missing birthdates. The HR approach performed well for a smaller sample size, although estimates were less smooth when there were very few ED visits at some younger ages. When an additional year of data is added, the estimates become better at these younger ages.
Overall the Hu and Rosychuk approach for coarsened ages performed well and captured the key features of the relationships between ED visit frequency and covariates.