Disease activity trajectories in juvenile dermatomyositis from childhood to adulthood.

OBJECTIVES: To assess whether there are identifiable subgroups of disease activity trajectory in a population of juvenile dermatomyositis (JDM) patients-followed throughout childhood and into adulthood-and determine factors that predict those trajectory groupings. METHODS: This is a retrospective, longitudinal inception cohort of patients with idiopathic inflammatory myopathies, largely JDM. We sought to identify baseline factors that predict membership into different groups (latent classes) of disease activity trajectory. RESULTS: A total of 172 patients (64% females), with median age at diagnosis of 7.7 years, were analyzed. We studied 4,725 visits (1,471 patient-years). We identified 3 latent classes of longitudinal disease activity, as measured by the modified disease activity score (DASm), with distinct class trajectories predicted by DASm at baseline, and by the changes of DASm from either baseline to 3 months or baseline to 6 months (early response to therapy). In the analysis in which DASm at baseline and the changes of DASm from baseline to 6 months are included as predictors, Class 1 (10%) has persistently high disease activity, Class 2 (34%) is characterized by moderate disease activity, and Class 3 (56%) is characterized by individuals with a high early disease activity but an apparently good response to treatment and long-term low disease activity. CONCLUSION: High early disease activity, and treatment resistance in the first few months, predict a more chronic longitudinal course of JDM.

Evaluating the Impact of Ex Vivo Lung Perfusion on Organ Transplantation: A Retrospective Cohort Study.

BACKGROUND: Ex vivo lung perfusion (EVLP) sustains and allows advanced assessment of potentially useable donor lungs before transplantation, potentially relieving resource constraints. OBJECTIVE: We sought to characterize the effect of EVLP on organ utilization and patient outcomes. METHODS: We performed a retrospective, before-after cohort study using linked institutional data sources of adults wait-listed for lung transplant and donor organs transplanted in Ontario, Canada between 2005 and 2019. We regressed the annual number of transplants against year, EVLP use, and organ characteristics. Time-to-transplant, waitlist mortality, primary graft dysfunction, tracheostomy insertion, in-hospital mortality, and chronic lung allograft dysfunction were evaluated using propensity score-weighted regression. RESULTS: EVLP availability ( P =0.01 for interaction) and EVLP use ( P <0.001 for interaction) were both associated with steeper increases in transplantation than expected by historical trends. EVLP was associated with more donation after circulatory death and extended-criteria donors transplanted, while the numbers of standard-criteria donors remained relatively stable. Significantly faster time-to-transplant was observed after EVLP was available (hazard ratio=1.64 [1.41-1.92]; P <0.001). Fewer patients died on the waitlist after EVLP was available, but no difference in the hazard of waitlist mortality was observed (HR=1.19 [0.81-1.74]; P =0.176). We observed no difference in the likelihood of chronic lung allograft dysfunction before versus after EVLP was available. CONCLUSIONS: We observed a significant increase in organ transplantation since EVLP was introduced into practice, predominantly from increased acceptance of donation after circulatory death and extended-criteria lungs. Our findings suggest that EVLP-associated increases in organ availability meaningfully alleviated some barriers to transplant.

Genetics of longitudinal kidney function in children and adults with systemic lupus erythematosus.

OBJECTIVES: Genome-wide association studies (GWAS) have identified loci associated with estimated glomerular filtration rate (eGFR). Few LN risk loci have been identified to date. We tested the association of SLE and eGFR polygenic risk scores (PRS) with repeated eGFR measures from children and adults with SLE. METHODS: Patients from two tertiary care lupus clinics that met ≥4 ACR and/or SLICC criteria for SLE were genotyped on the Illumina MEGA or Omni1-Quad arrays. PRSs were calculated for SLE and eGFR, using published weighted GWA-significant alleles. eGFR was calculated using the CKD-EPI and Schwartz equations. We tested the effect of eGFR- and SLE-PRSs on eGFR mean and variance, adjusting for age at diagnosis, sex, ancestry, follow-up time, and clinical event flags. RESULTS: We included 1158 SLE patients (37% biopsy-confirmed LN) with 36 733 eGFR measures over a median of 7.6 years (IQR: 3.9-15.3). LN was associated with lower within-person mean eGFR [LN: 93.8 (s.d. 26.4) vs non-LN: 101.6 (s.d. 17.7) mL/min per 1.73 m2; P < 0.0001] and higher variance [LN median: 157.0 (IQR: 89.5, 268.9) vs non-LN median: 84.9 (IQR: 46.9, 138.2) (mL/min per 1.73 m2)2; P < 0.0001]. Increasing SLE-PRSs were associated with lower mean eGFR and greater variance, while increasing eGFR-PRS was associated with increased eGFR mean and variance. CONCLUSION: We observed significant associations between SLE and eGFR PRSs and repeated eGFR measurements, in a large cohort of children and adults with SLE. Longitudinal eGFR may serve as a powerful alternative outcome to LN categories for discovery of LN risk loci.

Causal inference with longitudinal data subject to irregular assessment times.

Data collected in the context of usual care present a rich source of longitudinal data for research, but often require analyses that simultaneously enable causal inferences from observational data while handling irregular and informative assessment times. An inverse-weighting approach to this was recently proposed, and handles the case where the assessment times are at random (ie, conditionally independent of the outcome process given the observed history). In this paper, we extend the inverse-weighting approach to handle a special case of assessment not at random, where assessment and outcome processes are conditionally independent given past observed covariates and random effects. We use multiple outputation to accomplish the same purpose as inverse-weighting, and apply it to the Liang semi-parametric joint model. Moreover, we develop an alternative joint model that does not require covariates for the outcome model to be known at times where there is no assessment of the outcome. We examine the performance of these methods through simulation and illustrate them through a study of the causal effect of wheezing on time spent playing outdoors among children aged 2-9 years and enrolled in the TargetKids! study.

Randomized Trials With Repeatedly Measured Outcomes: Handling Irregular and Potentially Informative Assessment Times.

Randomized trials are often designed to collect outcomes at fixed points in time after randomization. In practice, the number and timing of outcome assessments can vary among participants (i.e., irregular assessment). In fact, the timing of assessments may be associated with the outcome of interest (i.e., informative assessment). For example, in a trial evaluating the effectiveness of treatments for major depressive disorder, not only did the timings of outcome assessments vary among participants but symptom scores were associated with assessment frequency. This type of informative observation requires appropriate statistical analysis. Although analytic methods have been developed, they are rarely used. In this article, we review the literature on irregular assessments with a view toward developing recommendations for analyzing trials with irregular and potentially informative assessment times. We show how the choice of analytic approach hinges on assumptions about the relationship between the assessment and outcome processes. We argue that irregular assessment should be treated with the same care as missing data, and we propose that trialists adopt strategies to minimize the extent of irregularity; describe the extent of irregularity in assessment times; make their assumptions about the relationships between assessment times and outcomes explicit; adopt analytic techniques that are appropriate to their assumptions; and assess the sensitivity of trial results to their assumptions.

Long-Term Sequelae and Health-Related Quality of Life Associated With Lyme Disease: A Systematic Review.

Lyme disease (LD) is the most commonly reported vector-borne disease, but its clinical consequences remain uncertain. We conducted a systematic review of the long-term sequelae and health-related quality of life (HRQoL) associated with LD in North America and Europe. We performed searches in 6 electronic databases up to December 2018 following Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, including observational studies reporting long-term sequelae, HRQoL, and prognostic factors. We included 46 studies, published between 1994 and 2019. Based on 21 studies reporting attributable outcomes, higher proportions of sequelae reported from exposed patients were: neck pain, myalgia, arthralgia, paresthesia, sleep disorder, poor appetite, and concentration difficulties. Patients with PTLDS reported impaired HRQoL compared to the general US population. Included studies were highly heterogeneous in terms of study design, settings, patient characteristics, and quality. Patients with LD are more likely to report nonspecific long-term sequelae, especially those experiencing persistent symptoms posttreatment. Opportunities exist for prospective longitudinal studies to better understand LD outcomes.

Summarizing the extent of visit irregularity in longitudinal data.

BACKGROUND: Observational longitudinal data often feature irregular, informative visit times. We propose descriptive measures to quantify the extent of irregularity to select an appropriate analytic outcome approach. METHODS: We divided the study period into bins and calculated the mean proportions of individuals with 0, 1, and > 1 visits per bin. Perfect repeated measures features everyone with 1 visit per bin. Missingness leads to individuals with 0 visits per bin while irregularity leads to individuals with > 1 visit per bin. We applied these methods to: 1) the TARGet Kids! study, which invites participation at ages 2, 4, 6, 9, 12, 15, 18, 24 months, and 2) the childhood-onset Systemic Lupus Erythematosus (cSLE) study which recommended at least 1 visit every 6 months. RESULTS: The mean proportions of 0 and > 1 visits per bin were above 0.67 and below 0.03 respectively in the TARGet Kids! study, suggesting repeated measures with missingness. For the cSLE study, bin widths of 6 months yielded mean proportions of 1 and > 1 visits per bin of 0.39, suggesting irregular visits. CONCLUSIONS: Our methods describe the extent of irregularity and help distinguish between protocol-driven visits and irregular visits. This is an important step in choosing an analytic strategy for the outcome.

Multiple outputation for the analysis of longitudinal data subject to irregular observation.

Observational cohort studies often feature longitudinal data subject to irregular observation. Moreover, the timings of observations may be associated with the underlying disease process and must thus be accounted for when analysing the data. This paper suggests that multiple outputation, which consists of repeatedly discarding excess observations, may be a helpful way of approaching the problem. Multiple outputation was designed for clustered data where observations within a cluster are exchangeable; an adaptation for longitudinal data subject to irregular observation is proposed. We show how multiple outputation can be used to expand the range of models that can be fitted to irregular longitudinal data.

Knowledge translation in biostatistics: a survey of current practices, preferences, and barriers to the dissemination and uptake of new statistical methods.

BACKGROUND: The use of standard statistical methods in the medical literature has been studied extensively; however, the adoption of new methods has received less attention. We sought to understand (i) whether there is a perception that new methods are underused, (ii) what the barriers to use of new methods are, (iii) what dissemination activities are used, and (iv) user preferences for learning about new methods. METHODS: We conducted a cross-sectional survey of members of the Statistical Society of Canada (SSC) and of principal investigators (knowledge-users) funded by the Canadian Institutes of Health Research (CIHR). RESULTS: There were 157 CIHR respondents (14% response rate), and 39 respondents were statisticians from the Statistical Society of Canada. Seventy percent of CIHR respondents and 82% of statisticians felt that new developments were under-used. Barriers to use of new methods included lack of access to the necessary expertise (selected by over 90% of respondents), lack of suitable software (selected by 81% of statisticians), and lack of time to implement new methods (selected by 78% of statisticians). Greater access to statistical colleagues with an interest in collaboration and availability of software to implement new methods were the top-rated preferences among knowledge-users. CONCLUSIONS: There was a clear perception among all respondents that new statistical methods are underused. Encouraging statistical methodologists to develop a knowledge translation plan for improved dissemination and uptake, placing greater value on the role of the statistical collaborator in research, and providing software alongside new methods may improve the use of newly developed statistical methods.

Creating a Multiply Imputed Value Set for the EQ-5D-5L in Canada: State-Level Misspecification Terms Are Needed to Characterize Parameter Uncertainty Correctly.

BACKGROUND: Parameter uncertainty in EQ-5D-5L value sets often exceeds the instrument's minimum important difference, yet this is routinely ignored. Multiple imputation (MI) accounts for parameter uncertainty in the value set; however, no valuation study has implemented this methodology. Our objective was to create a Canadian MI value set for the EQ-5D-5L, thus enabling users to account for parameter uncertainty in the value set. METHODS: Using the Canadian EQ-5D-5L valuation study (N = 1,073), we first refit the original model followed by models with state-level misspecification. Models were compared based on the adequacy of 95% credible interval (CrI) coverage for out-of-sample predictions. Using the best-fitting model, we took 100 draws from the posterior distribution to create 100 imputed value sets. We examined how much the standard error of the estimated mean health utilities increased after accounting for parameter uncertainty in the value set by using the MI and original value sets to score 2 data sets: 1) a sample of 1,208 individuals from the Canadian general public and 2) a sample of 401 women with breast cancer. RESULTS: The selected model with state-level misspecification outperformed the original model (95% CrI coverage: 94.2% v. 11.6%). We observed wider standard errors for the estimated mean utilities on using the MI value set for both the Canadian general public (MI: 0.0091; original: 0.0035) and patients with breast cancer (MI: 0.0169; original: 0.0066). DISCUSSION AND CONCLUSIONS: We provide 1) the first MI value sets for the EQ-5D-5L and 2) code to construct MI value sets while accounting for state-level model misspecification. Our study suggests that ignoring parameter uncertainty in value sets leads to falsely narrow SEs. HIGHLIGHTS: Value sets for health state utility instruments are estimated subject to parameter uncertainty; this parameter uncertainty may exceed the minimum important difference of the instrument, yet it is not fully captured using current methods.This study creates the first multiply imputed value set for a multiattribute utility instrument, the EQ-5D-5L, to fully capture this parameter uncertainty.We apply the multiply imputed value set to 2 data sets from 1) the Canadian general public and 2) women with invasive breast cancer.Scoring the EQ-5D-5L using a multiply imputed value set led to wider standard error estimates, suggesting that the current practice of ignoring parameter uncertainty in the value set leads to falsely low standard errors.Our work will be of interest to methodologists and developers of the EQ-5D-5L and users of the EQ-5D-5L, such as health economists, researchers, and policy makers.

Doubly robust estimation, optimally truncated inverse-intensity weighting and increment-based methods for the analysis of irregularly observed longitudinal data.

Longitudinal data arising from routine follow-up of patients will often have irregular measurement times. Existing methods for analysis include joint modelling of the outcome and measurement processes, and inverse-intensity weighting (IIW). This work extends previously proposed analysis of increments to the case of irregular follow-up, yielding a model for the increments that can be used as a stand-alone method. Furthermore, we propose two ways of combining the increments and IIW estimators. First, we use the increment model to select the truncation point for the inverse-intensity weights that minimises the mean squared error of the IIW estimator. Second, we use the increment model to augment the usual IIW estimating equations to form a doubly robust estimator. We evaluate the methods through simulation and apply these to a recent study of juvenile dermatomyositis.

Determining the impact of ex-vivo lung perfusion on hospital costs for lung transplantation: A retrospective cohort study.

INTRODUCTION: Ex-vivo lung perfusion (EVLP) has improved organ utilization for lung transplantation, but it is not yet known whether the benefits of this technology offset its additional costs. We compared the institutional costs of lung transplantation before vs after EVLP was available to identify predictors of costs and determine the health-economic impact of EVLP. METHODS: We performed a retrospective, before-after, propensity-score weighted cohort study of patients wait-listed for lung transplant at University Health Network (UHN) in Ontario, Canada, between January 2005 and December 2019 using institutional administrative data. We compared costs, in 2019 Canadian Dollars ($), between patients referred for transplant before EVLP was available (Pre-EVLP) to after (Modern EVLP). Cumulative costs were estimated using a novel application of multistate survival models. Predictors of costs were identified using weighted log-gamma generalized linear regression. RESULTS: A total of 1,199 patients met inclusion criteria (352 Pre-EVLP; 847 Modern EVLP). Mean total costs for the transplant hospitalization were $111,878 ($94,123-$130,767) in the Pre-EVLP era and $110,969 ($87,714-$136,000) in the Modern EVLP era. Cumulative five-year costs since referral were $278,777 ($82,575-$298,135) in the Pre-EVLP era and $293,680 ($252,832-$317,599) in the Modern EVLP era. We observed faster progression to transplantation when EVLP was available. EVLP availability was not a predictor of waitlist (cost ratio [CR] 1.04 [0.81-1.37]; p = 0.354) or transplant costs (CR 1.02 [0.80-1.29]; p = 0.425) but was associated with lower costs during posttransplant years 1&2 (CR 0.75 [0.58-1.06]; p = 0.05) and posttransplant years 3+ (CR 0.43 [0.26-0.74]; p = 0.001). CONCLUSIONS: At our center, EVLP availability was associated with faster progression to transplantation at no significant marginal cost.

Quantifying the extent of visit irregularity in longitudinal data.

The timings of visits in observational longitudinal data may depend on the study outcome, and this can result in bias if ignored. Assessing the extent of visit irregularity is important because it can help determine whether visits can be treated as repeated measures or as irregular data. We propose plotting the mean proportions of individuals with 0 visits per bin against the mean proportions of individuals with >1 visit per bin as bin width is varied and using the area under the curve (AUC) to assess the extent of irregularity. The AUC is a single score which can be used to quantify the extent of irregularity and assess how closely visits resemble repeated measures. Simulation results confirm that the AUC increases with increasing irregularity while being invariant to sample size and the number of scheduled measurement occasions. A demonstration of the AUC was performed on the TARGet Kids! study which enrolls healthy children aged 0-5 years with the aim of investigating the relationship between early life exposures and later health problems. The quality of statistical analyses can be improved by using the AUC as a guide to select the appropriate analytic outcome approach and minimize the potential for biased results.

Efficacy of intravenous Ig therapy in juvenile dermatomyositis.

UNLABELLED: Intravenous immunoglobulin (IVIg) is an adjunctive therapy for juvenile dermatomyositis (JDM) patients with poor response to first-line therapy (corticosteroid resistant; SR) or who are corticosteroid dependent (SD). Patients requiring IVIg are generally expected to have poorer outcomes, leading to confounding by indication in observational studies. Few studies have evaluated IVIg efficacy in JDM. OBJECTIVES: Compared with similar matched controls, to determine if JDM IVIg recipients achieve quiescence sooner and have less disease activity. For SD patients, to determine if IVIg recipients exhibit less disease activity than IVIg-naive patients. METHODS: A retrospective inception cohort of 78 JDM patients was studied. Kaplan-Meier survival determined time to quiescence. Marginal structural modelling was used to account for confounding by indication by incorporating inverse probability of treatment weights to handle patients' unequal likelihood of receiving IVIg. RESULTS: While similar demographically, the 30 IVIg patients demonstrated weaker muscle strength and more had photosensitivity at baseline than the 48 controls. As expected, IVIg patients achieved quiescence later than controls in unadjusted analysis. However, although IVIg patients started with greater disease activity, after accounting for confounding as best possible, they maintained similar or lower disease activity than controls from 30 days to 4 years post-diagnosis. This improvement was most marked in SR patients. Among SD patients, IVIg recipients maintained lower disease activity than IVIg-naive patients. CONCLUSION: This study, involving the largest JDM cohort receiving IVIg to date, applied bias-reduction methods and demonstrated IVIg efficacy in controlling JDM disease activity, particularly for SR patients.

An informed reference prior for between-study heterogeneity in meta-analyses of binary outcomes.

It is well known that when a Bayesian meta-analysis includes a small number of studies, inference can be sensitive to the choice of prior for the between-study variance. Choosing a vague prior does not solve the problem, as inferences can be substantially different depending on the degree of vagueness. Moreover, because the data provide little information on between-study heterogeneity, posterior inferences for the between-study variance based on vague priors will tend to be unrealistic. It is thus preferable to adopt a reasonable, informed prior for the between-study variance. However, relatively little is known about what constitutes a realistic distribution. On the basis of data from the Cochrane Database of Systematic Reviews, this paper describes the distribution of between-study variance in published meta-analyses, and proposes some realistic, informed priors for use in meta-analyses of binary outcomes. It is hoped that these priors will improve the calibration of inferences from Bayesian meta-analyses.

Clustered longitudinal data subject to irregular observation.

Data collected longitudinally as part of usual health care is becoming increasingly available for research, and is often available across several centres. Because the frequency of follow-up is typically determined by the patient's health, the timing of measurements may be related to the outcome of interest. Failure to account for the informative nature of the observation process can result in biased inferences. While methods for accounting for the association between observation frequency and outcome are available, they do not currently account for clustering within centres. We formulate a semi-parametric joint model to include random effects for centres as well as subjects. We also show how inverse-intensity weighted GEEs can be adapted to account for clustering, comparing stratification, frailty models, and covariate adjustment to account for clustering in the observation process. The finite-sample performance of the proposed methods is evaluated through simulation and the methods illustrated using a study of the relationship between outdoor play and air quality in children aged 2-9 living in the Greater Toronto Area.

Estimating the population health burden of Lyme disease in Ontario, Canada: a microsimulation modelling approach.

BACKGROUND: If untreated, Lyme disease can lead to long-term sequelae and post-treatment Lyme disease syndrome (PTLDS), resulting in reduced health-related quality of life. The objective of this study was to develop a microsimulation model to estimate the population-level health burden of Lyme disease in Ontario, Canada. METHODS: We developed a Lyme disease history model using microsimulation, simulating 100 000 people (mean age 37.6 yr, 51% female) from 2017 in Ontario over a lifetime risk of infection and time horizon. We extracted the sensitivity and specificity of the 2-tier testing recommended by the Canadian Public Health Laboratory Network, probabilities and health state utility values from the published literature and health administrative data. Our reported outcomes from our stochastic analysis include diagnosed cases of Lyme disease (stratified by stage), undiagnosed infections, sequelae, individuals with PTLDS and quality-adjusted life-years (QALYs) lost. RESULTS: Our model estimated 333 (95% confidence interval [CI] 329-337) infections over the lifetime of 100 000 simulated people (mean age 37.6 yr, 51% female), with 92% (95% CI 91%-93%) of infections diagnosed. Of those 308 people with Lyme Disease diagnoses, 67 (95% CI 65-69) developed sequelae (e.g., arthritic, cardiac, neurologic sequelae), and 34 (95% CI 33-35) developed PTLDS. Lyme disease resulted in a loss of 84.5 QALYs (95% CI 82.9-86.2) over the lifetime of the simulated cohort. Sensitivity and scenario analysis showed that increasing incidence rates of Lyme disease, potential underreporting, duration of PTLDS and quality of life (health state utility) associated with PTLDS had the greatest impact on health burden. INTERPRETATION: Lyme disease contributes considerable health burden in terms of QALYs lost. Our analysis provides evidence to understand the disease burden and lays the foundation to assess the cost-effectiveness of pharmaceutical and nonpharmaceutical interventions.

The analysis of treatment effects for recurring episodic conditions.

Many chronic disease processes feature acute episodic conditions which warrant therapeutic intervention to alleviate symptoms or reduce the risk of further complications. Examples of such disease processes arise in fields such as neurology, where migraineurs experience recurrent attacks of migraine, and respirology, where patients suffering from asthma, cystic fibrosis, or chronic obstructive pulmonary disease may experience recurrent exacerbations. In randomized clinical trials, patients suffering from diseases of this sort are often randomized to one of several treatments and followed over a fixed period of time, during which any episodes are treated with the assigned treatment. When the outcome of interest is a response to treatment at each episode, the data have a similar structure to longitudinal data from studies with prescheduled follow-up assessments, and it is commonplace for analyses to be based on the corresponding methodology. However, this approach ignores the fact that the timing of episodes, and hence the number observed in any given period, is stochastic. In this tutorial we demonstrate the biases that result from naive analyses, discuss analyses that account for the complete stochastic nature, and use a recent migraine trial for illustration. We conclude with some considerations for the design of randomized trials where the unit of analysis is the episode rather than the patient.

Use of a disease-specific instrument in economic evaluations: mapping WOMAC onto the EQ-5D utility index.

OBJECTIVE: To map the Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC) onto the EuroQol 5 Dimension (EQ-5D) utility index in patients with knee osteoarthritis (OA). METHODS: A consecutive sample of patients (n=258) diagnosed with knee OA completed both the WOMAC and the EQ-5D. Regression models with the ordinary least squares (OLS) or the censored least absolute deviations as the estimator were used to establish the mapping function. The WOMAC was represented as explanatory variables in four ways: 1) total score; 2) domain scores (i.e., pain, stiffness, and physical function); 3) domain scores plus pair-wise interaction terms to account for possible nonlinearities; and 4) individual item scores. Goodness-of-fit criteria included the mean absolute error (the primary criterion) and the root mean squared error, and were obtained using an iterative random sampling procedure. Prediction precision was evaluated at individual patient level and at the group level. RESULTS: The model using the OLS estimator and the WOMAC domain scores as explanatory variables had the best fit and was chosen as the preferred mapping model. The prediction error at the individual level exceeded the maximal tolerance value (i.e., the minimally important difference of the EQ-5D) in about 16% of the patients. At the group level, the width of the 95% confidence interval of prediction errors varied from 0.0176 at a sample size of 400 to 0.0359 at a sample size of 100. CONCLUSIONS: EQ-5D scores can be predicted using WOMAC domain scores with an acceptable precision at both individual and group levels in patients with mild to moderate knee OA.

Analysis of health utility data when some subjects attain the upper bound of 1: are Tobit and CLAD models appropriate?

BACKGROUND: Health utility data often show an apparent truncation effect, where a proportion of individuals achieve the upper bound of 1. The Tobit model and censored least absolute deviations (CLAD) have both been used as analytic solutions to this apparent truncation effect. These models assume that the observed utilities are censored at 1, and hence that the true utility can be greater than 1.We aimed to examine whether the Tobit and CLAD models yielded acceptable results when this censoring assumption was not appropriate. METHODS: Using health utility (captured through EQ5D) data from a diabetes study, we conducted a simulation to compare the performance of the Tobit, CLAD, ordinary least squares (OLS), two-part and latent class estimators in terms of their bias and estimated confidence intervals. We also illustrate the performance of semiparametric and nonparametric bootstrap methods. RESULTS: When the true utility was conceptually bounded above at 1, the Tobit and CLAD estimators were both biased. The OLS estimator was asymptotically unbiased and, while the model-based and semiparametric bootstrap confidence intervals were too narrow, confidence intervals based on the robust standard errors or the nonparametric bootstrap were acceptable for sample sizes of 100 and larger. Two-part and latent class models also yielded unbiased estimates. CONCLUSIONS: When the intention of the analysis is to inform an economic evaluation, and the utilities should be bounded above at 1, CLAD, and Tobit methods were biased. OLS coupled with robust standard errors or the nonparametric bootstrap is recommended as a simple and valid approach.