Search

Previous research linking opioid prescribing to adverse drug events has failed to properly account for the time-varying nature of opioid exposure. This study aimed to explore how the risk of opioid-related emergency department visits, readmissions, or deaths (composite outcome) varies with opioid dose and duration, comparing different novel modeling techniques. A prospective cohort of 1,511 hospitalized patients discharged from 2 McGill-affiliated hospitals in Montreal, 2014–2016, was followed from the first postdischarge opioid dispensation until 1 year after discharge. Marginal structural Cox proportional hazards models and their flexible extensions were used to explore the association between time-varying opioid use and the composite outcome. Weighted cumulative exposure models assessed cumulative effects of past use and explored how its impact depends on the recency of exposure. The patient mean age was 69.6 (standard deviation = 14.9) years; 57.7% were male. In marginal structural model analyses, current opioid use was associated with a 71% increase in the hazard of opioid-related adverse events (adjusted hazard ratio = 1.71, 95% confidence interval: 1.21, 2.43). The weighted cumulative exposure results suggested that the risk cumulates over the previous 50 days of opioid consumption. Flexible modeling techniques helped assess how the risk of opioid-related adverse events may be associated with time-varying opioid exposures while accounting for nonlinear relationships and the recency of past use. [ABSTRACT FROM AUTHOR]

Background: Long-term opioid use is an increasingly important problem related to the ongoing opioid epidemic. The purpose of this study was to identify patient, hospitalization and system-level determinants of long term opioid therapy (LTOT) among patients recently discharged from hospital. Design: To be eligible for this study, patient needed to have filled at least one opioid prescription three-months post-discharge. We retrieved data from the provincial health insurance agency to measure medical service and prescription drug use in the year prior to and after hospitalization. A multivariable Cox Proportional Hazards model was utilized to determine factors associated with time to the first LTOT occurrence, defined as time-varying cumulative opioid duration of ≥ 60 days. Results: Overall, 22.4% of the 1,551 study patients were classified as LTOT, who had a mean age of 66.3 years (SD = 14.3). Having no drug copay status (adjusted hazard ratio (aHR) 1.91, 95% CI: 1.40–2.60), being a LTOT user before the index hospitalization (aHR 6.05, 95% CI: 4.22–8.68) or having history of benzodiazepine use (aHR 1.43, 95% CI: 1.12–1.83) were all associated with an increased likelihood of LTOT. Cardiothoracic surgical patients had a 40% lower LTOT risk (aHR 0.55, 95% CI: 0.31–0.96) as compared to medical patients. Initial opioid dispensation of > 90 milligram morphine equivalents (MME) was also associated with higher likelihood of LTOT (aHR 2.08, 95% CI: 1.17–3.69). Conclusions and relevance: Several patient-level characteristics associated with an increased risk of ≥ 60 days of cumulative opioid use. The results could be used to help identify patients who are at high-risk of continuing opioids beyond guideline recommendations and inform policies to curb excessive opioid prescribing. [ABSTRACT FROM AUTHOR]

To assess the association between childhood body fatness and epithelial ovarian cancer (EOC), and whether this association differs by type of EOC. Using data from a population-based case-control study (497 cases and 902 controls) in Montreal, Canada conducted 2011–2016, we examined the association between childhood body fatness and EOC, overall and separately for invasive vs. borderline EOCs. A figure rating scale was used to measure body fatness at ages 5 and 10. Multivariable logistic regression was used to estimate adjusted odds ratios (aORs) and 95% confidence intervals (95% CI). Quantitative bias analyses were conducted to assess the impact of exposure misclassification and non-participation. The aOR (95% CI) of overall EOC for high vs. low body fatness was 1.07 (0.85–1.34) at age 5 and 1.28 (0.98–1.68) at age 10. The associations were stronger for invasive EOC, specifically the endometrioid histological type. For borderline cancers, the aORs were below the null value with wide confidence intervals. Bias analyses did not reveal a strong influence of non-participation. Non-differential exposure misclassification may have biased aORs towards the null for invasive cancers but did not appear to have an appreciable influence on the aORs for borderline cancers. Childhood body fatness may be a risk factor for invasive EOC in later adult life. Our study highlights the potential importance of examining early life factors for a comprehensive understanding of EOC development. • Few studies have examined the link between childhood body fatness and epithelial ovarian cancer (EOC) risk. • High childhood body fatness is positively associated with invasive EOC. • Quantitative bias analyses suggested minimal distortion of the estimates by selection bias or information bias. • The findings support that early-life exposures may influence later-life risk of EOC. [ABSTRACT FROM AUTHOR]

Background: In recent years, age at liver transplantation (LT) has markedly increased. In the context of organ shortage, we investigated the impact of recipient age on post‐transplantation mortality. Methods: All adult patients who received a first LT between 2007 and 2017 were included in this cross‐sectional study. Recipients' characteristics at the time of listing, donor and surgery data, post‐operative complications and follow‐up of vital status were retrieved from the national transplantation database. The impact of age on 5‐year overall mortality post‐LT was estimated using a flexible multivariable parametric model which was also used to estimate the association between age and 10‐year net survival, accounting for expected age‐ and sex‐related mortality. Results: Among the 7610 patients, 21.4% were aged 60–65 years, and 15.7% over 65. With increasing age, comorbidities increased but severity of liver disease decreased. Older recipient age was associated with decreased observed survival at 5 years after LT (p <.001), with a significant effect particularly during the first 2 years. The linear increase in the risk of death associated with age does not allow any definition of an age's threshold for LT (p =.832). Other covariates associated with an increased risk of 5‐year death were dialysis and mechanical ventilation at transplant, transfusion during LT, hepatocellular carcinoma and donor age. Ten‐year flexible net survival analysis confirmed these results. Conclusion: Although there was a selection process for older recipients, increasing age at LT was associated with an increased risk of death, particularly in the first years after LT. [ABSTRACT FROM AUTHOR]

Aims: We describe an innovative research protocol to: (a) examine patient‐level longitudinal associations between nurse staffing practices and the risk of adverse events in acute care hospitals and; (b) determine possible thresholds for safe nurse staffing. Design: A dynamic cohort of adult medical, surgical and intensive care unit patients admitted to 16 hospitals in Quebec (Canada) between January 2015–December 2019. Methods: Patients in the cohort will be followed from admission until 30‐day postdischarge to assess exposure to selected nurse staffing practices in relation to the subsequent occurrence of adverse events. Five staffing practices will be measured for each shift of an hospitalization episode, using electronic payroll data, with the following time‐varying indicators: (a) nursing worked hours per patient; (b) skill mix; (c) overtime use; (d) education mix and; and (e) experience. Four high‐impact adverse events, presumably associated with nurse staffing practices, will be measured from electronic health record data retrieved at the participating sites: (a) failure‐to‐rescue; (b) in‐hospital falls; (c) hospital‐acquired pneumonia and; and (d) venous thromboembolism. To examine the associations between the selected nurse staffing exposures and the risk of each adverse event, separate multivariable Cox proportional hazards frailty regression models will be fitted, while adjusting for patient, nursing unit and hospital characteristics, and for clustering. To assess for possible staffing thresholds, flexible non‐linear spline functions will be fitted. Funding for the study began in October 2019 and research ethics/institutional approval was granted in February 2020. Discussion: To our knowledge, this study is the first multisite patient‐level longitudinal investigation of the associations between common nurse staffing practices and the risk of adverse events. It is hoped that our results will assist hospital managers in making the most effective use of the scarce nursing resources and in identifying staffing practices that minimize the occurrence of adverse events. [ABSTRACT FROM AUTHOR]

Background: As cancer treatment, biotherapies can be as effective as chemotherapy while reducing the risk of secondary effects, so that they can be taken over longer periods than conventional chemotherapy. Thus, some trials aimed at assessing the benefit of maintaining biotherapies during chemotherapy-free intervals (CFI). For example, the recent PRODIGE9 trial assessed the effect of maintaining bevacizumab during CFI in metastatic colorectal cancer (mCRC) patients. However, its analysis was hindered by a small difference of exposure to the treatment between the randomized groups and by a large proportion of early drop outs, leading to a potentially unbalanced distribution of confounding factors among the trial completers. To address these limitations, we re-analyzed the PRODIGE9 data to assess the effects of different exposure metrics on all-cause mortality of patients with mCRC using methods originally developed for observational studies.Methods: To account for the actual patterns of drug use by individual patients and for possible cumulative effects, we used five alternative time-varying exposure metrics: (i) cumulative dose, (ii) quantiles of the cumulative dose, (iii) standardized cumulative dose, (iv) Theoretical Blood Concentration (TBC), and (v) Weighted Cumulative Exposure (WCE). The last two metrics account for the timing of drug use. Treatment effects were estimated using adjusted Hazard Ratio from multivariable Cox proportional hazards models.Results: After excluding 112 patients who died during the induction period, we analyzed data on 382 patients, among whom 320 (83.8%) died. All time-varying exposures improved substantially the model's fit to data, relative to using only the time-invariant randomization group. All exposures indicated a protective effect for higher cumulative bevacizumab doses. The best-fitting WCE and TBC models accounted for both the cumulative effects and the different impact of doses taken at different times.Conclusions: All time-varying analyses, regardless of the exposure metric used, consistently suggested protective effects of higher cumulative bevacizumab doses. However, the results may partly reflect the presence of a confusion bias. Complementing the main ITT analysis of maintenance trials with an analysis of potential cumulative effects of treatment actually taken can provide new insights, but the results must be interpreted with caution because they do not benefit from the randomization.Trial Registration: clinicaltrials.gov, NCT00952029 . Registered 8 August 2009. [ABSTRACT FROM AUTHOR]

Introduction: Catheter ablation (CA) has been increasingly used to treat atrial fibrillation (AF) in patients with heart failure (HF), however, its safety at the population‐level has not yet been evaluated. To assess the safety of CA in AF‐HF patients, the frequency and potential risk factors for adverse events (AEs) within 30 days post‐CA were determined. Methods: A population‐based cohort of AF‐HF patients who underwent CA in Quebec, Canada (2000‐2017) was constructed using administrative databases. Major AEs included all‐cause mortality, cerebrovascular accident (CVA), pericardial effusion requiring drainage (PERD), vascular AEs, hemorrhage/hematoma, and pulmonary embolism. Univariate logistic regression models were employed to assess potential risk factors for major AEs. Results: Of 700 AF‐HF patients who underwent CA (median age 64.5 years [interquartile range, IQR, 56.2‐71.0], 22.0% female, and median CHA2DS2‐Vasc 3 [IQR, 2‐4]), 14 (2.0%) patients developed 16 major AEs within 30 days of CA. Hemorrhage/hematoma was the most frequent major AE (four patients; 0.6%) followed by all‐cause mortality, CVA/TIA, PERD, and vascular AEs (three patients each; 0.4%). Coronary artery disease (odds ratio [OR], 3.9 [95% confidence interval, CI, 1.2‐12.3]) and age ≥65 years (OR, 3.1 [95% CI, 1.1‐9.8]) were identified predictors for the composite outcome of major AEs. More than half of the patients (57.2%) underwent a second CA within a median of 0.8 (IQR, 0.2‐2.2) years from the date of first CA. Conclusion: CA performed in the AF‐HF population portends a relatively low incidence of major AEs. A larger study is required to determine whether certain patient factors are independently associated with a higher risk of post‐CA AEs. [ABSTRACT FROM AUTHOR]

Large databases used in observational studies of drug safety often lack information on important confounders. The resulting unmeasured confounding bias may be avoided by using additional confounder information, frequently available in smaller clinical "validation samples". Yet, no existing method that uses such validation samples is able to deal with unmeasured time-varying variables acting as both confounders and possible mediators of the treatment effect. We propose and compare alternative methods which control for confounders measured only in a validation sample within marginal structural Cox models. Each method corrects the time-varying inverse probability of treatment weights for all subject-by-time observations using either regression calibration of the propensity score, or multiple imputation of unmeasured confounders. Two proposed methods rely on martingale residuals from a Cox model that includes only confounders fully measured in the large database, to correct inverse probability of treatment weight for imputed values of unmeasured confounders. Simulation demonstrates that martingale residual-based methods systematically reduce confounding bias over naïve methods, with multiple imputation including the martingale residual yielding, on average, the best overall accuracy. We apply martingale residual-based imputation to re-assess the potential risk of drug-induced hypoglycemia in diabetic patients, where an important laboratory test is repeatedly measured only in a small sub-cohort. [ABSTRACT FROM AUTHOR]

An accurate assessment of drug safety or effectiveness in pharmaco-epidemiology requires defining an etiologically correct time-varying exposure model, which specifies how previous drug use affects the hazard of the event of interest. An additional challenge is to account for the multitude of mutually exclusive events that may be associated with the use of a given drug. To simultaneously address both challenges, we develop, and validate in simulations, a new approach that combines flexible modeling of the cumulative effects of time-varying exposures with competing risks methodology to separate the effects of the same drug exposure on different outcomes. To account for the dosage, duration and timing of past exposures, we rely on a spline-based weighted cumulative exposure modeling. We also propose likelihood ratio tests to test if the cumulative effects of past exposure on the hazards of the competing events are the same or different. Simulation results indicate that the estimated event-specific weight functions are reasonably accurate, and that the proposed tests have acceptable type I error rate and power. In real-life application, the proposed method indicated that recent use of antihypertensive drugs may reduce the risk of stroke but has no effect on the hazard of coronary heart disease events. [ABSTRACT FROM AUTHOR]

Aims: To evaluate the association between metformin use and heart failure (HF) exacerbation in people with type 2 diabetes (T2D) and pre‐existing HF using alternative exposure models. Materials and methods: We analysed data for patients with T2D and incident HF from a national US insurance claims database. We compared the results of several multivariable Cox models where time‐varying use of metformin was modelled as: (1) current use; (2) total duration of past use; and (3) use within the past 30 days or 10 days. The outcome was defined as time to HF‐related hospitalization. We then re‐analysed the data using flexible weighted cumulative exposure (WCE) models. Results: A total of 7620 patients with diabetes and incident HF were analysed. The mean (SD) patient age was 54 (8) years, and 58% (n = 4440) were men. In all, 3799 individuals (50%) were exposed to metformin, and 837 HF hospitalizations (11%) occurred (mean follow‐up 1.7 years). Results of conventional models suggested potential acute benefits in reducing HF exacerbation with metformin use in the past 10 days (adjusted hazard ratio [aHR] 0.76, 95% confidence interval [CI] 0.60‐0.97), while WCE models, which provided a better fit for the data, suggested lack of a systematic effect (aHR 0.91, 95% CI 0.69‐1.20). Conclusions: Our results suggest that cumulative metformin exposure does not decrease the risk of HF‐related exacerbation. Use of other anti‐hyperglycaemic agents with proven efficacy in patients with HF should also be considered as treatment options in this population. [ABSTRACT FROM AUTHOR]

Objective: Trials of new systemic lupus erythematosus (SLE) treatments are hampered by the lack of effective outcome measures. To address this, we developed a novel Lupus Multivariable Outcome Score (LuMOS) and assessed its performance using data from 2 randomized controlled trials of belimumab in patients with SLE. Methods: The LuMOS formula was developed by analyzing raw data from 2 pivotal trials, the Study of Belimumab in Subjects with SLE 52‐week (BLISS‐52) and 76‐week (BLISS‐76) trials, which are the basis for approval of belimumab. Using the BLISS‐76 trial data as the learning data set, we carried out multivariable logistic regression analyses to optimize discrimination of outcomes between patients treated with 10 mg/kg belimumab and patients receiving placebo over the first 52 weeks of follow‐up. In addition, the performance of LuMOS was assessed using an independent validation data set from the BLISS‐52 trial. Results: The LuMOS model incorporated the following response criteria: a ≥4‐point reduction on the Safety of Estrogens in Lupus Erythematosus National Assessment version of the SLE Disease Activity Index, an increase in C4 levels, a decrease in anti–double‐stranded DNA titers, and changes in the British Isles Lupus Assessment Group scores for organ system manifestations (no worsening in renal components, and improvements in mucocutaneous components). A decrease in the prednisone dose and increase in C3 levels had very minor impacts on the total LuMOS score. In all analyses of the BLISS‐76 and BLISS‐52 trial data sets, the mean LuMOS scores were significantly higher (P < 0.0001) in patients treated with 1 mg or 10 mg belimumab compared to placebo. In contrast to the performance of the SLE Responder Index 4 (SRI‐4), the LuMOS revealed significant differences between the active treatment group (1 mg belimumab in the BLISS‐76 cohort) and placebo group. The effect sizes were significantly much higher with the LuMOS than with the SRI‐4. Conclusion: The evidenced‐based LuMOS outcome scoring system, developed with data from the BLISS‐76 trial of belimumab in patients with SLE and validated with data from the BLISS‐52 trial, exhibits a superior capacity to discriminate responders from nonresponders when compared to the SRI‐4. Use of the LuMOS may improve the efficiency and power of analyses in future lupus trials. [ABSTRACT FROM AUTHOR]

Introduction: Prospective pharmacovigilance aims to rapidly detect safety concerns related to medical products. The exposure model selected for pharmacovigilance impacts the timeliness of signal detection. However, in most real-life pharmacovigilance studies, little is known about which model correctly represents the association and there is no evidence to guide the selection of an exposure model. Different exposure models reflect different aspects of exposure history, and their relevance varies across studies. Therefore, one potential solution is to apply several alternative exposure models simultaneously, with each model assuming a different exposure-risk association, and then combine the model results.Methods: We simulated alternative clinically plausible associations between time-varying drug exposure and the hazard of an adverse event. Prospective surveillance was conducted on the simulated data by estimating parametric and semi-parametric exposure-risk models at multiple times during follow-up. For each model separately, and using combined evidence from different subsets of models, we compared the time to signal detection.Results: Timely detection across the simulated associations was obtained by fitting a set of pharmacovigilance models. This set included alternative parametric models that assumed different exposure-risk associations and flexible models that made no assumptions regarding the form/shape of the association. Times to detection generated using a simple combination of evidence from multiple models were comparable to those observed under the ideal, but unrealistic, scenario where pharmacovigilance relied on the single 'true' model used for data generation.Conclusions: Simulation results indicate that, if the true model is not known, an association can be detected in a more timely manner by first fitting a carefully selected set of exposure-risk models and then generating a signal as soon as any of the models considered yields a test statistic value below a predetermined testing threshold. [ABSTRACT FROM AUTHOR]

Unmeasured confounding remains an important problem in observational studies, including pharmacoepidemiological studies of large administrative databases. Several recently developed methods utilize smaller validation samples, with information on additional confounders, to control for confounders unmeasured in the main, larger database. However, up-to-date applications of these methods to survival analyses seem to be limited to propensity score calibration, which relies on a strong surrogacy assumption. We propose a new method, specifically designed for time-to-event analyses, which uses martingale residuals, in addition to measured covariates, to enhance imputation of the unmeasured confounders in the main database. The method is applicable for analyses with both time-invariant data and time-varying exposure/confounders. In simulations, our method consistently eliminated bias because of unmeasured confounding, regardless of surrogacy violation and other relevant design parameters, and almost always yielded lower mean squared errors than other methods applicable for survival analyses, outperforming propensity score calibration in several scenarios. We apply the method to a real-life pharmacoepidemiological database study of the association between glucocorticoid therapy and risk of type II diabetes mellitus in patients with rheumatoid arthritis, with additional potential confounders available in an external validation sample. Compared with conventional analyses, which adjust only for confounders measured in the main database, our estimates suggest a considerably weaker association. Copyright © 2016 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Unmeasured confounding is a major threat to the validity of pharmacoepidemiological studies of medication safety and effectiveness. We propose a new method for detecting and reducing the impact of unobserved confounding in large observational database studies. The method uses assumptions similar to the prescribing preference-based instrumental variable (IV) approach. Our method relies on the new 'missing cause' principle, according to which the impact of unmeasured confounding by (contra-)indication may be detected by assessing discrepancies between the following: (i) treatment actually received by individual patients and (ii) treatment that they would be expected to receive based on the observed data. Specifically, we use the treatment-by-discrepancy interaction to test for the presence of unmeasured confounding and correct the treatment effect estimate for the resulting bias. Under standard IV assumptions, we first proved that unmeasured confounding induces a spurious treatment-by-discrepancy interaction in risk difference models for binary outcomes and then simulated large pharmacoepidemiological studies with unmeasured confounding. In simulations, our estimates had four to six times smaller bias than conventional treatment effect estimates, adjusted only for measured confounders, and much smaller variance inflation than unbiased but very unstable IV estimates, resulting in uniformly lowest root mean square errors. The much lower variance of our estimates, relative to IV estimates, was also observed in an application comparing gastrointestinal safety of two classes of anti-inflammatory drugs. In conclusion, our missing cause-based method may complement other methods and enhance accuracy of analyses of large pharmacoepidemiological studies. [ABSTRACT FROM AUTHOR]

Prognostic studies often estimate survival curves for patients with different covariate vectors, but the validity of their results depends largely on the accuracy of the estimated covariate effects. To avoid conventional proportional hazards and linearity assumptions, flexible extensions of Cox's proportional hazards model incorporate non-linear (NL) and/or time-dependent (TD) covariate effects. However, their impact on survival curves estimation is unclear. Our primary goal is to develop and validate a flexible method for estimating individual patients' survival curves, conditional on multiple predictors with possibly NL and/or TD effects. We first obtain maximum partial likelihood estimates of NL and TD effects and use backward elimination to select statistically significant effects into a final multivariable model. We then plug the selected NL and TD estimates in the full likelihood function and estimate the baseline hazard function and the resulting survival curves, conditional on individual covariate vectors. The TD and NL functions and the log hazard are modeled with unpenalized regression B-splines. In simulations, our flexible survival curve estimates were unbiased and had much lower mean square errors than the conventional estimates. In real-life analyses of mortality after a septic shock, our model improved significantly the deviance (likelihood ratio test = 84.8, df = 20, p < 0.0001) and changed substantially the predicted survival for several subjects. [ABSTRACT FROM AUTHOR]

Accurate identification of factors associated with progression of colorectal cancer remains a challenge. In particular, it is unclear which statistical methods are most suitable to separate the effects of putative prognostic factors on cancer progression vs cancer-specific and other cause mortality. To address these challenges, we analyzed 10 year follow-up data for patients who underwent curative surgery for colorectal cancer in 1985-2000. Separate analyses were performed in two French cancer registries. Results of three multivariable models were compared: Cox model with recurrence as a time-dependent variable, and two multi-state models, which separated prognostic factor effects on recurrence vs death, with or without recurrence. Conventional multi-state model analyzed all-cause mortality while new relative survival multi-state model focused on cancer-specific mortality. Among the 2517 and 2677 patients in the two registries, about 50% died without a recurrence, and 28% had a recurrence, of whom almost 90% died. In both multi-state models men had significantly increased risk of cancer recurrence in both registries (HR = 0.79; 95% CI: 0.68-0.92 and HR = 0.83; 95% CI: 0.71-0.96). However, the two multistate models identified different prognostic factors for mortality without recurrence. In contrast to the conventional model, in the relative survival analyses gender had no independent association with cancer-specific mortality whereas patients diagnosed with stage III cancer had significantly higher risks in both registries (HR = 1.67; 95% CI: 1.27-2.22 and HR = 2.38; 95% CI: 1.29-3.27). In conclusion, relative survival multi-state model revealed that different factors may be associated with cancer recurrence vs cancer-specific mortality either after or without a recurrence. [ABSTRACT FROM AUTHOR]

Objectives: To illustrate the advantages of updating time-varying measures of disease activity and flexible modeling in prognostic clinical studies using the example of the association between the frequency of past relapses and occurrence of ambulation-related disability in multiple sclerosis (MS). Study Design and Setting: Longitudinal population-based study of 288 patients from Burgundy, France, diagnosed with relapsing-remitting MS in 1990-2003. The end point was a nonreversible moderate MS disability (European Database for Multiple Sclerosis score ≥3.0 derived from Extended Disability Status Scale). Alternative time-varying measures of attacks frequency included (1) conventional number of early MS attacks in the first 2 years after diagnosis; and two new measures, continuously updated during the follow-up; (2) cumulative number of past attacks; and (3) number of recent attacks, during the past 2 years. Multivariate analyses used Cox proportional hazards model and its flexible generalization, which accounted for time-dependent changes in the hazard ratios (HRs) for different attack frequency measures. Results: HRs for all measures decreased significantly with increasing follow-up time. The proposed updated number of recent attacks improved model's fit to data, relative to alternative measures of attack frequency, and was associated with a statistically significantly increased hazard of developing ambulation-related MS disability in the next 2 years during the entire follow-up period. Conclusion: Updated measures of recent disease activity, such as frequency of recent attacks and modeling of their time-dependent effects, may substantially improve prognosis of clinical outcomes, such as development of MS disability. [ABSTRACT FROM AUTHOR]

Background: Preference for fatty foods is a risk factor for obesity. It is a complex behaviour that involves the brain reward system and is regulated by genetic and environmental factors, such as the opioid receptor mu-1 gene (OPRM1) and prenatal exposure to maternal cigarette smoking (PEMCS). We examined whether OPRM1 and PEMCS interact in influencing fat intake and whether exposure-associated epigenetic modifications of OPRM1 may mediate this gene–environment interaction. Methods: We studied adolescents from a French Canadian genetic founder population, half of whom were exposed prenatally to maternal cigarette smoking. Fat intake was assessed with a 24-hour food recall in the form of a structured interview conducted by a trained nutritionist. The OPRM1 variant rs2281617 was genotyped for the whole sample with the Illumina Human610-Quad and HumanOmniExpress BeadChips. Methylation of blood DNA was assessed at 21 CpGs across OPRM1 in a subset of the sample using the Illumina HumanMethylation450 BeadChip. Results: We included 956 adolescents in our study. In the whole sample, OPRM1 (T carrier in rs2281617) was associated with lower fat intake (-1.6%, p = 0.017), and PEMCS was associated with higher fat intake (+1.6%, p = 0.005). OPRM1 and PEMCS interacted with each other (p = 0.003); the “protective” (fat intake–lowering) allele of OPRM1 was associated with lower fat intake in nonexposed (-3.2%, p < 0.001) but not in exposed individuals (+0.8%, p = 0.42). Further, PEMCS was associated with lower DNA methylation across multiple CpGs across OPRM1 in exposed versus nonexposed individuals (p = 0.031). Limitations: A limitation of our study was its cross-sectional design. Conclusion: Our study suggests that PEMCS may interact with OPRM1 in increasing fat preference. Silencing of the protective OPRM1 allele in exposed adolescents might be related to epigenetic modification of this gene. [ABSTRACT FROM AUTHOR]

The validity and practical utility of observational medical research depends critically on good study design, excellent data quality, appropriate statistical methods and accurate interpretation of results. Statistical methodology has seen substantial development in recent times. Unfortunately, many of these methodological developments are ignored in practice. Consequently, design and analysis of observational studies often exhibit serious weaknesses. The lack of guidance on vital practical issues discourages many applied researchers from using more sophisticated and possibly more appropriate methods when analyzing observational studies. Furthermore, many analyses are conducted by researchers with a relatively weak statistical background and limited experience in using statistical methodology and software. Consequently, even 'standard' analyses reported in the medical literature are often flawed, casting doubt on their results and conclusions. An efficient way to help researchers to keep up with recent methodological developments is to develop guidance documents that are spread to the research community at large. These observations led to the initiation of the strengthening analytical thinking for observational studies (STRATOS) initiative, a large collaboration of experts in many different areas of biostatistical research. The objective of STRATOS is to provide accessible and accurate guidance in the design and analysis of observational studies. The guidance is intended for applied statisticians and other data analysts with varying levels of statistical education, experience and interests. In this article, we introduce the STRATOS initiative and its main aims, present the need for guidance documents and outline the planned approach and progress so far. We encourage other biostatisticians to become involved. © 2014 The Authors. Statistics in Medicine published by John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Cox's proportional hazards (PH) model assumes constant-over-time covariate effects. Furthermore, most applications assume linear effects of continuous covariates on the logarithm of the hazard. Yet, many prognostic factors have time-dependent (TD) and/or nonlinear (NL) effects, that is, violate these conventional assumptions. Detection of such complex effects could affect prognosis and clinical decisions. However, assessing the effects of each of the multiple, often correlated, covariates in flexible multivariable analyses is challenging. In simulations, we investigated the impact of the approach used to build the flexible multivariable model on inference about the TD and NL covariate effects. Results demonstrate that the conclusions regarding the statistical significance of the TD/NL effects depend heavily on the strategy used to decide which effects of the other covariates should be adjusted for. Both a failure to adjust for true TD and NL effects of relevant covariates and inclusion of spurious effects of covariates that conform to the PH and linearity assumptions increase the risk of incorrect conclusions regarding other covariates. In this context, iterative backward elimination of nonsignificant NL and TD effects from the multivariable model, which initially includes all these effects, may help discriminate between true and spurious effects. The practical importance of these issues was illustrated in an example that reassessed the predictive ability of selected biomarkers for survival in advanced non-small-cell lung cancer. In conclusion, a careful model-building strategy and flexible modeling of multivariable survival data can yield new insights about predictors' roles and improve the validity of analyses. Copyright © 2014 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

The association between antiretroviral treatment and cardiovascular disease (CVD) risk in HIV-positive persons has been the subject of much debate since the Data collection on Adverse events of Anti-HIV Drugs (D:A:D) study reported that recent use of two antiretroviral drugs, abacavir (ABC) and didanosine (DDI), was associated with increased risk. We focus on the potential impact of DDI use, as this drug has not been as studied intensively as ABC. We propose a flexible marginal structural Cox model with weighted cumulative exposure modeling (Cox WCE MSM) to address two key challenges encountered when using observational longitudinal data to assess the adverse effects of medication: (1) the need to model the cumulative effect of a time-dependent treatment and (2) the need to control for time-dependent confounders that also act as mediators of the effect of past treatment. Simulations confirm that the Cox WCE MSM yields accurate estimates of the causal treatment effect given complex exposure effects and time-dependent confounding. We then use the new flexible Cox WCE MSM to assess the association between DDI use and CVD risk in the Swiss HIV Cohort Study. In contrast to the nonsignificant results obtained with conventional parametric Cox MSMs, our new Cox WCE MSM identifies a significant short-term risk increase due to DDI use in the previous year. Supplementary materials for this article are available online. [ABSTRACT FROM AUTHOR]

Abstract: Objectives: Preterm birth (PTB) before 37 weeks can occur over a wide range of gestational ages, but few studies have assessed if associations between risk factors and PTB vary over the duration of gestation. We sought to evaluate if associations between two major risk factors (maternal education and age) and PTB depend on gestational age at delivery. Study design: We estimated hazard ratios of PTB for education and age in a time-to-event analysis using a retrospective cohort of 223,756 live singleton births from the province of Québec, Canada for the years 2001–2005. Differences in hazards of maternal education and age with PTB were assessed over gestational age in a Cox proportional hazards model using linear and nonlinear time interaction terms, adjusting for maternal characteristics. Results: Associations of PTB with lower (vs. higher) education and older (vs. younger) age strengthened progressively at earlier gestational ages, such that the risk of PTB for maternal education and age was not constant over the course of gestation. Conclusions: Associations of PTB with risk factors such as maternal low education and older age may be stronger early in gestation. Models that capture the time-dependent nature of PTB may be useful when the goal is to assess associations at low gestational ages, and to avoid masked or biased associations early in gestation. [Copyright &y& Elsevier]

Visceral fat (VF) promotes the development of metabolic syndrome (MetS), which emerges as early as in adolescence. The clustering of MetS components suggests shared etiologies, but these are largely unknown and may vary between males and females. Here, we investigated the latent structure of pre-clinical MetS in a community-based sample of 286 male and 312 female adolescents, assessing their abdominal adiposity (VF) directly with magnetic resonance imaging. Principal component analysis of the five MetS-defining variables (VF, blood pressure [BP], fasting serum triglycerides, HDL-cholesterol and glucose) identified two independent components in both males and females. The first component was sex-similar; it explained >30% of variance and was loaded by all but BP variables. The second component explained >20% of variance; it was loaded by BP similarly in both sexes but additional loading by metabolic variables was sex-specific. This sex-specificity was not detected in analyses that used waist circumference instead of VF. In adolescence, MetS-defining variables cluster into at least two sub-syndromes: (1) sex-similar metabolic abnormalities of obesity-induced insulin resistance and (2) sex-specific metabolic abnormalities associated with BP elevation. These results suggest that the etiology of MetS may involve more than one pathway and that some of the pathways may differ between males and females. Further, the sex-specific metabolic abnormalities associated with BP elevation suggest the need for sex-specific prevention and treatment strategies of MetS. [ABSTRACT FROM AUTHOR]

Abstract: Purpose: Increasing numbers of women achieve extremely high education, but the association with preterm birth (PTB) is poorly understood, especially over the life course. We sought to determine how very high educational attainment is associated with PTB, and to assess differences by maternal age and nativity. Methods: Data included singleton live births to mothers aged ≥20 years in metropolitan areas of Québec, Canada, from 1995 to 2005 (n = 537,525). Hazard ratios of PTB (<37 gestational weeks) were estimated over the continuous range of education (0–30 years) according to maternal age (20–24, 25–29, 30–34, ≥35 years) and nativity in a flexible survival model. Results: The relationship between education and PTB was not linear, but suggested that extremely high education was not as protective against PTB as slightly lower education. Education thresholds that offered maximum protection increased with maternal age, and were lower for Canadian-born (17–21 years of education) than foreign-born (22–25 years of education) mothers. Conclusions: Extremely high education did not confer more protection against PTB than slightly lower education, and associations varied over the life course. The threshold number of years of education most protective against PTB: (1) increased with maternal age, especially for Canadian-born mothers, and (2) was higher for foreign-born mothers. [Copyright &y& Elsevier]

Objectives. To determine the effect of glucocorticoids (GCs) on acute myocardial infarction (MI) risk in patients with RA.Methods. Using administrative health data, we conducted a population-based cohort study of 8384 incident RA cases (1997–2006). Primary exposure was incident GC use. MI events were ascertained using hospitalization and vital statistics data. We used Cox proportional-hazards models and modelled GC use as four alternative time-dependent variables (current use, current dose, cumulative dose and cumulative duration), adjusting for demographics, comorbidities, cardiovascular drug use, propensity score and RA characteristics. Sensitivity analyses explored potential effects of unmeasured confounding.Results. Within 50 238 person-years in 8384 RA cases, we identified 298 incident MI events. Multivariable models showed that current GC use was associated with 68% increased risk of MI [Hazard ratio (HR) = 1.68, 95% CI 1.14, 2.47]. Similarly, separate multivariable models showed that current daily dose (HR = 1.14, 95% CI 1.05, 1.24 per each 5 mg/day increase), cumulative duration of use (HR = 1.14, 95% CI 1.00, 1.29 per year of GC use) and total cumulative dose (HR = 1.06, 95% CI 1.02, 1.10 per gram accumulated in the past) were also associated with increased risk of MI. Furthermore, in the same multivariable model, current dose and cumulative use were independently associated with an increased risk of MI (10% per additional year on GCs and 13% per 5 mg/day increase).Conclusion. GCs are associated with an increased risk of MI in RA. Our results suggest a dual effect of GCs on MI risk, an immediate effect mediated through current dosage and a long-term effect of cumulative exposure. [ABSTRACT FROM PUBLISHER]

The article investigates whether rhythm control versus rate control treatment strategies for atrial fibrillation (AF) have similar effectiveness when applied to a general population of patients with AF with longer follow-up. Results reveal little difference in mortality within four years of treatment initiation between patients with AF initiating rhythm control therapy versus those initiating rate control therapy. Rhythm control therapy, however, appears to be superior in the long-term.

Pharmacoepidemiology investigates associations between time-varying medication use/dose and risk of adverse events. Applied research typically relies on a priori chosen simple conventional models, such as current dose or any use in the past 3 months. However, different models imply different risk predictions, and only one model can be etiologically correct in any specific applications. We first formally defined several candidate models mapping the time vector of past drug doses ( X ( t), t = 1, ... , u) into the value of a time-varying exposure metric M( u) at current time u. In addition to conventional one-parameter models, we considered two-parameter models accounting for recent dose increase or withdrawal and a flexible spline-based weighted cumulative exposure (WCE) model that defines M( u) as the weighted sum of past doses. In simulations, we generated event times assuming one of the models was correct and then analyzed the data with all candidate models. We demonstrated that the minimum AIC criterion is able to identify the correct model as the best-fitting model or one of the equivalent (within 4 AIC points of the minimum) models in a vast majority of simulated samples, especially with 500 or more events. We also showed how relying on an incorrect a priori chosen model may largely reduce the power to test for an association. Finally, we demonstrated how the flexible WCE estimates may help with model diagnostics even if the correct model is not WCE. We illustrated the practical advantages of AIC-based a posteriori model selection and WCE modeling in a real-life pharmacoepidemiology example. Copyright © 2011 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Prognostic studies often have to deal with two important challenges: (i) separating effects of predictions on different 'competing' events and (ii) uncertainty about cause of death. Multistate Markov models permit multivariable analyses of competing risks of, for example, mortality versus disease recurrence. On the other hand, relative survival methods help estimate disease-specific mortality risks even in the absence of data on causes of death. In this paper, we propose a new Markov relative survival (MRS) model that attempts to combine these two methodologies. Our MRS model extends the existing multistate Markov piecewise constant intensities model to relative survival modeling. The intensity of transitions leading to death in the MRS model is modeled as the sum of an estimable excess hazard of mortality from the disease of interest and an ' offset' defined as the expected hazard of all-cause 'natural' mortality obtained from relevant life-tables. We evaluate the new MRS model through simulations, with a design based on registry-based prognostic studies of colon cancer. Simulation results show almost unbiased estimates of prognostic factor effects for the MRS model. We also applied the new MRS model to reassess the role of prognostic factors for mortality in a study of colorectal cancer. The MRS model considerably reduces the bias observed with the conventional Markov model that does not permit accounting for unknown causes of death, especially if the 'true' effects of a prognostic factor on the two types of mortality differ substantially. Copyright © 2011 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Abstract: Objective: The instrumental variable (IV) method can remove bias because of unobserved confounding, but it is unclear to what extent the choice of the IV may affect the results. We compared the estimates obtained with different provider-based IVs in a real-life observational comparative drug effectiveness study. Study Design and Setting: We assessed the effectiveness of rhythm vs. rate control treatment in reducing 5-years mortality in a population-based cohort of patients with atrial fibrillation. We compared the IV treatment effect estimates obtained from two-stage least square regression models using nine alternative provider-based IVs defined at either hospital or physician level. Results: All nine IVs reduced the covariate imbalance between the treatment groups. Yet, there were large variations in both the point estimates and the width of the confidence intervals obtained with alternative IVs. Relative to the physician-based IVs, the hospital-based IVs were stronger, had smaller variance, and produced less extreme point estimates. Conclusions: The IV estimates of treatment effect may vary considerably depending on the IV definition. Choosing the strongest IV could reduce the variance of the IV estimates. [Copyright &y& Elsevier]

Instrumental variable (IV) methods based on the physician's prescribing preference may remove bias due to unobserved confounding in pharmacoepidemiologic studies. However, IV estimates, originally defined as the treatment prescribed for a single previous patient of a given physician, show important variance inflation. The authors proposed and validated in simulations a new method to reduce the variance of IV estimates even when physicians’ preferences change over time. First, a potential “change-time,” after which the physician's preference has changed, was estimated for each physician. Next, all patients of a given physician were divided into 2 homogeneous subsets: those treated before the change-time versus those treated after the change-time. The new IV was defined as the proportion of all previous patients in a corresponding homogeneous subset who were prescribed a specific drug. In simulations, all alternative IV estimators avoided strong bias of the conventional estimates. The change-time method reduced the standard deviation of the estimates by approximately 30% relative to the original previous patient-based IV. In an empirical example, the proposed IV correlated better with the actual treatment and yielded smaller standard errors than alternative IV estimators. Therefore, the new method improved the overall accuracy of IV estimates in studies with unobserved confounding and time-varying prescribing preferences. [ABSTRACT FROM PUBLISHER]

To develop and validate the accuracy of a predictive model to identify adult asthmatics from administrative health care databases. An existing electronic medical record project in Montreal, Quebec. One thousand four hundred and thirty-one patients with confirmed asthma status were identified from primary care physician's electronic medical record. Therapeutic indication of asthma in an electronic prescription and/or confirmed asthma from an automated problem list were used as the gold standard. Five groups of asthma-specific markers were identified from administrative health care databases to estimate the probability of the presence of asthma. Cross-validation evaluated the diagnostic ability of each predictive model using 50 percent of sample. The best performance in discriminating between the patients with asthma and those without it included indicators from medical service and prescription claims databases. The best-fitting algorithm had a sensitivity of 70 percent, a specificity of 94 percent, and positive predictive value of 65 percent. The prescriptions claims-specific algorithm demonstrated a nearly equal performance to the model with medical services and prescription claims combined. Our algorithm using asthma-specific markers from administrative claims databases provided moderate sensitivity and high specificity. [ABSTRACT FROM AUTHOR]

Background: Education is inversely associated with cardiovascular disease incidence in developed countries. Blood pressure may be an explanatory biological mechanism. However few studies have investigated educational gradients in longitudinal blood pressure trajectories, particularly over substantial proportions of the life course. Study objectives were to determine whether low education was associated with increased blood pressure from multiple longitudinal assessments over 30 years. Furthermore, we aimed to separate antecedent effects of education, and other related factors, that might have caused baseline differences in blood pressure, from potential long-term effects of education on post-baseline blood pressure changes. Methods: The study examined 3890 participants of the Framingham Offspring Study (mean age 36.7 years, 52.0% females at baseline) from 1971 through 2001 at up to 7 separate examinations using multivariable mixed linear models. Results: Mixed linear models demonstrated that mean systolic blood pressure (SBP) over 30 years was higher for participants with ≤12 vs. ≥17 years education after adjusting for age (3.26 mmHg, 95% CI: 1.46, 5.05 in females, 2.26 mmHg, 95% CI: 0.87, 3.66 in males). Further adjustment for conventional covariates (antihypertensive medication, smoking, body mass index and alcohol) reduced differences in females and males (2.86, 95% CI: 1.13, 4.59, and 1.25, 95% CI: -0.16, 2.66 mmHg, respectively). Additional analyses adjusted for baseline SBP, to evaluate if there may be educational contributions to post-baseline SBP. In analyses adjusted for age and baseline SBP, females with ≤12 years education had 2.69 (95% CI: 1.09, 4.30) mmHg higher SBP over follow-up compared with ≥17 years education. Further adjustment for aforementioned covariates slightly reduced effect strength (2.53 mmHg, 95% CI: 0.93, 4.14). Associations were weaker in males, where those with ≤12 years education had 1.20 (95% CI: -0.07, 2.46) mmHg higher SBP over follow-up compared to males with ≥17 years of education, after adjustment for age and baseline blood pressure; effects were substantially reduced after adjusting for aforementioned covariates (0.34 mmHg, 95% CI: -0.90, 1.68). Sex-by-education interaction was marginally significant (p = 0.046). Conclusion: Education was inversely associated with higher systolic blood pressure throughout a 30-year life course span, and associations may be stronger in females than males. [ABSTRACT FROM AUTHOR]

Prognostic studies often involve modeling competing risks, where an individual can experience only one of alternative events, and the goal is to estimate hazard functions and covariate effects associated with each event type. Lunn and McNeil proposed data manipulation that permits extending the Cox's proportional hazards model to estimate covariate effects on the hazard of each competing events. However, the hazard functions for competing events are assumed to remain proportional over the entire follow-up period, implying the same shape of all event-specific hazards, and covariate effects are restricted to also remain constant over time, even if such assumptions are often questionable. To avoid such limitations, we propose a flexible model to (i) obtain distinct estimates of the baseline hazard functions for each event type, and (ii) allow estimating time-dependent covariate effects in a parsimonious model. Our flexible competing risks regression model uses smooth cubic regression splines to model the time-dependent changes in (i) the ratio of event-specific baseline hazards, and (ii) the covariate effects. In simulations, we evaluate the performance of the proposed estimators and likelihood ratio tests, under different assumptions. We apply the proposed flexible model in a prognostic study of colorectal cancer mortality, with two competing events: 'death from colorectal cancer' and 'death from other causes'. Copyright © 2010 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

The article discusses a study which investigated the influence of a physician's medical management and communication ability on persistence with antihypertensive treatment. The study involved 13,205 hypertensive patients who received antihypertensive medication prescribed by a cohort of 645 physicians who entered practice in Quebec between 1993 and 2007. The benefits of improved clinical decision-making and data collection skills were noted by the researchers.

We propose two bootstrap-based methods to correct the standard errors (SEs) from Cox's model for within-cluster correlation of right-censored event times. The cluster-bootstrap method resamples, with replacement, only the clusters, whereas the two-step bootstrap method resamples (i) the clusters, and (ii) individuals within each selected cluster, with replacement. In simulations, we evaluate both methods and compare them with the existing robust variance estimator and the shared gamma frailty model, which are available in statistical software packages. We simulate clustered event time data, with latent cluster-level random effects, which are ignored in the conventional Cox's model. For cluster-level covariates, both proposed bootstrap methods yield accurate SEs, and type I error rates, and acceptable coverage rates, regardless of the true random effects distribution, and avoid serious variance under-estimation by conventional Cox-based standard errors. However, the two-step bootstrap method over-estimates the variance for individual-level covariates. We also apply the proposed bootstrap methods to obtain confidence bands around flexible estimates of time-dependent effects in a real-life analysis of cluster event times. Copyright © 2010 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Many epidemiological studies assess the effects of time-dependent exposures, where both the exposure status and its intensity vary over time. One example that attracts public attention concerns pharmacoepidemiological studies of the adverse effects of medications. The analysis of such studies poses challenges for modeling the impact of complex time-dependent drug exposure, especially given the uncertainty about the way effects cumulate over time and about the etiological relevance of doses taken in different time periods. We present a flexible method for modeling cumulative effects of time-varying exposures, weighted by recency, represented by time-dependent covariates in the Cox proportional hazards model. The function that assigns weights to doses taken in the past is estimated using cubic regression splines. We validated the method in simulations and applied it to re-assess the association between exposure to a psychotropic drug and fall-related injuries in the elderly. Copyright © 2009 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Often in generalized additive models (GAMs), the amount of smoothing is chosen to optimize some data-dependent criterion (e.g., AIC). Through simulations, we estimated the type I error of the GAM-based tests of (i) no association and (ii) linearity while using this approach. Overall, type I error rates were much higher than nominal levels. We proposed new critical values, which resulted in correct Overall type I error. We also compared power to detect nonlinearities of GAMs with several df-selection strategies with conventional parametric models. To illustrate our approach, we re-analyzed the association between body mass index and coronary heart disease mortality. [ABSTRACT FROM AUTHOR]

Abstract: Objectives: To reassess the effects of prognostic factors on mortality in gastric cancers, and to illustrate the advantages of flexible modeling. Study Design and Setting: A prospective population-based cohort of persons diagnosed with gastric cancers in 1976 to 1995 in Burgundy, France, was followed for 5 years since diagnosis. Multivariable survival analyses, stratified by cancer stage, involved both conventional Cox''s model and its flexible generalization, which permitted testing the underlying assumptions and accounting for changes over time in the effects of prognostic factors. Results: Conventional assumptions of proportional hazards (PH) (P =0.003) and linear increase in risk with increasing age (P =0.003) were rejected for age at cancer diagnosis in patients with less advanced (stage I/II) gastric cancers. Flexible modeling revealed that: (1) the effect of age was important mostly in the first year after diagnosis; and (2) mortality increased both for the youngest and the oldest patients. In conventional analyses, calendar year of diagnosis had no association with mortality in stage I/II cancers (P =0.37). In contrast, flexible analyses indicated a statistically significant reduction in early, mostly postsurgical, mortality between early 1970s and 1980s. Conclusion: Flexible modeling and testing conventional assumptions may yield new insights in prognostic studies of cancer mortality. [Copyright &y& Elsevier]

The authors compare the performance of different regression models for censored survival data in modeling the impact of prognostic factors on all-cause mortality in colon cancer. The data were for 1,951 patients, who were diagnosed in 1977-1991, recorded by the Registry of Digestive Tumors of Cote d'Or, France, and followed for up to 15 years. Models include the Cox proportional hazards model and its three generalizations that allow for hazard ratio to change over time: 1) the piecewise model where hazard ratio is a step function; 2) the model with interaction between a predictor and a parametric function of time; and 3) the non-parametric regression spline model. Results illustrate the importance of accounting for non-proportionality of hazards, and some advantages of flexible non-parametric modeling of time-dependent effects. The authors provide empirical evidence for the dependence of the results of piecewise and parametric models on arbitrary a priori choices, regarding the number of time intervals and specific parametric function, which may lead to biased estimates and low statistical power. The authors demonstrate that a single, a priori selected spline model recovers a variety of patterns of changes in hazard ratio and fits better than other models, especially when the changes are nonmonotonic, as in the case of cancer stages. Am J Epidemiol 1999; 150:1188–1200. [ABSTRACT FROM PUBLISHER]

The Cox proportional hazards model with time-dependent covariates (TDC) is now a part of the standard statistical analysis toolbox in medical research. As new methods involving more complex modeling of time-dependent variables are developed, simulations could often be used to systematically assess the performance of these models. Yet, generating event times conditional on TDC requires well-designed and efficient algorithms. We compare two classes of such algorithms: permutational algorithms (PAs) and algorithms based on a binomial model. We also propose a modification of the PA to incorporate a rejection sampler. We performed a simulation study to assess the accuracy, stability, and speed of these algorithms in several scenarios. Both classes of algorithms generated data sets that, once analyzed, provided virtually unbiased estimates with comparable variances. In terms of computational efficiency, the PA with the rejection sampler reduced the time necessary to generate data by more than 50 per cent relative to alternative methods. The PAs also allowed more flexibility in the specification of the marginal distributions of event times and required less calibration. Copyright © 2007 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Background: Existing clinical trial data do not address whether all angiotensin-converting-enzyme (ACE) inhibitors are similarly beneficial in improving survival and reducing the rate of readmission among patients with congestive heart failure. We sought to answer this question using administrative databases from Canada's 3 most populous provinces. Methods: Using linked hospital discharge and prescription claims databases in Quebec, Ontario and British Columbia, we identified all patients 65 years or older who were admitted to hospital because of congestive heart failure between Jan. 1, 1998, and Mar. 31, 2002, and who had not been admitted for the same reason in the 3 years preceding the study period. We analyzed the association between the type of ACE inhibitor prescribed within 30 days after discharge and subsequent mortality using Cox proportional hazards models. We then adjusted for demographic, clinical, physician and hospital-related variables, with additional time-dependent variables representing current drug use and dosage. We chose ramipril as the reference category for comparison with the other ACE inhibitors because it has increasingly been prescribed to patients with congestive heart failure. Results: A total of 43 316 patients with congestive heart failure filled prescriptions for ACE inhibitors within 30 days after discharge from hospital. Demographic, clinical and prescription-related characteristics were similar among users of each type of ACE inhibitor. In the time-dependent model, the mortality associated with 5 ACE inhibitors was similar to that with ramipril: adjusted hazard ratios (and 95% confidence intervals [CIs]) were 0.95 (0.89-1.02) for lisinopril, 0.92 (0.85-1.00) for fosinopril, 0.99 (0.88-1.11) for quinapril, 0.90 (0.77-1.06) for perindopril and 1.00 (0.80-1.24) for cilazapril. However, use of enalapril or captopril was associated with higher mortality compared with ramipril: adjusted hazard ratios (and 95% CIs) were 1.10 (1.04-1.16) for enalapril and 1.13 (1.01-1.26) for captopril. Interpretation: When prescribing ACE inhibitors to patients, physicians should consider a possible 10%-15% increase in mortality with captopril and enalapril compared with ramipril among patients with congestive heart failure. [ABSTRACT FROM AUTHOR]

The article reports on a study investigating the physician to patient communication skills examination's results as a predictor of medical care complaints. Medical schools have incorporated clinical skills and patient communication studies into their curricula to address patient dissatisfaction and to decrease the incidence of malpractice claims. A national licensing examination was instituted in Canada and the U.S. to evaluate physicians' ability to communicate with patients. The study explains the correlation with the scores and predicted complaints.

Abstract: Objective: To evaluate alternative approaches to correct for bias due to inaccurate diagnostic criteria in database studies of associations. Study Design and Settings: A simulation study of a hypothetical cohort of 10,000 subjects selected based on database-derived diagnostic criteria with positive predictive value (PPV) of either 53% or 80%. Analyses focus on the putative association between a drug and the time to a negative outcome. The association is confounded for “false positive” subjects, where the drug acts as a marker for unobserved frailty. First, we estimate the conventional multivariable Cox''s Model 1. We then assume having in-depth evaluation of a fraction of subjects, which permits estimating the probabilities of having the disease for all subjects in the cohort. Alternative correction methods use the estimated probability as a confounder (Model 2), a modifier of the drug effect (Model 3), or an importance weight (Model 4). Results: With a PPV of 53%, Models 1 and 2 induced about 50% underestimation bias for the drug effect. Interaction-based Model 3 yielded the least biased estimates (25% bias), whereas weighting by probability (Model 4) resulted in slightly more biased (33%), but more stable estimates. Conclusion: Proposed methods help reducing bias due to sample contamination. [Copyright &y& Elsevier]

In order to yield more flexible models, the Cox regression model, λ( t; x) = λ0( t)exp(β x), has been generalized using different non-parametric model estimation techniques. One generalization is the relaxation of log-linearity in x, λ( t; x) = λ0( t)exp[ r( x)]. Another is the relaxation of the proportional hazards assumption, λ( t; x) = λ0( t)exp[β( t) x]. These generalizations are typically considered independently of each other. We propose the product model, λ( t; x) = λ0( t)exp[β( t)r( x)] which allows for joint estimation of both effects, and investigate its properties. The functions describing the time-dependent β( t) and non-linear r( x) effects are modelled simultaneously using regression splines and estimated by maximum partial likelihood. Likelihood ratio tests are proposed to compare alternative models. Simulations indicate that both the recovery of the shapes of the two functions and the size of the tests are reasonably accurate provided they are based on the correct model. By contrast, type I error rates may be highly inflated, and the estimates considerably biased, if the model is misspecified. Applications in cancer epidemiology illustrate how the product model may yield new insights about the role of prognostic factors. Copyright © 2006 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

The mathematical representation of smoking history is an important tool in analysis of epidemiological and clinical data. Hoffmann and colleagues recently proposed a single aggregate measure of smoking exposure that incorporates intensity, duration, and time since cessation. This comprehensive smoking index (CSI), which may be incorporated in any regression model, depends on a half-life (τ) and a lag (δ) parameters that have to be fixed a priori, or estimated by maximizing the fit. The CSI has not previously been used for analysis of cancer data. Following some preliminary results on smoking and lung cancer, the authors proposed a new version of the CSI for lung cancer. The aim of this study was to investigate the performance of the original and the new versions of the CSI in the analysis of three data sets from two case-control studies of lung cancer undertaken in Montreal, in 1979-1985 in males, and in 1996-2000 in both males and females. The estimates of τ and δ for both versions of the CSI were similar across data sets. The new version of the CSI fitted the three data sets systematically although moderately better than the original version, and at least as well as other representations of lifetime smoking history that used separate variables for time since cessation and cumulative amount of cigarettes smoked. The results suggest that the CSI may be an attractive and parsimonious alternative to conventional modelling of different aspects of smoking history for lung cancer. Copyright © 2006 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Abstract: Background and Objectives: Accurate assessment of medication impact requires modeling cumulative effects of exposure duration and dose; however, postmarketing studies usually represent medication exposure by baseline or current use only. We propose new methods for modeling various aspects of medication use history and employment of them to assess the adverse effects of selected benzodiazepines. Study Design and Setting: Time-dependent measures of cumulative dose or duration of use, with weighting of past exposures by recency, were proposed. These measures were then included in alternative versions of the multivariable Cox model to analyze the risk of fall related injuries among the elderly new users of three benzodiazepines (nitrazepam, temazepam, and flurazepam) in Quebec. Akaike's information criterion (AIC) was used to select the most predictive model for a given benzodiazepine. Results: The best-fitting model included a combination of cumulative duration and current dose for temazepam, and cumulative dose for flurazepam and nitrazepam, with different weighting functions. The window of clinically relevant exposure was shorter for flurazepam than for the two other products. Conclusion: Careful modeling of the medication exposure history may enhance our understanding of the mechanisms underlying their adverse effects. [Copyright &y& Elsevier]

Background: Many exposures in epidemiological studies have nonlinear effects and the problem is to choose an appropriate functional relationship between such exposures and the outcome. One common approach is to investigate several parametric transformations of the covariate of interest, and to select a posteriori the function that fits the data the best. However, such approach may result in an inflated Type I error. Methods: Through a simulation study, we generated data from Cox's models with different transformations of a single continuous covariate. We investigated the Type I error rate and the power of the likelihood ratio test (LRT) corresponding to three different procedures that considered the same set of parametric dose-response functions. The first unconditional approach did not involve any model selection, while the second conditional approach was based on a posteriori selection of the parametric function. The proposed third approach was similar to the second except that it used a corrected critical value for the LRT to ensure a correct Type I error. Results: The Type I error rate of the second approach was two times higher than the nominal size. For simple monotone dose-response, the corrected test had similar power as the unconditional approach, while for non monotone, dose-response, it had a higher power. A real-life application that focused on the effect of body mass index on the risk of coronary heart disease death, illustrated the advantage of the proposed approach. Conclusion: Our results confirm that a posteriori selecting the functional form of the dose-response induces a Type I error inflation. The corrected procedure, which can be applied in a wide range of situations, may provide a good trade-off between Type I error and power. [ABSTRACT FROM AUTHOR]