Self-controlled Case Series Model Research Articles

Association between statins and the risk of suicide attempt, depression, anxiety, and seizure: A population-based, self-controlled case series study

BackgroundRisk of suicide attempt, depression, anxiety and seizure and the association with statins is an ongoing debate. We aim to investigate the association between statins and the above neuropsychological outcomes, in specific pre- and post-exposure time windows. MethodsWe identified patients aged 40–75 years old who were dispensed a statin between January 1, 2003 and December 31, 2012 from the Hong Kong Clinical Data Analysis & Reporting System (CDARS), an electronic medical records database. Patients with new onset of suicide attempt, depression, anxiety and seizure were derived from the original dataset separately, in a self-controlled case series study design. A non-parametric spline-based self-controlled case series model was built to measure continuous changes of risk. ResultsWe identified 396,614 statin users. The risk of each outcome was elevated prior to statin initiation with incidence rate ratios of 1.38 (95 % CI, 1.09–1.74) for suicide attempt, 1.29 (95 % CI, 1.15–1.45) for depression, 1.35 (95 % CI, 1.19–1.53) for anxiety, and 1.45 (95 % CI, 1.21–1.73) for seizure. The incidence rate ratios remained elevated after the initiation of statins during the first 90 and 91–365 days after statin prescription and decreased to the baseline level after 1 year of continuous prescription. LimitationsCDARS includes prescription data but not adherence data, which could lead to misclassification of exposure periods. ConclusionsOur study does not support a direct association between statin use and suicide attempt, depression, anxiety and seizure, whose risks could be explained by cardiovascular events, for which statins were prescribed.

A modified self-controlled case series method for event-dependent exposures and high event-related mortality, with application to COVID-19 vaccine safety.

We propose a modified self‐controlled case series (SCCS) method to handle both event‐dependent exposures and high event‐related mortality. This development is motivated by an epidemiological study undertaken in France to quantify potential risks of cardiovascular events associated with COVID‐19 vaccines. Event‐dependence of vaccinations, and high event‐related mortality, are likely to arise in other SCCS studies of COVID‐19 vaccine safety. Using this case study and simulations to broaden its scope, we explore these features and the biases they may generate, implement the modified SCCS model, illustrate some of the properties of this model, and develop a new test for presence of a dose effect. The model we propose has wider application, notably when the event of interest is death.

Clinical connectivity map for drug repurposing: using laboratory results to bridge drugs and diseases

BackgroundDrug repurposing, the process of identifying additional therapeutic uses for existing drugs, has attracted increasing attention from both the pharmaceutical industry and the research community. Many existing computational drug repurposing methods rely on preclinical data (e.g., chemical structures, drug targets), resulting in translational problems for clinical trials.ResultsIn this study, we propose a novel framework based on clinical connectivity mapping for drug repurposing to analyze therapeutic effects of drugs on diseases. We firstly establish clinical drug effect vectors (i.e., drug-laboratory results associations) by applying a continuous self-controlled case series model on a longitudinal electronic health record data, then establish clinical disease sign vectors (i.e., disease-laboratory results associations) by applying a Wilcoxon rank sum test on a large-scale national survey data. Eventually, a repurposing possibility score for each drug-disease pair is computed by applying a dot product-based scoring function on clinical disease sign vectors and clinical drug effect vectors. During the experiment, we comprehensively evaluate 392 drugs for 6 important chronic diseases (include asthma, coronary heart disease, congestive heart failure, heart attack, type 2 diabetes, and stroke). The experiment results not only reflect known associations between diseases and drugs, but also include some hidden drug-disease associations. The code for this paper is available at: https://github.com/HoytWen/CCMDRConclusionsThe proposed clinical connectivity map framework uses laboratory results found from electronic clinical information to bridge drugs and diseases, which make their relations explainable and has better translational power than existing computational methods. Experimental results demonstrate the effectiveness of our proposed framework, further case analysis also proves our method can be used to repurposing existing drugs opportunities.

Methylphenidate and the risk of burn injury among children with attention-deficit/hyperactivity disorder.

Attention-deficit/hyperactivity disorder (ADHD) is associated with a higher risk of burn injury than in the normal population. Nevertheless, the influence of methylphenidate (MPH) on the risk of burn injury remains unclear. This retrospective cohort study analysed the effect of MPH on the risk of burn injury in children with ADHD. Data were from Taiwan's National Health Insurance Research Database (NHIRD). The sample comprised individuals younger than 18 years with a diagnosis of ADHD (n = 90 634) in Taiwan's NHIRD between January 1996 and December 2013. We examined the cumulative effect of MPH on burn injury risk using Cox proportional hazards models. We conducted a sensitivity analysis for immortal time bias using a time-dependent Cox model and within-patient comparisons using the self-controlled case series model. Children with ADHD taking MPH had a reduced risk of burn injury, with a cumulative duration of treatment dose-related effect, compared with those not taking MPH. Compared with children with ADHD not taking MPH, the adjusted hazard ratio for burn injury was 0.70 in children taking MPH for <90 days (95% confidence interval (CI) 0.64-0.77) and 0.43 in children taking MPH for ≥90 days (95% CI 0.40-0.47), with a 50.8% preventable fraction. The negative association of MPH was replicated in age-stratified analysis using time-dependent Cox regression and self-controlled case series models. This study showed that MPH treatment was associated with a lower risk of burn injury in a cumulative duration of treatment dose-related effect manner.

ConvSCCS: convolutional self-controlled case series model for lagged adverse event detection

With the increased availability of large electronic health records databases comes the chance of enhancing health risks screening. Most post-marketing detection of adverse drug reaction (ADR) relies on physicians' spontaneous reports, leading to under-reporting. To take up this challenge, we develop a scalable model to estimate the effect of multiple longitudinal features (drug exposures) on a rare longitudinal outcome. Our procedure is based on a conditional Poisson regression model also known as self-controlled case series (SCCS). To overcome the need of precise risk periods specification, we model the intensity of outcomes using a convolution between exposures and step functions, which are penalized using a combination of group-Lasso and total-variation. Up to our knowledge, this is the first SCCS model with flexible intensity able to handle multiple longitudinal features in a single model. We show that this approach improves the state-of-the-art in terms of mean absolute error and computation time for the estimation of relative risks on simulated data. We apply this method on an ADR detection problem, using a cohort of diabetic patients extracted from the large French national health insurance database (SNIIRAM), a claims database containing medical reimbursements of more than 53 million people. This work has been done in the context of a research partnership between Ecole Polytechnique and CNAMTS (in charge of SNIIRAM).

A data-driven method to detect adverse drug events from prescription data

Drug safety issues such as Adverse Drug Events (ADEs) can cause serious consequences for the public. The clinical trials that are undertaken to assess medicine efficacy and safety prior to marketing, generally, may provide sufficient samples for discovering common ADEs. However, more samples are needed to detect infrequent and rare events. Additionally, clinical trials may not include all subgroups of patients. For these reasons, post-marketing surveillance of medicines is necessary for identifying drug safety issues. Most regulatory agencies use the Spontaneous Reporting Systems to identify associations between medicines and suspected ADEs. Data mining with effective analytical frameworks and large-scale medical data is potentially an alternative method to discover and monitor ADEs. In the present paper, we aim to detect potential ADEs from prescription data by discovering ADE associated prescription sequences. In an ADE associated prescription sequence 〈Dp→Ds〉, the prior medicine Dp leads to an ADE for which the succeeding medicine Ds is dispensed to treat. We propose a data-driven method which integrates (1) a constrained sequential pattern mining to uncover prescription sequences as potential signals of ADEs, (2) domain constraints to eliminate interference signals and (3) an adapted Self-Controlled Case Series model to evaluate the potential signals of ADEs. Despite ample prior works using Electronic Health Records (EHRs), our method utilises pure prescription data which does not contain additional information, e.g. symptoms or diagnoses as included in EHRs. To assess the performance of the proposed method, we apply it to a real-world dataset from the Pharmaceutical Benefits Scheme of Australia. The dataset contains over 50 million records covering approximately 2 million patients. The results demonstrate the effectiveness of our method in identifying both known ADEs and unknown yet suspicious ADEs with limited detection of false positive signals. Comparing to a recognised gold standard, our method successfully detects 67.4% of the positive adverse events while only 8.78% false positives exist.

Investigating the assumptions of the self-controlled case series method.

We describe some simple techniques for investigating 2 key assumptions of the self-controlled case series (SCCS) method, namely, that events do not influence subsequent exposures and that events do not influence the length of observation periods. For each assumption, we propose some simple tests based on the standard SCCS model, along with associated graphical displays. The methods also enable the user to investigate the robustness of the results obtained using the standard SCCS model to failure of assumptions. The proposed methods are investigated by simulations and applied to data on measles, mumps and rubella vaccine, and antipsychotics.

Antibiotic Exposure and Risk of Community-associated Clostridium difficile infection (CA-CDI): A Self-Controlled Case Series Analysis

BackgroundCA-CDI accounts for up to 50% of all CDIs. Case–control studies (CCS) have been used to estimate the odds ratio (OR) of CA-CDI associated with antibiotic exposure. These ORs demonstrate significant heterogeneity across studies. Unlike CCS, a self-controlled case series (SCCS) design can be used to control for all time-invariant confounders leading to less biased effect estimates.MethodsAdults (≥18 years) registered (N = 139,670) with the Barrie and Community Family Health Team (BCFHT) were included in the study. Cases were defined as any patient with an incident case of CA-CDI and ≥1 antibiotic exposure occurring between January 1, 2011 and December 31, 2016. The SCCS model was used to estimate the association between antibiotic exposure and CA-CDI. The SCCS model yields estimates of the relative incidence rate of CA-CDI in exposure periods relative to non-exposure periods within a case. Exposure periods were defined as starting two days after any antibiotic prescription and ending 60 days later. Multiple exposure periods and time-varying confounders due to calendar year were included in the final model. The relative incidence rate ratio (IRR) was estimated using conditional poisson regression analysis. Proton pump inhibitor (PPI) use was included as an effect modifier. Antibiotics were divided into high-risk (fluoroquinolone, clindamycin, and cephalosporin) and low-risk exposures. Research ethics approval was obtained from the BFCHT research ethics board.ResultsAmong 544 total CDI cases, N = 189 CA-CDI cases met the inclusion criteria. Any antibiotic exposure increases the risk by ≥2-fold, with no difference observed between high and low-risk groups (IRR=1.11, 95% CI 0.53–2.36) (Table 1).ConclusionAntibiotic exposure increases the risk of CA-CDI, with IRR estimates similar to those observed for healthcare-associated-CDI. This, along with the control of all time-invariant confounders by the SCCS method suggests a less biased effect estimate previously reported from CCS.Table 1 Variable IRR 95% Confidence Interval P-value Antibiotic Exposure GroupPPINoneYes0.80(0.62–1.03)0.09Low riskYes1.95(0.09–4.24)0.09High riskYes1.20(0.42–3.40)0.73OverallLow risk2.03(1.19–3.47)0.009High risk2.26(1.29–3.98)0.005Disclosures All authors: No reported disclosures.

Flexible modelling of vaccine effect in self-controlled case series models.

The self-controlled case series (SCCS) method, commonly used to investigate the safety of vaccines, requires information on cases only and automatically controls all age-independent multiplicative confounders, while allowing for an age-dependent baseline incidence. Currently, the SCCS method represents the time-varying exposures using step functions with pre-determined cut points. A less prescriptive approach may be beneficial when the shape of the relative risk function associated with exposure is not known a priori, especially when exposure effects can be long-lasting. We therefore propose to model exposure effects using flexible smooth functions. Specifically, we used a linear combination of cubic M-splines which, in addition to giving plausible shapes, avoids the integral in the log-likelihood function of the SCCS model. The methods, though developed specifically for vaccines, are applicable more widely. Simulations showed that the new approach generally performs better than the step function method. We applied the new method to two data sets, on febrile convulsion and exposure to MMR vaccine, and on fractures and thiazolidinedione use.

A Positive Event Dependence Model for Self‐Controlled Case Series with Applications in Postmarketing Surveillance

A primary objective in the application of postmarketing drug safety surveillance is to ascertain the relationship between time-varying drug exposures and recurrent adverse events (AEs) related to health outcomes. The self-controlled case series (SCCS) method is one approach to analysis in this context. It is based on a conditional Poisson regression model, which assumes that events at different time points are conditionally independent given the covariate process. This requirement is problematic when the occurrence of an event can alter the future event risk. In a clinical setting, for example, patients who have a first myocardial infarction (MI) may be at higher subsequent risk for a second. In this work, we propose the positive dependence self-controlled case series (PD-SCCS) method: a generalization of SCCS that allows the occurrence of an event to increase the future event risk, yet maintains the advantages of the original model by controlling for fixed baseline covariates and relying solely on data from cases. As in the SCCS model, individual-level baseline parameters drop out of the PD-SCCS likelihood. Data sources used for postmarketing surveillance can contain tens of millions of people, so in this situation it is particularly advantageous that PD-SCCS avoids doing a costly estimation of individual parameters. We develop expressions for large sample inference and optimization for PD-SCCS and compare the results of our generalized model with the more restrictive SCCS approach.

Within-Individual Dependence in Self-Controlled Case Series Models for Recurrent Events

SummaryThe self-controlled case series model may be used to analyse recurrent events when event times are conditionally independent given fixed or random individual effects. To test the hypothesis of within-individual independence, the model is augmented by an association parameter for diagonal dependence, which provides the focus for a test of independence. Estimation methods are described, and simulations are presented to illustrate the power of the method in relevant scenarios, and to quantify the bias resulting from failure of the independence assumption. The methods are applied to two data sets, relating to a rare bleeding disorder and to myocardial infarction.

Case series analysis for censored, perturbed, or curtailed post-event exposures

A new method is developed for analyzing case series data in situations where occurrence of the event censors, curtails, or otherwise affects post-event exposures. Unbiased estimating equations derived from the self-controlled case series model are adapted to allow for exposures whose occurrence or observation is influenced by the event. The method applies to transient point exposures and rare nonrecurrent events. Asymptotic efficiency is studied in some special cases. A computational scheme based on a pseudo-likelihood is proposed to make the computations feasible in complex models. Simulations, a validation study, and 2 applications are described.

Self-controlled case series analyses: Small-sample performance

Second-order expressions for the asymptotic bias and variance of the log relative incidence estimator are derived for the self-controlled case series model in a simplified scenario. The dependence of the bias and variance on factors such as the relative incidence and ratio of risk to observation period are studied. Small-sample performance of the estimator in realistic scenarios is investigated using simulations. It is found that, in scenarios likely to arise in practice, asymptotic methods are valid for numbers of cases in excess of 20–50 depending on the ratio of the risk period to the observation period and on the relative incidence. The application of Monte Carlo methods to self-controlled case series analyses is also discussed.