Gabapentinoids and Risk for Severe Exacerbation in Chronic Obstructive Pulmonary Disease : A Population-Based Cohort Study.

BACKGROUND: North American and European health agencies recently warned of severe breathing problems associated with gabapentinoids, including in patients with chronic obstructive pulmonary disease (COPD), although supporting evidence is limited. OBJECTIVE: To assess whether gabapentinoid use is associated with severe exacerbation in patients with COPD. DESIGN: Time-conditional propensity score-matched, new-user cohort study. SETTING: Health insurance databases from the Régie de l'assurance maladie du Québec in Canada. PATIENTS: Within a base cohort of patients with COPD between 1994 and 2015, patients initiating gabapentinoid therapy with an indication (epilepsy, neuropathic pain, or other chronic pain) were matched 1:1 with nonusers on COPD duration, indication for gabapentinoids, age, sex, calendar year, and time-conditional propensity score. MEASUREMENTS: The primary outcome was severe COPD exacerbation requiring hospitalization. Hazard ratios (HRs) associated with gabapentinoid use were estimated in subcohorts according to gabapentinoid indication and in the overall cohort. RESULTS: The cohort included 356 gabapentinoid users with epilepsy, 9411 with neuropathic pain, and 3737 with other chronic pain, matched 1:1 to nonusers. Compared with nonuse, gabapentinoid use was associated with increased risk for severe COPD exacerbation across the indications of epilepsy (HR, 1.58 [95% CI, 1.08 to 2.30]), neuropathic pain (HR, 1.35 [CI, 1.24 to 1.48]), and other chronic pain (HR, 1.49 [CI, 1.27 to 1.73]) and overall (HR, 1.39 [CI, 1.29 to 1.50]). LIMITATION: Residual confounding, including from lack of smoking information. CONCLUSION: In patients with COPD, gabapentinoid use was associated with increased risk for severe exacerbation. This study supports the warnings from regulatory agencies and highlights the importance of considering this potential risk when prescribing gabapentin and pregabalin to patients with COPD. PRIMARY FUNDING SOURCE: Canadian Institutes of Health Research and Canadian Lung Association.

Semiparametric Bayesian inference for optimal dynamic treatment regimes via dynamic marginal structural models.

Considerable statistical work done on dynamic treatment regimes (DTRs) is in the frequentist paradigm, but Bayesian methods may have much to offer in this setting as they allow for the appropriate representation and propagation of uncertainty, including at the individual level. In this work, we extend the use of recently developed Bayesian methods for Marginal Structural Models to arrive at inference of DTRs. We do this (i) by linking the observational world with a world in which all patients are randomized to a DTR, thereby allowing for causal inference and then (ii) by maximizing a posterior predictive utility, where the posterior distribution has been obtained from nonparametric prior assumptions on the observational world data-generating process. Our approach relies on Bayesian semiparametric inference, where inference about a finite-dimensional parameter is made all while working within an infinite-dimensional space of distributions. We further study Bayesian inference of DTRs in the double robust setting by using posterior predictive inference and the nonparametric Bayesian bootstrap. The proposed methods allow for uncertainty quantification at the individual level, thereby enabling personalized decision-making. We examine the performance of these methods via simulation and demonstrate their utility by exploring whether to adapt HIV therapy to a measure of patients' liver health, in order to minimize liver scarring.

Variable selection in high dimensions for discrete-outcome individualized treatment rules: Reducing severity of depression symptoms.

Despite growing interest in estimating individualized treatment rules, little attention has been given the binary outcome setting. Estimation is challenging with nonlinear link functions, especially when variable selection is needed. We use a new computational approach to solve a recently proposed doubly robust regularized estimating equation to accomplish this difficult task in a case study of depression treatment. We demonstrate an application of this new approach in combination with a weighted and penalized estimating equation to this challenging binary outcome setting. We demonstrate the double robustness of the method and its effectiveness for variable selection. The work is motivated by and applied to an analysis of treatment for unipolar depression using a population of patients treated at Kaiser Permanente Washington.

Principal stratification for quantile causal effects under partial compliance.

Within the principal stratification framework in causal inference, the majority of the literature has focused on binary compliance with an intervention and modelling means. Yet in some research areas, compliance is partial, and research questions-and hence analyses-are concerned with causal effects on (possibly high) quantiles rather than on shifts in average outcomes. Modelling partial compliance is challenging because it can suffer from lack of identifiability. We develop an approach to estimate quantile causal effects within a principal stratification framework, where principal strata are defined by the bivariate vector of (partial) compliance to the two levels of a binary intervention. We propose a conditional copula approach to impute the missing potential compliance and estimate the principal quantile treatment effect surface at high quantiles, allowing the copula association parameter to vary with the covariates. A bootstrap procedure is used to estimate the parameter to account for inflation due to imputation of missing compliance. Moreover, we describe precise assumptions on which the proposed approach is based, and investigate the finite sample behavior of our method by a simulation study. The proposed approach is used to study the 90th principal quantile treatment effect of executive stay-at-home orders on mitigating the risk of COVID-19 transmission in the United States.

Dynamic Treatment Regimes Using Bayesian Additive Regression Trees for Censored Outcomes.

To achieve the goal of providing the best possible care to each individual under their care, physicians need to customize treatments for individuals with the same health state, especially when treating diseases that can progress further and require additional treatments, such as cancer. Making decisions at multiple stages as a disease progresses can be formalized as a dynamic treatment regime (DTR). Most of the existing optimization approaches for estimating dynamic treatment regimes including the popular method of Q-learning were developed in a frequentist context. Recently, a general Bayesian machine learning framework that facilitates using Bayesian regression modeling to optimize DTRs has been proposed. In this article, we adapt this approach to censored outcomes using Bayesian additive regression trees (BART) for each stage under the accelerated failure time modeling framework, along with simulation studies and a real data example that compare the proposed approach with Q-learning. We also develop an R wrapper function that utilizes a standard BART survival model to optimize DTRs for censored outcomes. The wrapper function can easily be extended to accommodate any type of Bayesian machine learning model.

Impact of Hepatitis C Virus Cure on Depressive Symptoms in the Human Immunodeficiency Virus-Hepatitis C Virus Coinfected Population in Canada.

BACKGROUND: Depression is common in people with human immunodeficiency virus (HIV) and hepatitis C virus (HCV), with biological and psychosocial mechanisms at play. Direct acting antivirals (DAA) result in high rates of sustained virologic response (SVR), with minimal side-effects. We assessed the impact of SVR on presence of depressive symptoms in the HIV-HCV coinfected population in Canada during the second-generation DAA era (2013-2020). METHODS: We used data from the Canadian CoInfection Cohort (CCC), a multicenter prospective cohort of people with a HIV and HCV coinfection, and its associated sub-study on food security. Because depression screening was performed only in the sub-study, we predicted Center for Epidemiologic Studies Depression Scale-10 classes in the CCC using a random forest classifier and corrected for misclassification. We included participants who achieved SVR and fit a segmented modified Poisson model using an interrupted time series design, adjusting for time-varying confounders. RESULTS: We included 470 participants; 58% had predicted depressive symptoms at baseline. The median follow-up was 2.4 years (interquartile range [IQR]: 1.0-4.5.) pre-SVR and 1.4 years (IQR: 0.6-2.5) post-SVR. The pre-SVR trend suggested depressive symptoms changed little over time, with no immediate level change at SVR. However, post-SVR trends showed a reduction of 5% per year (risk ratio: 0.95 (95% confidence interval [CI]: .94-.96)) in the prevalence of depressive symptoms. CONCLUSIONS: In the DAA era, predicted depressive symptoms declined over time following SVR. These improvements reflect possible changes in biological pathways and/or better general health. If such improvements in depression symptoms are durable, this provides an additional reason for treatment and early cure of HCV.

Variable selection in regression-based estimation of dynamic treatment regimes.

Dynamic treatment regimes (DTRs) consist of a sequence of decision rules, one per stage of intervention, that aim to recommend effective treatments for individual patients according to patient information history. DTRs can be estimated from models which include interactions between treatment and a (typically small) number of covariates which are often chosen a priori. However, with increasingly large and complex data being collected, it can be difficult to know which prognostic factors might be relevant in the treatment rule. Therefore, a more data-driven approach to select these covariates might improve the estimated decision rules and simplify models to make them easier to interpret. We propose a variable selection method for DTR estimation using penalized dynamic weighted least squares. Our method has the strong heredity property, that is, an interaction term can be included in the model only if the corresponding main terms have also been selected. We show our method has both the double robustness property and the oracle property theoretically; and the newly proposed method compares favorably with other variable selection approaches in numerical studies. We further illustrate the proposed method on data from the Sequenced Treatment Alternatives to Relieve Depression study.

Bayesian sample size calculations for comparing two strategies in SMART studies.

In the management of most chronic conditions characterized by the lack of universally effective treatments, adaptive treatment strategies (ATSs) have grown in popularity as they offer a more individualized approach. As a result, sequential multiple assignment randomized trials (SMARTs) have gained attention as the most suitable clinical trial design to formalize the study of these strategies. While the number of SMARTs has increased in recent years, sample size and design considerations have generally been carried out in frequentist settings. However, standard frequentist formulae require assumptions on interim response rates and variance components. Misspecifying these can lead to incorrect sample size calculations and correspondingly inadequate levels of power. The Bayesian framework offers a straightforward path to alleviate some of these concerns. In this paper, we provide calculations in a Bayesian setting to allow more realistic and robust estimates that account for uncertainty in inputs through the 'two priors' approach. Additionally, compared to the standard frequentist formulae, this methodology allows us to rely on fewer assumptions, integrate pre-trial knowledge, and switch the focus from the standardized effect size to the MDD. The proposed methodology is evaluated in a thorough simulation study and is implemented to estimate the sample size for a full-scale SMART of an internet-based adaptive stress management intervention on cardiovascular disease patients using data from its pilot study conducted in two Canadian provinces.

Double robust estimation of optimal partially adaptive treatment strategies: An application to breast cancer treatment using hormonal therapy.

Precision medicine aims to tailor treatment decisions according to patients' characteristics. G-estimation and dynamic weighted ordinary least squares are double robust methods to identify optimal adaptive treatment strategies. It is underappreciated that they require modeling all existing treatment-confounder interactions to be consistent. Identifying optimal partially adaptive treatment strategies that tailor treatments according to only a few covariates, ignoring some interactions, may be preferable in practice. Building on G-estimation and dWOLS, we propose estimators of such partially adaptive strategies and demonstrate their double robustness. We investigate these estimators in a simulation study. Using data maintained by the Centre des Maladies du Sein, we estimate a partially adaptive treatment strategy for tailoring hormonal therapy use in breast cancer patients. R software implementing our estimators is provided.

A time-dependent Poisson-Gamma model for recruitment forecasting in multicenter studies.

Forecasting recruitments is a key component of the monitoring phase of multicenter studies. One of the most popular techniques in this field is the Poisson-Gamma recruitment model, a Bayesian technique built on a doubly stochastic Poisson process. This approach is based on the modeling of enrollments as a Poisson process where the recruitment rates are assumed to be constant over time and to follow a common Gamma prior distribution. However, the constant-rate assumption is a restrictive limitation that is rarely appropriate for applications in real studies. In this paper, we illustrate a flexible generalization of this methodology which allows the enrollment rates to vary over time by modeling them through B-splines. We show the suitability of this approach for a wide range of recruitment behaviors in a simulation study and by estimating the recruitment progression of the Canadian Co-infection Cohort.

Benefits of the PRISM Shelter-Based Program for Attainment of Stable Housing and Functional Outcomes by People Experiencing Homelessness and Mental Illness: A Quantitative Analysis.

OBJECTIVE: To explore the housing trajectory, personal recovery, functional level, and quality of life of clients at discharge and 1 year after completing Projet Réaffiliation Itinérance Santé Mentale (PRISM), a shelter-based mental health and rehabilitation program intended to provide individuals experiencing homelessness and severe mental illness with transition housing and to reconnect them with mental health and social services. METHOD: Housing status, psychiatric follow-up trajectory, personal recovery (Canadian Personal Recovery Outcome Measure), functional level (Multnomah Community Ability Scale), and quality of life (Lehman Quality of Life Interview) were assessed at program entry, at program discharge and 1 year later. RESULTS: Of the 50 clients who participated in the study from May 31, 2018, to December 31, 2019, 43 completed the program. Of these, 76.7% were discharged to housing modalities and 78% were engaged with psychiatric follow-up at the program's end. Housing stability, defined as residing at the same permanent address since discharge, was achieved for 62.5% of participants at 1-year follow-up. Functional level and quality of life scores improved significantly both at discharge and at 1-year follow-up from baseline. CONCLUSIONS: Admission to PRISM helped clients secure long-term stable housing and appropriate psychiatric follow-up. Stable housing was maintained for most clients at 1-year follow-up, and they benefited from sustained functional and quality of life outcomes in long-term follow-up.

On "Reflections on the concept of optimality of single decision point treatment regimes".

This is a discussion of "Reflections on the concept of optimality of single decision point treatment regimes" by Trung Dung Tran, Ariel Alonso Abad, Geert Verbeke, Geert Molenberghs, and Iven Van Mechelen. The authors propose a thoughtful consideration of optimization targets and the implications of such targets for the resulting optimal treatment rule. However, we contest the assertation that targets of optimization have been overlooked and suggest additional considerations that researchers must contemplate as part of a complete framework for learning about optimal treatment regimes.

Monte Carlo sensitivity analysis for unmeasured confounding in dynamic treatment regimes.

Data-driven methods for personalizing treatment assignment have garnered much attention from clinicians and researchers. Dynamic treatment regimes formalize this through a sequence of decision rules that map individual patient characteristics to a recommended treatment. Observational studies are commonly used for estimating dynamic treatment regimes due to the potentially prohibitive costs of conducting sequential multiple assignment randomized trials. However, estimating a dynamic treatment regime from observational data can lead to bias in the estimated regime due to unmeasured confounding. Sensitivity analyses are useful for assessing how robust the conclusions of the study are to a potential unmeasured confounder. A Monte Carlo sensitivity analysis is a probabilistic approach that involves positing and sampling from distributions for the parameters governing the bias. We propose a method for performing a Monte Carlo sensitivity analysis of the bias due to unmeasured confounding in the estimation of dynamic treatment regimes. We demonstrate the performance of the proposed procedure with a simulation study and apply it to an observational study examining tailoring the use of antidepressant medication for reducing symptoms of depression using data from Kaiser Permanente Washington.

Prenatal Exposure to Insecticides and Weight Trajectories Among South African Children in the VHEMBE Birth Cohort.

BACKGROUND: Dichlorodiphenyltrichloroethane (DDT) or pyrethroid insecticides are sprayed inside dwellings for malaria vector control, resulting in high exposure to millions of people, including pregnant women. These chemicals disrupt endocrine function and may affect child growth. To our knowledge, few studies have investigated the potential impact of prenatal exposure to DDT or pyrethroids on growth trajectories. METHODS: We investigated associations between gestational insecticide exposure and child growth trajectories in the Venda Health Examination of Mothers, Babies and their Environment, a birth cohort of 751 children born between 2012 and 2013 in South Africa. Based on child weight measured at follow-up and abstracted from medical records, we modeled weight trajectories from birth to 5 years using SuperImposition, Translation and Rotation, which estimated two child-specific parameters: size (average weight) and tempo (age at peak weight velocity). We estimated associations between peripartum maternal concentrations of serum DDT, dichlorodiphenyldichloroethylene, or urinary pyrethroid metabolites and SuperImposition, Translation and Rotation parameters using marginal structural models. RESULTS: We observed that a 10-fold increase in maternal concentrations of the pyrethroid metabolite trans-3-(2,2,-dicholorvinyl)-2,2-dimethyl-cyclopropane carboxylic acid was associated with a 21g (95% confidence interval = -40, -1.6) smaller size among boys but found no association among girls (Pinteraction = 0.07). Estimates suggested that pyrethroids may be associated with earlier tempo but were imprecise. We observed no association with serum DDT or dichlorodiphenyldichloroethylene. CONCLUSIONS: Inverse associations between pyrethroids and weight trajectory parameters among boys are consistent with hypothesized disruption of androgen pathways and with our previous research in this population, and support the endocrine-disrupting potential of pyrethroids in humans.

HIV incidence and related risks among gay, bisexual, and other men who have sex with men in Montreal, Toronto, and Vancouver: Informing blood donor selection criteria in Canada.

BACKGROUND: An individualized behavior-based selection approach has potential to allow for a more equitable blood donor eligibility process. We collected biological and behavioral data from urban gay, bisexual, and other men who have sex with men (GBM) to inform the use of this approach in Canada. STUDY DESIGN AND METHODS: Engage is a closed prospective cohort of sexually active GBM, aged 16+ years, recruited via respondent-driven-sampling (RDS) in Montreal, Toronto, and Vancouver, Canada. Participants completed a questionnaire on behaviors (past 6 months) and tested for HIV and sexually transmitted and blood-borne infections at each visit. Rate ratios for HIV infection and predictive values for blood donation eligibility criteria were estimated by RDS-adjusted Poisson regression. RESULTS: Data on 2008 (study visits 2017-02 to 2021-08) HIV-negative participants were used. The HIV incidence rate for the three cities was 0.4|100 person-years [95%CI:0.3, 0.6]. HIV seroconversion was associated with age <30 years: adjusted rate ratio (aRR) 9.1 [95%CI:3.2, 26.2], 6-10 and >10 anal sex partners versus 1-6 aRR: 5.3 [2.1,13.5] and 8.4 [3.4, 20.9], and use of crystal methamphetamine during sex: 4.2 [1.5, 11.6]. Applying the combined selection criteria: drug injection, ≥2 anal sex partners, and a new anal sex partner, detected all participants who seroconverted (100% sensitivity, 100% negative predictive value), and would defer 63% of study participants from donating. CONCLUSION: Using three screening questions regarding drug injection and sexual behaviors in the past 6 months would correctly identify potential GBM donors at high risk of having recently contracted HIV. Doing so would reduce the proportion of deferred sexually active GBM by one-third.

Preserving data privacy when using multi-site data to estimate individualized treatment rules.

Precision medicine is a rapidly expanding area of health research wherein patient level information is used to inform treatment decisions. A statistical framework helps to formalize the individualization of treatment decisions that characterize personalized management plans. Numerous methods have been proposed to estimate individualized treatment rules that optimize expected patient outcomes, many of which have desirable properties such as robustness to model misspecification. However, while individual data are essential in this context, there may be concerns about data confidentiality, particularly in multi-center studies where data are shared externally. To address this issue, we compared two approaches to privacy preservation: (i) data pooling, which is a covariate microaggregation technique and (ii) distributed regression. These approaches were combined with the doubly robust yet user-friendly method of dynamic weighted ordinary least squares to estimate individualized treatment rules. In simulations, we extensively evaluated the performance of the methods in estimating the parameters of the decision rule under different assumptions. The results demonstrate that double robustness is not maintained in data pooling setting and that this can result in bias, whereas the distributed regression provides good performance. We illustrate the methods via an analysis of optimal Warfarin dosing using data from the International Warfarin Consortium.

Predicting the presence of depressive symptoms in the HIV-HCV co-infected population in Canada using supervised machine learning.

BACKGROUND: Depression is common in the human immunodeficiency virus (HIV)-hepatitis C virus (HCV) co-infected population. Demographic, behavioural, and clinical data collected in research settings may be of help in identifying those at risk for clinical depression. We aimed to predict the presence of depressive symptoms indicative of a risk of depression and identify important classification predictors using supervised machine learning. METHODS: We used data from the Canadian Co-infection Cohort, a multicentre prospective cohort, and its associated sub-study on Food Security (FS). The Center for Epidemiologic Studies Depression Scale-10 (CES-D-10) was administered in the FS sub-study; participants were classified as being at risk for clinical depression if scores ≥ 10. We developed two random forest algorithms using the training data (80%) and tenfold cross validation to predict the CES-D-10 classes-1. Full algorithm with all candidate predictors (137 predictors) and 2. Reduced algorithm using a subset of predictors based on expert opinion (46 predictors). We evaluated the algorithm performances in the testing data using area under the receiver operating characteristic curves (AUC) and generated predictor importance plots. RESULTS: We included 1,934 FS sub-study visits from 717 participants who were predominantly male (73%), white (76%), unemployed (73%), and high school educated (52%). At the first visit, median age was 49 years (IQR:43-54) and 53% reported presence of depressive symptoms with CES-D-10 scores ≥ 10. The full algorithm had an AUC of 0.82 (95% CI:0.78-0.86) and the reduced algorithm of 0.76 (95% CI:0.71-0.81). Employment, HIV clinical stage, revenue source, body mass index, and education were the five most important predictors. CONCLUSION: We developed a prediction algorithm that could be instrumental in identifying individuals at risk for depression in the HIV-HCV co-infected population in research settings. Development of such machine learning algorithms using research data with rich predictor information can be useful for retrospective analyses of unanswered questions regarding impact of depressive symptoms on clinical and patient-centred outcomes among vulnerable populations.

Estimating the lagged effect of price discounting: a time-series study on sugar sweetened beverage purchasing in a supermarket.

BACKGROUND: Price discount is an unregulated obesogenic environmental risk factor for the purchasing of unhealthy food, including Sugar Sweetened Beverages (SSB). Sales of price discounted food items are known to increase during the period of discounting. However, the presence and extent of the lagged effect of discounting, a sustained level of sales after discounting ends, is previously unaccounted for. We investigated the presence of the lagged effect of discounting on the sales of five SSB categories, which are soda, fruit juice, sport and energy drink, sugar-sweetened coffee and tea, and sugar-sweetened drinkable yogurt. METHODS: We fitted distributed lag models to weekly volume-standardized sales and percent discounting generated by a supermarket in Montreal, Canada between January 2008 and December 2013, inclusive (n = 311 weeks). RESULTS: While the sales of SSB increased during the period of discounting, there was no evidence of a prominent lagged effect of discounting in four of the five SSB; the exception was sports and energy drinks, where a posterior mean of 28,459 servings (95% credible interval: 2661 to 67,253) of excess sales can be attributed to the lagged effect in the target store during the 6 years study period. CONCLUSION: Our results indicate that studies that do not account for the lagged effect of promotions may not fully capture the effect of price discounting for some food categories.

Mental health services use and depressive symptom scores among gay and bisexual men in Canada.

PURPOSE: To evaluate the association between mental health services (MHS) use and depressive symptom scores among gay and bisexual men (GBM) and compare with heterosexual men in Canada. METHODS: We used data from the 2015-2016 cycles of the Canadian Community Health Survey. Depressive symptoms were assessed using the PHQ-9 questionnaire (prior two weeks). MHS consultations with any licensed mental health professional (prior year) were categorized as 0, 1, 2-11, ≥ 12. We fit linear regression models to quantify the associations between MHS use and PHQ-9 scores, with an interaction term for sexual identity (GBM and heterosexual men). Models were adjusted for socioeconomic and health-related indicators. RESULTS: Among 21,383 men, 97.3% self-identified as heterosexual and 2.7% as GBM. Compared to heterosexual men, GBM used any MHS (21% vs. 10%, p < 0.05) and consulted ≥ 2 health professionals for their mental health (6% vs. 2%, p < 0.05) in the preceding year more frequently. Overall, mean PHQ-9 scores were higher among GBM compared to heterosexual men (3.9 vs. 2.3, p < 0.05). Relative to no consultations, higher MHS use (2-11, ≥ 12 consultations) was associated with higher PHQ-9 scores (1.4-4.9 points higher). Associations between MHS use and PHQ-9 scores did not differ statistically between GBM and heterosexual men. CONCLUSION: Our findings were inconclusive in demonstrating a difference between heterosexual men and GBM for the association between MHS use and PHQ-9 scores. However, GBM consistently had higher average PHQ-9 scores for every category of consultations. Considering the higher use of MHS and higher burden of depressive symptoms among GBM, more research is needed.

Extended Bayesian endemic-epidemic models to incorporate mobility data into COVID-19 forecasting.

Forecasting the number of daily COVID-19 cases is critical in the short-term planning of hospital and other public resources. One potentially important piece of information for forecasting COVID-19 cases is mobile device location data that measure the amount of time an individual spends at home. Endemic-epidemic (EE) time series models are recently proposed autoregressive models where the current mean case count is modelled as a weighted average of past case counts multiplied by an autoregressive rate, plus an endemic component. We extend EE models to include a distributed-lag model in order to investigate the association between mobility and the number of reported COVID-19 cases; we additionally include a weekly first-order random walk to capture additional temporal variation. Further, we introduce a shifted negative binomial weighting scheme for the past counts that is more flexible than previously proposed weighting schemes. We perform inference under a Bayesian framework to incorporate parameter uncertainty into model forecasts. We illustrate our methods using data from four US counties.

La prévision du nombre de cas quotidiens de COVID­19 est cruciale pour la planification à court terme de ressources hospitalières et d'autres ressources publiques. Les données de localisation des téléphones mobiles qui mesurent le temps passé à la maison peuvent constituer un élément d'information important pour prédire les cas de COVID­19. Les modèles de séries chronologiques endémiques­épidémiques sont des modèles auto­régressifs récents où le nombre moyen de cas en cours est modélisé comme une moyenne pondérée du nombre de cas antérieurs multipliée par un taux auto­régressif (reproductif), plus une composante endémique. Les auteurs de ce travail généralisent les modèles endémiques­épidémiques pour y inclure un modèle à décalage distribué, et ce, dans le but de tenir compte du lien entre la mobilité et le nombre de cas de COVID­19 enregistrés. Pour saisir les variations de temps supplémentaires, ils y incorporent une marche hebdomadaire aléatoire d'ordre supérieur. De plus, ils proposent un schéma de pondération binomiale négative décalée pour les dénombrements passés, qui est plus flexible que les schémas de pondération existants. Ils utilisent l'inférence bayésienne afin d'intégrer l'incertitude des paramètres aux prédictions du modèle et ils illustrent les méthodes proposées avec des données provenant de quatre comtés américains.