Association of ABO blood groups with venous thrombosis recurrence in middle-aged patients: insights from a weighted Cox analysis dedicated to ambispective design.

BACKGROUND: In studies of time-to-events, it is common to collect information about events that occurred before the inclusion in a prospective cohort. When the studied risk factors are independent of time, including both pre- and post-inclusion events in the analyses, generally referred to as relying on an ambispective design, increases the statistical power but may lead to a selection bias. In the field of venous thromboembolism (VT), ABO blood groups have been the subject of extensive research due to their substantial effect on VT risk. However, few studies have investigated their effect on the risk of VT recurrence. Motivated by the study of the association of genetically determined ABO blood groups with VT recurrence, we propose a methodology to include pre-inclusion events in the analysis of ambispective studies while avoiding the selection bias due to mortality. METHODS: This work relies on two independent cohorts of VT patients, the French MARTHA study built on an ambispective design and the Dutch MEGA study built on a standard prospective design. For the analysis of the MARTHA study, a weighted Cox model was developed where weights were defined by the inverse of the survival probability at the time of data collection about the events. Thanks to the collection of information on the vital status of patients, we could estimate the survival probabilities using a delayed-entry Cox model on the death risk. Finally, results obtained in both studies were then meta-analysed. RESULTS: In the combined sample totalling 2,752 patients including 993 recurrences, the A1 blood group has an increased risk (Hazard Ratio (HR) of 1.18, p = 4.2 × 10-3) compared with the O1 group, homogeneously in MARTHA and in MEGA. The same trend (HR = 1.19, p = 0.06) was observed for the less frequent A2 group. CONCLUSION: The proposed methodology increases the power of studies relying on an ambispective design which is frequent in epidemiologic studies about recurrent events. This approach allowed to clarify the association of ABO blood groups with the risk of VT recurrence. Besides, this methodology has an immediate field of application in the context of genome wide association studies.

Impact of interventions scenarios targeting three main vascular risk factors on the future burden of dementia in France.

The epidemiological and societal burden of dementia is expected to increase in the coming decades due to the world population aging. In this context, the evaluation of the potential impact of intervention scenarios aiming at reducing the prevalence of dementia risk factors is an active area of research. However, such studies must account for the associated changes in mortality and the dependence between the risk factors. Using micro-simulations, this study aims to estimate the changes in dementia burden in France in 2040 according to intervention scenarios targeting the prevention or treatment of hypertension, diabetes and physical inactivity. Accounting for their communality and their effects on mortality, the results show that the disappearance of hypertension, diabetes and physical inactivity in France in 2020 could decrease dementia prevalence by 33% among men and 26% among women in 2040 and increase the life expectancy without dementia at age 65 by 3.4 years (men) and 2.6 years (women). Among the three factors, the prevention of hypertension would be the most efficient. These projections rely on current estimates of the risk of dementia and death associated with risk factors. Thanks to the R package developed they could be refined for different countries or different interventions and updated with new estimates.

Five-Year Dynamic Prediction of Dementia Using Repeated Measures of Cognitive Tests and a Dependency Scale.

The progression of dementia prevalence over the years and the lack of efficient treatments to stop or reverse the cognitive decline make dementia a major public health challenge in the developed world. Identifying people at high risk of developing dementia could improve the treatment of these patients and help select the target population for preventive clinical trials. We used joint modeling to build a dynamic prediction tool of dementia based on the change over time of 2 neurocognitive tests (the Mini-Mental State Examination and the Isaacs Set Tests) as well as an autonomy scale (the Instrumental Activities of Daily Living). The model was estimated with data from the French cohort Personnes Agées QUID (1988-2015) and validated both by cross-validation and externally with data from the French Three City cohort (1999-2018). We evaluated its predictive abilities through area under the receiver operating characteristics curve and Brier score, accounting for right censoring and competing risk of death, and obtained an average area under the curve value of 0.95 for the risk of dementia in the next 5 or 10 years. This tool is able to discriminate a high-risk group of people from the rest of the population. This could be of help in clinical practice and research.

How Selection Over Time Contributes to the Inconsistency of the Association Between Sex/Gender and Cognitive Decline Across Cognitive Aging Cohorts.

The association between sex/gender and aging-related cognitive decline remains poorly understood because of inconsistencies in findings. Such heterogeneity could be attributable to the cognitive functions studied and study population characteristics, but also to differential selection by dropout and death between men and women. We aimed to evaluate the impact of selection by dropout and death on the association between sex/gender and cognitive decline. We first compared the statistical methods most frequently used for longitudinal data, targeting either population estimands (marginal models fitted by generalized estimating equations) or subject-specific estimands (mixed/joint models fitted by likelihood maximization) in 8 studies of aging: 6 population-based studies (the Advanced Cognitive Training for Independent and Vital Elderly (ACTIVE) Study (1996-2009), Personnes Âgées QUID (PAQUID; 1988-2014), the Reasons for Geographic and Racial Differences in Stroke (REGARDS) Study (2003-2016), the Three-City Study (Bordeaux only; 1999-2016), the Washington Heights-Inwood Community Aging Project (WHICAP; 1992-2017), and the Whitehall II Study (2007-2016)) and 2 clinic-based studies (the Alzheimer's Disease Neuroimaging Initiative (ADNI; 2004-2017) and a nationwide French cohort study, MEMENTO (2011-2016)). We illustrate differences in the estimands of the association between sex/gender and cognitive decline in selected examples and highlight the critical role of differential selection by dropout and death. Using the same estimand, we then contrast the sex/gender-cognitive decline associations across cohorts and cognitive measures suggesting a residual differential sex/gender association depending on the targeted cognitive measure (memory or animal fluency) and the initial cohort selection. We recommend focusing on subject-specific estimands in the living population for assessing sex/gender differences while handling differential selection over time.

Predicting Progression to Advanced Age-Related Macular Degeneration from Clinical, Genetic, and Lifestyle Factors Using Machine Learning.

PURPOSE: Current prediction models for advanced age-related macular degeneration (AMD) are based on a restrictive set of risk factors. The objective of this study was to develop a comprehensive prediction model applying a machine learning algorithm allowing selection of the most predictive risk factors automatically. DESIGN: Two population-based cohort studies. PARTICIPANTS: The Rotterdam Study I (RS-I; training set) included 3838 participants 55 years of age or older, with a median follow-up period of 10.8 years, and 108 incident cases of advanced AMD. The Antioxydants, Lipids Essentiels, Nutrition et Maladies Oculaires (ALIENOR) study (test set) included 362 participants 73 years of age or older, with a median follow-up period of 6.5 years, and 33 incident cases of advanced AMD. METHODS: The prediction model used the bootstrap least absolute shrinkage and selection operator (LASSO) method for survival analysis to select the best predictors of incident advanced AMD in the training set. Predictive performance of the model was assessed using the area under the receiver operating characteristic curve (AUC). MAIN OUTCOME MEASURES: Incident advanced AMD (atrophic, neovascular, or both), based on standardized interpretation of retinal photographs. RESULTS: The prediction model retained (1) age, (2) a combination of phenotypic predictors (based on the presence of intermediate drusen, hyperpigmentation in one or both eyes, and Age-Related Eye Disease Study simplified score), (3) a summary genetic risk score based on 49 single nucleotide polymorphisms, (4) smoking, (5) diet quality, (6) education, and (7) pulse pressure. The cross-validated AUC estimation in RS-I was 0.92 (95% confidence interval [CI], 0.88-0.97) at 5 years, 0.92 (95% CI, 0.90-0.95) at 10 years, and 0.91 (95% CI, 0.88-0.94) at 15 years. In ALIENOR, the AUC reached 0.92 at 5 years (95% CI, 0.87-0.98). In terms of calibration, the model tended to underestimate the cumulative incidence of advanced AMD for the high-risk groups, especially in ALIENOR. CONCLUSIONS: This prediction model reached high discrimination abilities, paving the way toward making precision medicine for AMD patients a reality in the near future.

Benefits of dimension reduction in penalized regression methods for high-dimensional grouped data: a case study in low sample size.

MOTIVATION: In some prediction analyses, predictors have a natural grouping structure and selecting predictors accounting for this additional information could be more effective for predicting the outcome accurately. Moreover, in a high dimension low sample size framework, obtaining a good predictive model becomes very challenging. The objective of this work was to investigate the benefits of dimension reduction in penalized regression methods, in terms of prediction performance and variable selection consistency, in high dimension low sample size data. Using two real datasets, we compared the performances of lasso, elastic net, group lasso, sparse group lasso, sparse partial least squares (PLS), group PLS and sparse group PLS. RESULTS: Considering dimension reduction in penalized regression methods improved the prediction accuracy. The sparse group PLS reached the lowest prediction error while consistently selecting a few predictors from a single group. AVAILABILITY AND IMPLEMENTATION: R codes for the prediction methods are freely available at https://github.com/SoufianeAjana/Blisar. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Dynamic modeling of multivariate dimensions and their temporal relationships using latent processes: Application to Alzheimer's disease.

Alzheimer's disease gradually affects several components including the cerebral dimension with brain atrophies, the cognitive dimension with a decline in various functions, and the functional dimension with impairment in the daily living activities. Understanding how such dimensions interconnect is crucial for Alzheimer's disease research. However, it requires to simultaneously capture the dynamic and multidimensional aspects and to explore temporal relationships between dimensions. We propose an original dynamic structural model that accounts for all these features. The model defines dimensions as latent processes and combines a multivariate linear mixed model and a system of difference equations to model trajectories and temporal relationships between latent processes in finely discrete time. Dimensions are simultaneously related to their observed (possibly multivariate) markers through nonlinear equations of observation. Parameters are estimated in the maximum likelihood framework enjoying a closed form for the likelihood. We demonstrate in a simulation study that this dynamic model in discrete time benefits the same causal interpretation of temporal relationships as models defined in continuous time as long as the discretization step remains small. The model is then applied to the data of the Alzheimer's Disease Neuroimaging Initiative. Three longitudinal dimensions (cerebral anatomy, cognitive ability, and functional autonomy) measured by six markers are analyzed, and their temporal structure is contrasted between different clinical stages of Alzheimer's disease.

Excess cumulative incidence estimation for matched cohort survival studies.

We suggest a regression approach to estimate the excess cumulative incidence function (CIF) when matched data are available. In a competing risk setting, we define the excess risk as the difference between the CIF in the exposed group and the background CIF observed in the unexposed group. We show that the excess risk can be estimated through an extended binomial regression model that actively uses the matched structure of the data, avoiding further estimation of both the exposed and the unexposed CIFs. The method naturally deals with two time scales, age and time since exposure and simplifies how to deal with the left truncation on the age time-scale. The model makes it easy to predict individual excess risk scenarios and allows for a direct interpretation of the covariate effects on the cumulative incidence scale. After introducing the model and some theory to justify the approach, we show via simulations that our model works well in practice. We conclude by applying the excess risk model to data from the ALiCCS study to investigate the excess risk of late events in childhood cancer survivors.

Long-term risk of hip or forearm fractures in older occasional users of benzodiazepines.

AIMS: This article sought to study the association between patterns of benzodiazepine (BZD) use and the risk of hip and forearm fractures in people aged 50 and 75 years or more. METHODS: In a representative cohort of the French National Health Insurance Fund of individuals aged 50 years or older (n = 106 437), we followed up BZD dispensing (reflecting their patterns of use) and the most frequent fall-related fractures (hip and forearm) for 8 years. We used joint latent class models to simultaneously identify BZD dispensing trajectories and the risk of fractures in the entire cohort and in those 75 years or older). We used a survival model to estimate the adjusted hazard ratios (aHRs) between these trajectories and the risk of fractures. RESULTS: In the entire cohort, we identified 5 BZD trajectories: non-users (76.7% of the cohort); occasional users (15.2%); decreasing users (2.6%); late increasing users (3.0%); and early increasing users (2.4%). Compared with non-users, fracture risk was not increased in either occasional users (aHR = 0.99, 95% confidence interval [CI] 0.99-1.00) or in decreasing users (aHR = 0.90, 95% CI 0.74-1.08). It was significantly higher in early increasing users (aHR = 1.86, 95% CI 1.62-2.14) and in late increasing users (aHR = 1.39, 95% CI 1.15-1.60). We observed similar trajectories and risk levels in the people older than 75 years. CONCLUSION: Occasional BZD use, which is compatible with current recommendations, was not associated with an excess risk of the most frequent fall-related fractures in people older than 50 or 75 years.

A hypothesis testing procedure for random changepoint mixed models.

In biomedical research, random changepoint mixed models are used to take into account an individual breakpoint in a biomarker trajectory. This may be observed in the cognitive decline measured by psychometric tests in the prediagnosis phase of Alzheimer's disease. The existence, intensity and duration of this accelerated decline can depend on individual characteristics. The main objective of our work is to propose inferential methods to assess the existence of this phase of accelerated decline, ie, the existence of a random changepoint. To do so, we use a mixed model with two linear phases and test the nullity of the parameter measuring the difference of slopes between the two phases. Because we face the issue of nuisance parameters being unidentifiable under the null hypothesis, the supremum of the classic score test statistic on these parameters is used. The asymptotic distribution of the supremum under the null is approached with a perturbation method based on the multiplier bootstrap. The performance of our testing procedure is assessed via simulations and the test is applied to the French cohort PAQUID of elderly subjects to study the shape of the prediagnosis decline according to educational level. The test is significant for both educational levels and the estimated trajectories confirmed that educational level is a good marker for cognitive reserve.

Temporal Trends in the Level and Decline of Cognition and Disability in an Elderly Population: The PAQUID Study.

In line with declining trends in dementia incidence, we compared the cognitive and functional evolution of 2 "generations" of elderly individuals aged 78-88 years, who were included 10 years apart in the French Personnes Agées Quid cohort (n = 612 in 1991-1992 and n = 628 in 2001-2002) and followed-up for 12 years with assessments of cognition and disability. The impact of specific risk factors on this evolution was evaluated. Differences between the generations in baseline levels and decline over time were estimated using a joint model to account for differential attrition. Compared with the first generation, the second generation had higher performances at baseline on 4 cognitive tests (from P < 0.005). Differences in global cognition, verbal fluency, and processing speed, but not in working memory, were mostly explained by improvement in educational level. The second generation also exhibited less cognitive decline in verbal fluency and working memory. Progression of disability was less over the follow-up period for the second generation than for the first. The cognitive state of this elderly population improved, partially due to improvements in educational level.

Projections of prevalence, lifetime risk, and life expectancy of Parkinson's disease (2010-2030) in France.

BACKGROUND: Previous studies on the number of Parkinson's disease (PD) patients in the future based on projections of population size underestimated PD burden because they did not take into account the improvement of life expectancy over time. OBJECTIVE: The objective of this study was to assess PD progression from 2010 to 2030 in France in terms of prevalent patient numbers, prevalence rates, lifetime risk, and life expectancy with PD, accounting for projections of overall mortality and increased risk of death of PD patients. METHODS: To provide projections of PD burden, we applied a multistate approach considering age and calendar time to incidence and prevalence rates of PD (France 2010) based on drug claims and national demographic data. RESULTS: The number of PD patients will increase by ∼65% between 2010 (n = 155,000) and 2030 (n ∼ 260,000), mainly for individuals older than 65 years; the prevalence rate of PD after age 45 will increase from 0.59% in 2010 to ∼0.80% in 2030. We project an extension of ∼3 years of the life expectancy of PD patients at 65 years between 2010 (women, 14.8 years; men, 13.0 years) and 2030 (women, 17.8 years; men, 16.1 years), and a relative increase of about 10% of the lifetime risk of PD at 45 years between 2010 (women, 5.5%; men, 6.0%) and 2030 (women, 6.3%; men, 7.4%). CONCLUSIONS: The number of PD patients is predicted to grow substantially in future years as a consequence of population aging and life expectancy improvement. The assessment of the future PD burden is an important step for planning resources needed for patient care in aging societies. © 2018 International Parkinson and Movement Disorder Society.

Projections of health indicators for chronic disease under a semi-Markov assumption.

Chronic diseases are a growing public health problem due to the population aging. Their economic, social and demographic burden will worsen in years to come. Up to now, the method used to provide projections and assess the future disease burden makes a non-homogeneous Markov assumption in an illness-death model. Both age and calendar year have been taken into account in all parameter estimations, but the time spent with the disease was not considered. This work develops the method with a semi-Markov assumption to model mortality among the diseased and considering the time spent with the disease. The method is applied to estimate several health indicators for dementia in France in 2030. We find that mortality among the individuals with dementia depends on age, calendar year and disease duration, and it is greater for men than for women at all ages. The projections for 2030 suggest a 27% increase of the number of dementia cases. The model proposed in this work has flexible assumptions that make it adaptable to provide projections for various diseases.

A Simulation Platform for Quantifying Survival Bias: An Application to Research on Determinants of Cognitive Decline.

Bias due to selective mortality is a potential concern in many studies and is especially relevant in cognitive aging research because cognitive impairment strongly predicts subsequent mortality. Biased estimation of the effect of an exposure on rate of cognitive decline can occur when mortality is a common effect of exposure and an unmeasured determinant of cognitive decline and in similar settings. This potential is often represented as collider-stratification bias in directed acyclic graphs, but it is difficult to anticipate the magnitude of bias. In this paper, we present a flexible simulation platform with which to quantify the expected bias in longitudinal studies of determinants of cognitive decline. We evaluated potential survival bias in naive analyses under several selective survival scenarios, assuming that exposure had no effect on cognitive decline for anyone in the population. Compared with the situation with no collider bias, the magnitude of bias was higher when exposure and an unmeasured determinant of cognitive decline interacted on the hazard ratio scale to influence mortality or when both exposure and rate of cognitive decline influenced mortality. Bias was, as expected, larger in high-mortality situations. This simulation platform provides a flexible tool for evaluating biases in studies with high mortality, as is common in cognitive aging research.

Joint latent class model for longitudinal data and interval-censored semi-competing events: Application to dementia.

Joint models are used in ageing studies to investigate the association between longitudinal markers and a time-to-event, and have been extended to multiple markers and/or competing risks. The competing risk of death must be considered in the elderly because death and dementia have common risk factors. Moreover, in cohort studies, time-to-dementia is interval-censored since dementia is assessed intermittently. So subjects can develop dementia and die between two visits without being diagnosed. To study predementia cognitive decline, we propose a joint latent class model combining a (possibly multivariate) mixed model and an illness-death model handling both interval censoring (by accounting for a possible unobserved transition to dementia) and semi-competing risks. Parameters are estimated by maximum-likelihood handling interval censoring. The correlation between the marker and the times-to-events is captured by latent classes, homogeneous sub-groups with specific risks of death, dementia, and profiles of cognitive decline. We propose Markovian and semi-Markovian versions. Both approaches are compared to a joint latent-class model for competing risks through a simulation study, and applied in a prospective cohort study of cerebral and functional ageing to distinguish different profiles of cognitive decline associated with risks of dementia and death. The comparison highlights that among subjects with dementia, mortality depends more on age than on duration of dementia. This model distinguishes the so-called terminal predeath decline (among healthy subjects) from the predementia decline.

Joint modeling of repeated multivariate cognitive measures and competing risks of dementia and death: a latent process and latent class approach.

Joint models initially dedicated to a single longitudinal marker and a single time-to-event need to be extended to account for the rich longitudinal data of cohort studies. Multiple causes of clinical progression are indeed usually observed, and multiple longitudinal markers are collected when the true latent trait of interest is hard to capture (e.g., quality of life, functional dependency, and cognitive level). These multivariate and longitudinal data also usually have nonstandard distributions (discrete, asymmetric, bounded, etc.). We propose a joint model based on a latent process and latent classes to analyze simultaneously such multiple longitudinal markers of different natures, and multiple causes of progression. A latent process model describes the latent trait of interest and links it to the observed longitudinal outcomes using flexible measurement models adapted to different types of data, and a latent class structure links the longitudinal and cause-specific survival models. The joint model is estimated in the maximum likelihood framework. A score test is developed to evaluate the assumption of conditional independence of the longitudinal markers and each cause of progression given the latent classes. In addition, individual dynamic cumulative incidences of each cause of progression based on the repeated marker data are derived. The methodology is validated in a simulation study and applied on real data about cognitive aging obtained from a large population-based study. The aim is to predict the risk of dementia by accounting for the competing death according to the profiles of semantic memory measured by two asymmetric psychometric tests.

Joint modelling of longitudinal and multi-state processes: application to clinical progressions in prostate cancer.

Joint modelling of longitudinal and survival data is increasingly used in clinical trials on cancer. In prostate cancer for example, these models permit to account for the link between longitudinal measures of prostate-specific antigen (PSA) and time of clinical recurrence when studying the risk of relapse. In practice, multiple types of relapse may occur successively. Distinguishing these transitions between health states would allow to evaluate, for example, how PSA trajectory and classical covariates impact the risk of dying after a distant recurrence post-radiotherapy, or to predict the risk of one specific type of clinical recurrence post-radiotherapy, from the PSA history. In this context, we present a joint model for a longitudinal process and a multi-state process, which is divided into two sub-models: a linear mixed sub-model for longitudinal data and a multi-state sub-model with proportional hazards for transition times, both linked by a function of shared random effects. Parameters of this joint multi-state model are estimated within the maximum likelihood framework using an EM algorithm coupled with a quasi-Newton algorithm in case of slow convergence. It is implemented under R, by combining and extending mstate and JM packages. The estimation program is validated by simulations and applied on pooled data from two cohorts of men with localized prostate cancer. Thanks to the classical covariates available at baseline and the repeated PSA measurements, we are able to assess the biomarker's trajectory, define the risks of transitions between health states and quantify the impact of the PSA dynamics on each transition intensity. Copyright © 2016 John Wiley & Sons, Ltd.

Trends in dementia incidence: Evolution over a 10-year period in France.

INTRODUCTION: Few recent studies have suggested declining trends in dementia frequency. French cohorts with long follow-up allowed us to explore incidence evolution trends. METHODS: Two different populations of subjects aged ≥65 years included in 1988-1989 (n = 1469) and 1999-2000 (n = 2104) were followed up over 10 years, with systematic assessment for cognition and dementia. Multistates illness-death models were used to compare dementia incidence using both clinical and algorithmic diagnoses. RESULTS: Using the algorithmic diagnosis, incidence declined significantly overall and for women (age-adjusted hazard ratio [HR] = 0.62; confidence interval (CI) = 0.48-0.80 for women between the two populations). Differences in education, vascular factors, and depression accounted only to some extent for this reduction (women full-adjusted HR = 0.73; CI = 0.57-0.95). No significant decreasing trends were found for men or when using the clinical diagnosis for either sex. DISCUSSION: Our study provides further support for a decrease in dementia incidence in women using algorithmic diagnosis. Changes in diagnostic boundaries mask this reduction.

Quantifying and comparing dynamic predictive accuracy of joint models for longitudinal marker and time-to-event in presence of censoring and competing risks.

Thanks to the growing interest in personalized medicine, joint modeling of longitudinal marker and time-to-event data has recently started to be used to derive dynamic individual risk predictions. Individual predictions are called dynamic because they are updated when information on the subject's health profile grows with time. We focus in this work on statistical methods for quantifying and comparing dynamic predictive accuracy of this kind of prognostic models, accounting for right censoring and possibly competing events. Dynamic area under the ROC curve (AUC) and Brier Score (BS) are used to quantify predictive accuracy. Nonparametric inverse probability of censoring weighting is used to estimate dynamic curves of AUC and BS as functions of the time at which predictions are made. Asymptotic results are established and both pointwise confidence intervals and simultaneous confidence bands are derived. Tests are also proposed to compare the dynamic prediction accuracy curves of two prognostic models. The finite sample behavior of the inference procedures is assessed via simulations. We apply the proposed methodology to compare various prediction models using repeated measures of two psychometric tests to predict dementia in the elderly, accounting for the competing risk of death. Models are estimated on the French Paquid cohort and predictive accuracies are evaluated and compared on the French Three-City cohort.