Dataset Information

Modelling of longitudinal data to predict cardiovascular disease risk: a methodological review.

ABSTRACT:

Objective

The identification of methodology for modelling cardiovascular disease (CVD) risk using longitudinal data and risk factor trajectories.

Methods

We screened MEDLINE-Ovid from inception until 3 June 2020. MeSH and text search terms covered three areas: data type, modelling type and disease area including search terms such as "longitudinal", "trajector*" and "cardiovasc*" respectively. Studies were filtered to meet the following inclusion criteria: longitudinal individual patient data in adult patients with ≥3 time-points and a CVD or mortality outcome. Studies were screened and analyzed by one author. Any queries were discussed with the other authors. Comparisons were made between the methods identified looking at assumptions, flexibility and software availability.

Results

From the initial 2601 studies returned by the searches 80 studies were included. Four statistical approaches were identified for modelling the longitudinal data: 3 (4%) studies compared time points with simple statistical tests, 40 (50%) used single-stage approaches, such as including single time points or summary measures in survival models, 29 (36%) used two-stage approaches including an estimated longitudinal parameter in survival models, and 8 (10%) used joint models which modelled the longitudinal and survival data together. The proportion of CVD risk prediction models created using longitudinal data using two-stage and joint models increased over time.

Conclusions

Single stage models are still heavily utilized by many CVD risk prediction studies for modelling longitudinal data. Future studies should fully utilize available longitudinal data when analyzing CVD risk by employing two-stage and joint approaches which can often better utilize the available data.

SUBMITTER: Stevens D

PROVIDER: S-EPMC8684210 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:ObjectivesTo systematically identify and qualitatively review the statistical approaches used in prospective cohort studies of team sports that reported intensive longitudinal data (ILD) (>20 observations per athlete) and examined the relationship between athletic workloads and injuries. Since longitudinal research can be improved by aligning the (1) theoretical model, (2) temporal design and (3) statistical approach, we reviewed the statistical approaches used in these studies to evaluate how closely they aligned these three components.DesignMethodological review.MethodsAfter finding 6 systematic reviews and 1 consensus statement in our systematic search, we extracted 34 original prospective cohort studies of team sports that reported ILD (>20 observations per athlete) and examined the relationship between athletic workloads and injuries. Using Professor Linda Collins' three-part framework of aligning the theoretical model, temporal design and statistical approach, we qualitatively assessed how well the statistical approaches aligned with the intensive longitudinal nature of the data, and with the underlying theoretical model. Finally, we discussed the implications of each statistical approach and provide recommendations for future research.ResultsStatistical methods such as correlations, t-tests and simple linear/logistic regression were commonly used. However, these methods did not adequately address the (1) themes of theoretical models underlying workloads and injury, nor the (2) temporal design challenges (ILD). Although time-to-event analyses (eg, Cox proportional hazards and frailty models) and multilevel modelling are better-suited for ILD, these were used in fewer than a 10% of the studies (n=3).ConclusionsRapidly accelerating availability of ILD is the norm in many fields of healthcare delivery and thus health research. These data present an opportunity to better address research questions, especially when appropriate statistical analyses are chosen.

Project description:ImportanceFormer heavy smokers (ie, those with ≥20 pack-years of smoking) may have higher atherosclerotic cardiovascular disease (ASCVD) risk than never smokers for up to 16 years after smoking cessation. However, the 2013 pooled cohort equations (PCE) do not account for pack-years of smoking and only consider current vs noncurrent smoking status without distinguishing former smokers from never smokers.ObjectiveTo assess the predictive utility of smoking history when added to the PCE using data from 18 400 person examinations among Framingham offspring participants.Design, setting, and participantsThis is a retrospective analysis of prospectively collected data from the Framingham Heart Study, a community-based cohort. Framingham Heart Study offspring cohort participants attending their first examination (1971-1975) who were followed-up through December 2016 were included.ExposuresSelf-reported current/former/never smoking status, pack-years smoked, and years since quitting.Main outcomes and measuresIncident ASCVD (myocardial infarction, fatal/nonfatal ischemic stroke, coronary heart disease death).ResultsOf 3908 patients, there were 358 and 197 events among 1895 men and 2013 women, respectively, with a mean (SD) age of 55 (9.5) years. Ever smoking prevalence was high (6474 men [77%] and 7760 women [78%]), as were median pack-years (men: 39; women: 32 overall person examinations). Four sex-specific ASCVD risk prediction models were built using pooled-repeated Cox proportional hazards regression. The PCEs were was fit in this sample with continuous predictors on their natural scale (ie, not logarithmically transformed) as well as polynomials accounting for nonlinearity and then cumulatively adjusted for former smoking, pack-years, and years since quitting. Models were compared via change in C statistic, continuous net reclassification improvement (NRI[>0]), and relative integrated discrimination improvement (rIDI). Including former smoking status, pack-years, and years since quitting had significant but modest NRI(>0) and rIDI values compared with the PCE with continuous variables on their natural scale in both sexes (men: NRI[>0] = 0.23; rIDI = 0.19; women: NRI[>0] = 0.34, rIDI = 0.11; change in C statistic = 0.01 for both).Conclusions and relevanceFormer smoking, pack-years, and years since quitting significantly improved ASCVD risk prediction in this sample. The Framingham Heart Study offspring cohort is largely composed of non-Hispanic White participants of European ancestry. If results are validated in cohorts of race and ethnicity groups other than White, these variables could be considered for inclusion in future ASCVD risk prediction models.

Project description:The often-used A(C)E model that decomposes phenotypic variance into parts due to additive genetic and environmental influences can be extended to a longitudinal model when the trait has been assessed at multiple occasions. This enables inference about the nature (e.g., genetic or environmental) of the covariance among the different measurement points. In the case that the measurement of the phenotype relies on self-report data (e.g., questionnaire data), often, aggregated scores (e.g., sum-scores) are used as a proxy for the phenotype. However, earlier research based on the univariate ACE model that concerns a single measurement occasion has shown that this can lead to an underestimation of heritability and that instead, one should prefer to model the raw item data by integrating an explicit measurement model into the analysis. This has, however, not been translated to the more complex longitudinal case. In this paper, we first present a latent state twin A(C)E model that combines the genetic twin model with an item response theory (IRT) model as well as its specification in a Bayesian framework. Two simulation studies were conducted to investigate 1) how large the bias is when sum-scores are used in the longitudinal A(C)E model and 2) if using the latent twin model can overcome the potential bias. Results of the first simulation study (e.g., AE model) demonstrated that using a sum-score approach leads to underestimated heritability estimates and biased covariance estimates. Surprisingly, the IRT approach also lead to bias, but to a much lesser degree. The amount of bias increased in the second simulation study (e.g., ACE model) under both frameworks, with the IRT approach still being the less biased approach. Since the bias was less severe under the IRT approach than under the sum-score approach and due to other advantages of latent variable modelling, we still advise researcher to adopt the IRT approach. We further illustrate differences between the traditional sum-score approach and the latent state twin A(C)E model by analyzing data of a two-wave twin study, consisting of the answers of 8,016 twins on a scale developed to measure social attitudes related to conservatism.