Predicting health outcomes from longitudinal health histories is of central importance to healthcare. Observational healthcare databases such as patient diary databases provide a rich resource for patient-level predictive modeling. In this paper, we propose a Bayesian hierarchical vector autoregressive (VAR) model to predict medical and psychological conditions using multivariate time series data. Compared to the existing patient-specific predictive VAR models, our model demonstrated higher accuracy in predicting future observations in terms of both point and interval estimates due to the pooling effect of the hierarchical model specification. In addition, by adopting an elastic-net prior, our model offers greater interpretability about the associations between variables of interest on both the population level and the patient level, as well as between-patient heterogeneity. We apply the model to two examples: 1) predicting substance use craving, negative affect and tobacco use among college students, and 2) predicting functional somatic symptoms and psychological discomforts.

Longitudinal studies of inflammatory biomarkers and depression.

BackgroundGlycemic disorder is closely related to the risk of pancreatic cancer, but previous studies focused on the influence of diabetes. The aim of this meta-analysis was to investigate the influence of prediabetes, an intermediate state between normoglycemia and diabetes, on the risk of pancreatic cancer.MethodsRelevant longitudinal observational studies were identified through a search of Medline, Embase, and Web of Science databases. To minimize the influence of between-study heterogeneity, a randomized-effects model was used to pool the results.ResultsNine cohort studies including 26,444,624 subjects were available for the meta-analysis. Among them, 2,052,986 (7.8%) had prediabetes at baseline, and the participants were followed for a mean duration of 5.9 years. It was found that, compared to people with normoglycemia, those with prediabetes had a higher incidence of pancreatic cancer (risk ratio [RR]: 1.42, 95% confidence interval: 1.36 to 1.49, p