Missing data in longitudinal studies: Comparison of multiple imputation methods in a real clinical setting

Longitudinal profiling and tracking stability in the Singapore study of macro-angiopathy and microvascular reactivity in type 2 diabetes cohort

INTRODUCTION

The Singapore Study of Macro-Angiopathy and microvascular Reactivity in Type 2 Diabetes (SMART2D) is a prospective cohort study which was started in 2011 to investigate the effect of risk factors on vascular function and diabetes-related complications in Asians. We aimed to compare the longitudinal change in risk factors by accounting for batch effect and assess the tracking stability of risk factors over time in patients recruited for SMART2D. In this study, we (1) described batch effect and its extent across a heterogenous range of longitudinal data parameters; (2) mitigated batch effect through statistical approach; and (3) assessed the tracking stability of the risk factors over time.

METHODS

A total of 2258 patients with type 2 diabetes mellitus (T2DM) were recruited at baseline. The study adopted a three-wave longitudinal design with intervals of 3 years between consecutive waves. The changes in a few selected risk factors were assessed after calibration, assuming patients with similar demographic and anthropometry profile had similar physiology. The tracking pattern of the risk factors was determined with stability coefficients derived from generalised estimating equations.

RESULTS

The medians of the longitudinal differences in risk factors between the waves were mostly modest at <10%. Larger increases in augmentation index (AI), aortic systolic blood pressure (BP) and aortic mean BP were consistently observed after calibration. The medians of the longitudinal differences in AI, aortic systolic BP and aortic mean BP between the waves were <2% before calibration, but increased slightly to <5% after calibration. Most of the risk factors had moderate to high tracking stability. Muscle mass and serum creatinine were among those with relatively high tracking stability.

CONCLUSIONS

The longitudinal differences in parameters between the waves were overall modest after calibration, suggesting that calibration may attenuate longitudinal differences inflated by non-biological factors such as systematic drift due to batch effect. Changes of the hemodynamic parameters are robust over time and not entirely attributable to age. Our study also demonstrated moderate to high tracking stability for most of the parameters.

Pelvic floor symptoms from first pregnancy up to 8 years after the first delivery: a longitudinal study

BACKGROUND

Despite the strong association between vaginal childbirth and pelvic floor dysfunction, genetic factors, pregnancy, advancing age, and lifestyle also play a role. The pelvic floor undergoes substantial changes during pregnancy which may contribute to pelvic floor dysfunction. On the other hand, these changes may be favorable to allow for vaginal delivery. However, there is a lack of studies assessing pelvic floor symptoms over time according to delivery mode, which includes women prior to delivery.

OBJECTIVE

The aim of this study was to describe urinary incontinence, vaginal symptoms, and bowel control symptoms from 21 weeks of gestation in the first pregnancy and up to 8 years after the first delivery, stratified by delivery mode.

STUDY DESIGN

This is a longitudinal observational cohort study. 300 nulliparous women were recruited during their first pregnancy. Pelvic floor symptoms were assessed at 21 and 37 weeks of gestation, and 6 weeks, 6 months, 12 months and 8 years after first delivery using the International Consultation on Incontinence Questionnaire (ICIQ) modules: the urinary incontinence sum score; the weighted vaginal symptom sum score; the vaginal-associated quality of life score; the bowel control sum score; and the bowel-associated quality of life sum score. Delivery mode at first delivery defined delivery groups as: normal vaginal, operative vaginal and cesarean delivery. A linear mixed model analysis was used to assess symptom scores over time and to assess the differences in symptom scores between the delivery groups.

RESULTS

Of the 300 women included in the study, of which 193 attended the 8-year follow-up. Pelvic floor symptoms differed in women with vaginal and cesarean delivery. The symptom scores showed a non-linear statistically significant trend. In women, who delivered vaginally, there was an increase of urinary incontinence and vaginal symptom scores already during pregnancy. In women, who later delivered by cesarean, there was a decrease of symptoms scores during pregnancy, and overall lower symptom scores compared to women with vaginal delivery until 12 months after first delivery. Pelvic floor symptoms scores increased from 12 months to 8 years after the first delivery and exceeded pregnancy levels in all delivery groups, however overall symptom scores were low. Differences between delivery groups were not statistically significant.

CONCLUSION

Pelvic floor symptoms differed in women with vaginal and cesarean delivery from the first pregnancy up to 8 years after the first delivery. These differences were recognizable already prior to first delivery.

Longitudinal Studies 1: Determinants of Risk

Longitudinal or observational study designs are important methodologies to investigate potential associations that may not be amenable to randomized controlled trials. In many cases, they may be performed using existing data and are often cost-effective ways of addressing important questions. The major disadvantage of observational studies is the potential for bias. The absence of randomization means that one can never be certain that unknown confounders are present, and specific studies designs have their own inherent forms of bias. Careful study design may minimize bias. Establishing casual association based on observational methods requires due consideration of the quality of the individual study and knowledge of their limitations.