Dataset Information

FPCA-based method to select optimal sampling schedules that capture between-subject variability in longitudinal studies.

ABSTRACT: A critical component of longitudinal study design involves determining the sampling schedule. Criteria for optimal design often focus on accurate estimation of the mean profile, although capturing the between-subject variance of the longitudinal process is also important since variance patterns may be associated with covariates of interest or predict future outcomes. Existing design approaches have limited applicability when one wishes to optimize sampling schedules to capture between-individual variability. We propose an approach to derive optimal sampling schedules based on functional principal component analysis (FPCA), which separately characterizes the mean and the variability of longitudinal profiles and leads to a parsimonious representation of the temporal pattern of the variability. Simulation studies show that the new design approach performs equally well compared to an existing approach based on parametric mixed model (PMM) when a PMM is adequate for the data, and outperforms the PMM-based approach otherwise. We use the methods to design studies aiming to characterize daily salivary cortisol profiles and identify the optimal days within the menstrual cycle when urinary progesterone should be measured.

SUBMITTER: Wu M

PROVIDER: S-EPMC5677595 | biostudies-literature | 2018 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

FPCA-based method to select optimal sampling schedules that capture between-subject variability in longitudinal studies.

Wu Meihua M Diez-Roux Ana A Raghunathan Trivellore E TE Sánchez Brisa N BN

Biometrics 20170508 1

A critical component of longitudinal study design involves determining the sampling schedule. Criteria for optimal design often focus on accurate estimation of the mean profile, although capturing the between-subject variance of the longitudinal process is also important since variance patterns may be associated with covariates of interest or predict future outcomes. Existing design approaches have limited applicability when one wishes to optimize sampling schedules to capture between-individual ...[more]

PMID: 28482120

Similar Datasets

Project description:Background: Gene expression profiling has been used extensively within breast cancer research. Patient matched transcriptomic studies of tumour samples before and after treatment offer great potential and have been initiated, but tend not to include a control group. Here we examine gene expression changes between patient-matched core biopsies and surgical resection samples in the absence of treatment, to consider sampling methods and tumour heterogeneity. Patients and Methods: Illumina BeadArray technology was used to measure dynamic changes in gene expression from thirty-seven paired baseline and surgically excised breast tumour samples obtained from women receiving no treatment prior to surgery. Results: Patient-matched sample pairs had significantly higher correlations than samples between different individuals, demonstrating that tumour heterogeneity and intra-tumour differences are less prominent than inter-tumour/patient differences. Perhaps surprisingly, consistent changes in gene expression were identified during the diagnosis-surgery interval, despite a lack of treatment. 50 genes were significantly differentially expressed (48 up, 2 down; FDR 0.05) in a manner that appears independent of both subtype and the sampling-interval length. Gene set enrichment analysis using four independent treated datasets has implicated the tumour sampling method as the likely cause of these expression changes which include increases in early growth response genes such as EGR1, 2 and 3 along with DUSP1 and FOS. Our data does not support the idea that there is a significant wounding or immune response. Conclusion: This is the largest cohort of patient-matched transcriptome profiling of tumours from patients receiving no treatment between diagnosis and surgery to date. It has revealed that consistent changes in gene expression do exist between diagnostic core biopsy and the surgical excision sample. We have confirmed these findings in a number of published breast cancer datasets. Ultimately, researchers should be aware of the potential for the tumour sampling method to introduce a confounding factor in future neoadjuvant studies.

Dataset Information

FPCA-based method to select optimal sampling schedules that capture between-subject variability in longitudinal studies.

Publications

FPCA-based method to select optimal sampling schedules that capture between-subject variability in longitudinal studies.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets