Making predictions from complex longitudinal data, with application to planning monitoring intervals in a national screening programme

M. J. Sweeting*, S. G. Thompson

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

18 Citations (Scopus)

Abstract

When biological or physiological variables change over time, we are often interested in making predictions either of future measurements or of the time taken to reach some threshold value. On the basis of longitudinal data for multiple individuals, we develop Bayesian hierarchical models for making these predictions together with their associated uncertainty. Particular aspects addressed, which include some novel components, are handling curvature in individuals' trends over time, making predictions for both underlying and measured levels, making predictions from a single baseline measurement, making predictions from a series of measurements, allowing flexibility in the error and random-effects distributions, and including covariates. In the context of data on the expansion of abdominal aortic aneurysms over time, where reaching a certain threshold leads to referral for surgery, we discuss the practical application of these models to the planning of monitoring intervals in a national screening programme. Prediction of the time to reach a threshold was too imprecise to be practically useful, and we focus instead on limiting the probability of exceeding the threshold after given time intervals. Although more complex models can be shown to fit the data better, we find that relatively simple models seem to be adequate for planning monitoring intervals.

Original languageEnglish
Pages (from-to)569-586
Number of pages18
JournalJournal of the Royal Statistical Society. Series A: Statistics in Society
Volume175
Issue number2
DOIs
Publication statusPublished - Apr 2012
Externally publishedYes

Keywords

  • Abdominal aortic aneurysm
  • Hierarchical model
  • Monitoring intervals
  • National screening
  • Prediction
  • Simulation

Fingerprint

Dive into the research topics of 'Making predictions from complex longitudinal data, with application to planning monitoring intervals in a national screening programme'. Together they form a unique fingerprint.

Cite this