Risk estimation and dynamic prediction using discrete-time joint models for longitudinal and multistate data with interval and state censoring
(2026) In Biostatistics (Oxford, England) 27(1).- Abstract
This paper presents a joint model of multivariate longitudinal data and multistate data with application to modeling and predicting autoantibody development in The Environmental Determinants of Diabetes in the Young (TEDDY) study. The model quantifies the risks of state transitions based on observed time-varying and non-time-varying risk factors. Based on the estimated model, a dynamic prediction approach is suggested to predict future state occupation probabilities using historical data. The proposed method can handle uncertainties in the observed data, due to measurement errors in the observed longitudinal data and interval censoring or missing information in the observed multistate data. For evaluating the predictions by the proposed... (More)
This paper presents a joint model of multivariate longitudinal data and multistate data with application to modeling and predicting autoantibody development in The Environmental Determinants of Diabetes in the Young (TEDDY) study. The model quantifies the risks of state transitions based on observed time-varying and non-time-varying risk factors. Based on the estimated model, a dynamic prediction approach is suggested to predict future state occupation probabilities using historical data. The proposed method can handle uncertainties in the observed data, due to measurement errors in the observed longitudinal data and interval censoring or missing information in the observed multistate data. For evaluating the predictions by the proposed approach, some performance metrics and their estimation are discussed. The proposed method is evaluated by some simulation studies. It is discussed in detail how this method can be used in analyzing the TEDDY data by properly handling the missing information and predicting future disease status using the proposed dynamic prediction algorithm.
(Less)
- author
- You, Lu
; Salami, Falastin
LU
; Törn, Carina
LU
; Lernmark, Åke
LU
; Vehik, Kendra
LU
; Liu, Xiang
; Qiu, Peihua
and Tamura, Roy
- organization
- publishing date
- 2026-01-20
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Humans, Models, Statistical, Longitudinal Studies, Prediction Algorithms, Data Interpretation, Statistical, Risk Assessment/methods, Predictive Learning Models, Biostatistics/methods
- in
- Biostatistics (Oxford, England)
- volume
- 27
- issue
- 1
- publisher
- Oxford University Press
- external identifiers
-
- pmid:42410993
- ISSN
- 1468-4357
- DOI
- 10.1093/biostatistics/kxag018
- language
- English
- LU publication?
- yes
- additional info
- © The Author(s) 2026. Published by Oxford University Press.
- id
- 5e572304-d3ef-4f14-a274-608ad774a44c
- date added to LUP
- 2026-07-12 00:35:59
- date last changed
- 2026-07-13 09:07:31
@article{5e572304-d3ef-4f14-a274-608ad774a44c,
abstract = {{<p>This paper presents a joint model of multivariate longitudinal data and multistate data with application to modeling and predicting autoantibody development in The Environmental Determinants of Diabetes in the Young (TEDDY) study. The model quantifies the risks of state transitions based on observed time-varying and non-time-varying risk factors. Based on the estimated model, a dynamic prediction approach is suggested to predict future state occupation probabilities using historical data. The proposed method can handle uncertainties in the observed data, due to measurement errors in the observed longitudinal data and interval censoring or missing information in the observed multistate data. For evaluating the predictions by the proposed approach, some performance metrics and their estimation are discussed. The proposed method is evaluated by some simulation studies. It is discussed in detail how this method can be used in analyzing the TEDDY data by properly handling the missing information and predicting future disease status using the proposed dynamic prediction algorithm.</p>}},
author = {{You, Lu and Salami, Falastin and Törn, Carina and Lernmark, Åke and Vehik, Kendra and Liu, Xiang and Qiu, Peihua and Tamura, Roy}},
issn = {{1468-4357}},
keywords = {{Humans; Models, Statistical; Longitudinal Studies; Prediction Algorithms; Data Interpretation, Statistical; Risk Assessment/methods; Predictive Learning Models; Biostatistics/methods}},
language = {{eng}},
month = {{01}},
number = {{1}},
publisher = {{Oxford University Press}},
series = {{Biostatistics (Oxford, England)}},
title = {{Risk estimation and dynamic prediction using discrete-time joint models for longitudinal and multistate data with interval and state censoring}},
url = {{http://dx.doi.org/10.1093/biostatistics/kxag018}},
doi = {{10.1093/biostatistics/kxag018}},
volume = {{27}},
year = {{2026}},
}