EUVIMEDSkopri EUVIMED
Open access · CC BY 4.0

Joint modeling of longitudinal and time‐to‐event data for dynamic disease risk prediction using proteomics

Markus Lindén iD, Tea Ammunét, Tommi Välikangas, Laura L Elo iD, Tomi Suomi iD

Protein Science · 2026-06 · 35 (6)

DOI: 10.1002/pro.70621 ↗

At a glance

Journal article in Protein Science, published online on 2026-05-18. Written by Markus Lindén and 4 co-authors. Institution: Turku Bioscience Centre, University of Turku and Åbo Akademi University, Turku, Finland. Major MEDLINE topics: Proteomics, Diabetes Mellitus, Type 1, Proteome. 46 references. The full text is freely available (open access, CC BY 4.0). Funded by: European Research Council, H2020 European Research Council, Academy of Finland.

AstrattSubjectsDettalji biblijografiċiCiteRelated studies

Abstract (original language)

Biomedical studies increasingly incorporate longitudinal data, enabling us to track individual disease processes over time at the molecular level, and to discover associations of the molecular profiles with the outcome of interest, such as the onset of a disease. Despite the potential of statistical methods that jointly model longitudinal and time‐to‐event data, they have not yet been widely adopted in high‐throughput omics studies. Therefore, we evaluated multiple approaches for joint modeling of longitudinal and time‐to‐event data, and we introduce a joint modeling strategy for longitudinal proteomics studies. The focus is on assessing the utility of the methods in predicting the dynamic disease risk of an individual from longitudinal proteome profiles. To benchmark the methods, we used a range of simulated datasets that reflected real proteome profiles with varying complexities. Our results clearly demonstrated the advantages of the longitudinal methods over conventional Cox proportional hazards models with single time point studies. This was further supported by re‐analysis of data from a proteomics study of early type 1 diabetes prediction, where we discovered new early candidate proteins associated with the disease onset that were not detected in the original study.

Subjects

MeSH terms (MEDLINE)

ProteomicsDiabetes Mellitus, Type 1ProteomeHumansProportional Hazards ModelsLongitudinal Studies

Author keywords

joint modellongitudinalrisk predictionsurvival analysistype 1 diabetes

Substances

Proteome

Authors and institutions

  • Turku Bioscience Centre, University of Turku and Åbo Akademi University, Turku, Finland.
  • Institute of Biomedicine, University of Turku, Turku, Finland.

ORCID profiles: Markus Lindén, Laura L Elo, Tomi Suomi

Funding

  • European Research Council
  • H2020 European Research Council
  • Academy of Finland
  • Sigrid Juséliuksen Säätiö
  • Vilho, Yrjö and Kalle Väisälä Foundation
  • Biocenter Finland
  • ELIXIR Finland
  • Research Council of Finland

Cite

APA

Lindén, M., Ammunét, T., Välikangas, T., Elo, L. L., & Suomi, T. (2026). Joint modeling of longitudinal and time‐to‐event data for dynamic disease risk prediction using proteomics. Protein Science, 35(6). https://doi.org/10.1002/pro.70621

Vancouver

Lindén M, Ammunét T, Välikangas T, Elo LL, Suomi T. Joint modeling of longitudinal and time‐to‐event data for dynamic disease risk prediction using proteomics. Protein Science. 2026;35(6). doi:10.1002/pro.70621

BibTeX
@article{Lindn2026,
  author = {Lindén, Markus and Ammunét, Tea and Välikangas, Tommi and Elo, Laura L and Suomi, Tomi},
  title = {Joint modeling of longitudinal and time‐to‐event data for dynamic disease risk prediction using proteomics},
  journal = {Protein Science},
  year = {2026},
  volume = {35},
  number = {6},
  doi = {10.1002/pro.70621}
}
Start for free →