Improving interpretation of latent class models for diagnostic tests: distinguishing target condition from measurands using directed acyclic graphs
Biometrics · 07.10.2026 · 82 (4)
DOI: 10.1093/biomtc/ujag185 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biometrics, online erschienen am 06.11.2026. Verfasst von Nandini Dendukuri und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medicine, McGill University, Montreal QC H4A 3J1, Canada. Hauptthemen laut MEDLINE: Latent Class Analysis, Diagnostic Tests, Routine, Models, Statistical. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: CIHR, Canadian Institutes of Health Research.
Abstract (Originalsprache)
In the absence of a perfect diagnostic test for a target condition, one or more imperfect tests may be used to arrive at a clinical diagnosis. Latent class analysis can be used to model data from imperfect tests with the objective of estimating test accuracy and target condition prevalence. Such models typically assume there are 2 latent classes underlying the observed data—target condition positive and target condition negative. However, as we illustrate, this would be an oversimplification when any of the observed tests has a measurand that is different from the target condition. We show how a directed acyclic graph can be used to illustrate the relationships between the relevant variables—the observed imperfect test results, their latent measurands, the latent target condition, covariates affecting observed or latent variables, and sources of conditional dependence. We then show how to determine the underlying latent classes and their labels. Finally, we examine how consideration of the measurand of each test impacts the likelihood and identifiability of the latent class model. Using simulation studies, we show how ignoring measurands, which are distinct from the target condition, can lead to mislabeling of the latent classes. We illustrate the value of the proposed approach by re-analyzing 2 datasets used in previously published latent class analyses of tests for pediatric tuberculosis and leptospirosis.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Medicine, McGill University, Montreal QC H4A 3J1, Canada.
- Centre for Outcomes Research and Evaluation (CORE), Research Institute - McGill University Health Centre (RI-MUHC), Montreal QC H4A 3S9, Canada.
- Department of Paediatrics, Oxford Vaccine Group, University of Oxford, Oxford OX3 9DU, UK.
- Department of Paediatrics, Maastricht University Medical Center, MosaKids Children's Hospital, Maastricht 6229 HX, The Netherlands.
- J. D. Maclean Centre for Tropical Medicine, McGill University Health Centre, Montreal QC H4A 3J1, Canada.
- Department of Statistics, University of British Columbia, Vancouver BC V6T 1Z4, Canada.
ORCID-Profile: Michael Libman, Paul Gustafson
Förderung
- CIHR
- Canadian Institutes of Health Research
Zitieren
APA
Dendukuri, N., Schiller, I., Bijker, E. M., Libman, M., Gustafson, P., Bossuyt, P. M., & Merckx, J. (2026). Improving interpretation of latent class models for diagnostic tests: distinguishing target condition from measurands using directed acyclic graphs. Biometrics, 82(4). https://doi.org/10.1093/biomtc/ujag185
Vancouver
Dendukuri N, Schiller I, Bijker EM, Libman M, Gustafson P, Bossuyt PM, et al. Improving interpretation of latent class models for diagnostic tests: distinguishing target condition from measurands using directed acyclic graphs. Biometrics. 2026;82(4). doi:10.1093/biomtc/ujag185
BibTeX
@article{Dendukuri2026,
author = {Dendukuri, Nandini and Schiller, Ian and Bijker, Else Margreet and Libman, Michael and Gustafson, Paul and Bossuyt, Patrick M and Merckx, Joanna},
title = {Improving interpretation of latent class models for diagnostic tests: distinguishing target condition from measurands using directed acyclic graphs},
journal = {Biometrics},
year = {2026},
volume = {82},
number = {4},
doi = {10.1093/biomtc/ujag185}
}
EUVIMED