Latent transition analysis for longitudinal studies of post-acute infection syndromes

Post-Acute Infectious Syndromes (PAIS) refer to the symptoms persisting months after initial infection. Clinical research studies on this topic often collect rich, multi-modal datasets. Yet, the complexity of the datasets and the lack of a precise clinical case definition pose difficulties in creating comprehensive analyses. Here, we present a generalisable framework for analysing data from longitudinal studies of PAIS using Latent Transition Analysis (LTA). It enables the identification of disease phenotypes and the patient-level analysis of transitions between them, without relying on predefined clinical categorisations. Furthermore, we introduce a method for incorporating covariate information, which enables exploration of how patient characteristics influence disease trajectories. We apply this methodology to the ORCHESTRA dataset, composed of individuals affected by SARS-CoV-2 infection from multiple European centres, for investigation into Post-COVID-19 condition (PCC). 5094 patient assessments were collected at SARS-CoV-2 infection, and at 6, 12, 18, and 24 months of follow-up. Our model identifies distinct PCC phenotypes with patient trajectories impacted by age and sex. Our results highlight how LTA can enhance the interpretability of complex, time-resolved clinical data, support personalized patient monitoring and management, and accelerate therapeutic development for other PAISs, too.

Authors

Institutions

Publication Details

Journal
Nature Communications
Published
2026-02-10
DOI
https://doi.org/10.1038/s41467-026-68650-7
Primary Topic
Machine Learning in Healthcare
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Latent transition analysis for longitudinal studies of post-acute infection syndromes

L. J. van Pelt, Filippo Trapani, Concetta Sciammarella, Andrea M. Sartori et al.
Nature Communications
Machine Learning in Healthcare
article

Latent transition analysis for longitudinal studies of post-acute infection syndromes

L. J. van Pelt, Filippo Trapani, Concetta Sciammarella, Andrea M. Sartori, Alex W. Friedrich, Elisa Gentilotti, Gerolf de Boer, Anna Giulia Salvadori, Erley Lizarazo, Aurora Alemán Rodríguez, Manuel Huth, Lorenza Lambertenghi, Elena Addis, Maddalena Armellini, Alessia Savoldi, Giorgia Franchina, Roy Gusinow, Enrico Gibbin, Cinzia Perlini, Andrea Leonardi, Matteo Morra, Marcella Sibani, Riccardo Cecchetto, Alessandro Visentin, Anna Maria Azzini, P. Gisondi, Maria Giulia Caponcello, Daniele Fasan, Elda Righi, Mariana Guedes, Federico Lattanzi, Marjolein Knoester, M Rocchi, Giorgia Tomassini, Sara K. Tedeschi, M Giannella, Salvatore Cataudella, Filippo Cioli Puviani, Ruth Joanna Davis, Davide Gibellini, Iris Lopes-Rafegas, Chiara Dellacasa, J Hasenauer, Laura Rovigo, Margriet van der Meer, Salvatore Monaco, Clemens Peiter, Benedetta Barana, Carolina Alvarez Garavito, Jacopo Garlasco, Pedro Navarro, Carmine Cutone, Debora Calì, Lorenzo Tavernaro, Marco Meroi, Rebecca Scardellato, Alessandro Castelli, Lucia Bonato, Sandra De la Rosa Riestra, Prof Tiziana Lazzarotto, Silvia Vituliano, Maria Mongardi, Alessandra Nazeri, Nadhem Lahfej, Elena Carrara, Andrea Volpe, Claudio Micheletto, Zaira R. Palacios Baena, Elisa Sicuri, Lidia Del Piccolo, Natascia Caroccia, Alice Toschi, Beatrice Tazza, Mara F. Vincenti-González, Adriana Tami, Giada Fasani, Giulia Rosini, Lola Cubero Aranda, Elisa Rossi, Gloria Mazzali, Jade Ghosn, Jesús Rodrguez-Baño, Raffaella Cordioli, Nicolò Cardobi, Gianluca Vantini, Maria Paola Cecchini, CINECA, Evelina Tacconelli, on behalf of the Telenephrology EWI Working Group, José M. Bravo-Ferrero, Erica Sodano, Aline-Marie Florence, Cecilia Bonazzetti, Cédric Laouénan, Michela Di Chiara, Lorenzo Maria Canziani, Lilli Gard, Chiara Konishi De Toffoli, Karin I. Wold, Anna Górska, Zeno Igor Adrien Pasquini, Servicio Andaluz de Salud (SAS), Maria Diletta Pezzani, Giacomo Fornaro, Lorenzo Marconi, Alida C. M. Veloo, Alessio Esposito, Maddalena Marcanti, Ana Belén Hidalgo Céspedes, Anna Mason, Salvatore Hermes Dall’O’, Gaia Maccarrone, Francesco Luca, Pasquale De Nardo, Simona Sorbello, Chiara Perlini, Mara Isabel Garcia Sánchez, Miriam Emiliani
article en

Abstract

Post-Acute Infectious Syndromes (PAIS) refer to the symptoms persisting months after initial infection. Clinical research studies on this topic often collect rich, multi-modal datasets. Yet, the complexity of the datasets and the lack of a precise clinical case definition pose difficulties in creating comprehensive analyses. Here, we present a generalisable framework for analysing data from longitudinal studies of PAIS using Latent Transition Analysis (LTA). It enables the identification of disease phenotypes and the patient-level analysis of transitions between them, without relying on predefined clinical categorisations. Furthermore, we introduce a method for incorporating covariate information, which enables exploration of how patient characteristics influence disease trajectories. We apply this methodology to the ORCHESTRA dataset, composed of individuals affected by SARS-CoV-2 infection from multiple European centres, for investigation into Post-COVID-19 condition (PCC). 5094 patient assessments were collected at SARS-CoV-2 infection, and at 6, 12, 18, and 24 months of follow-up. Our model identifies distinct PCC phenotypes with patient trajectories impacted by age and sex. Our results highlight how LTA can enhance the interpretability of complex, time-resolved clinical data, support personalized patient monitoring and management, and accelerate therapeutic development for other PAISs, too.

Nature CommunicationsVol. 17(1)
Délégation Paris 5 (FR), University of Verona (IT), University of Parma (IT), University Medical Center Groningen (NL), University of Bonn (DE), Inserm (FR), University of Groningen (NL), Guy's and St Thomas' NHS Foundation Trust (GB), Université Paris Cité (FR), Instituto de Salud Carlos III (ES), Hospital de São João (PT), Hospital Universitario Virgen Macarena (ES), Biobanco del Sistema Sanitario Público de Andalucía (ES), Sorbonne Paris Cité (FR), Departament de Salut (ES), Assistance Publique – Hôpitaux de Paris (FR), Hôpital Nord (FR), Manhiça Health Research Centre (MZ), Azienda USL di Bologna (IT), Instituto de Biomedicina de Sevilla (ES), Guglielmo da Saliceto Hospital (IT), Hôpital Bichat-Claude-Bernard (FR), Barcelona Institute for Global Health (ES), Consorzio Interuniversitario Nazionale per l'Informatica (IT), Consorzio Interuniversitario Fisica Spaziale (IT), Life & Brain (Germany) (DE), Universitat de Barcelona (ES), London School of Economics and Political Science (GB), University of Bologna (IT)
Openalex Percentile: Top 63%
Machine Learning in Healthcare
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.