Circulating lncRNAs as biomarkers for severe dengue using a machine learning approach - 08/04/25

Doi : 10.1016/j.jinf.2025.106471

Rodolfo Katz ^a,^{^{1
These authors have contributed equally to this work.}}, Nguyen Minh Nam ^b,^{^{1
These authors have contributed equally to this work.}}, Tulio de Lima Campos ^c,^{^{1
These authors have contributed equally to this work.}}, Victoria Indenbaum ^d, Sophie Terenteva ^e, Dinh Thi Thu Hang ^f, Le Thi Hoi ^g, Amos Danielli ^e, Yaniv Lustig ^d,^h, Eli Schwartz ^i,^j, Hoang Van Tong ^f,^k,^{^{2
These authors jointly supervised this work.}}, Ella H. Sklan ^a,^⁎,^{^{2
These authors jointly supervised this work.}}
^a Department of Clinical Microbiology and Immunology, Faculty of Medical and Health Sciences, Tel Aviv University, Tel Aviv, Israel
^b 103 Military Hospital, Vietnam Military Medical University, Hanoi, Vietnam
^c Bioinformatics Core Facility, Aggeu Magalhães Institute, Oswaldo Cruz Foundation, Recife PE, Brazil
^d Central Virology Laboratory, Ministry of Health, Chaim Sheba Medical Center, Tel Hashomer, Israel
^e Faculty of Engineering, The Institute of Nanotechnology and Advanced Materials, Bar-Ilan University, Ramat Gan, Israel
^f Institute of Biomedicine and Pharmacy, Vietnam Military Medical University, Hanoi, Vietnam
^g Hanoi Medical University, Hanoi, Vietnam
^h School of Public Health, School of Medicine, Tel Aviv University, Tel Aviv, Israel
ⁱ The Institute of Tropical Medicine, Sheba Medical Center, Ramat Gan, Israel
^j Faculty of Medical and Health Sciences, Tel Aviv University, Tel Aviv, Israel
^k Department of Pathophysiology, Vietnam Military Medical University, Hanoi, Vietnam

^⁎Corresponding author.

Summary

Objectives

Dengue virus (DENV) infection is a significant global health concern, causing severe morbidity and mortality. While many cases present as a mild febrile illness, some progress to life-threatening severe dengue (SD). Early intervention is essential to improve outcomes, but current predictive methods lack specificity, burdening healthcare systems in endemic regions. Circulating long non-coding RNAs (lncRNAs) have emerged as stable and promising biomarkers. This study explored the use of lncRNAs as predictive markers for SD.

Methods

Differential expression and qPCR arrays were employed to identify lncRNAs associated with SD. Candidate lncRNAs were validated, and their plasma levels were measured in a cohort of Vietnamese dengue patients ( =377) and healthy controls ( =128) at admission. Machine learning algorithms were applied to predict the probability of SD progression.

Results

The predictive model demonstrated high sensitivity and specificity, with an area under the curve (AUC) of 0.98 (95% CI: 0.96–1.0). At admission, it accurately identified 17 of 18 patients who later died as high-risk, compared to traditional warning signs, which flagged only 9 of these cases.

Conclusions

Our findings suggest that this panel of lncRNAs has the potential to predict SD, which could help reduce healthcare burden and improve patient management in endemic countries.

Le texte complet de cet article est disponible en PDF.

Highlights

•	Dengue infection can cause severe dengue (SD), a life-threatening disease.
•	Early intervention is key to preventing SD deterioration and improving outcomes.
•	Current SD prediction methods lack specificity, burdening healthcare systems.
•	A panel of circulating lncRNAs correlating with disease severity was identified.
•	Machine learning algorithms calculated SD probability with high sensitivity and specificity.

Le texte complet de cet article est disponible en PDF.

Keywords : Dengue virus, Severe dengue, Machine learning, Dengue warning signs, Long non-coding RNAs

Plan

Introduction

Materials and methods

Overview of the experimental design

RNA-seq analysis

Cells and virus stocks

Qiagen RT² lncRNA PCR array

Determination of lncRNA levels in cell lines

Study population and sample collection

Machine learning prediction models

Statistical analysis

Results

Identification of lncRNAs induced during DENV infection

Validation of the identified lncRNAs

Model generation to predict progression to severe dengue

Discussion

Export

Vol 90 - N° 4

Article 106471- avril 2025 Retour au numéro

Article précédent

Oral ADC189 for adults and adolescents with uncomplicated influenza
Jingya Zhao, Guoping Sheng, Yingqi Lyu, Yilan Sun, Sikui Wang, Xiaolin Chen, Feng Ye, Lin Chen, Xiaowei Xu, Hong Wang, Bin Wu, Chunxian Peng, Min Deng, Lihong Qu, Xuehong Jiang, Junyan Hu, Yan Feng, Yongzhong Li, Jie Peng, Weiyang Li, Lei Shao, Feng Gao, Dongbo Tian, Jie Tan, Huanwei Zheng, Meifang Chen, Hong Wu, Xiaoyun Zhu, Min Zhou, Jieming Qu

| Article suivant

Post-vaccination IgG4 and IgG2 class switch associates with increased risk of SARS-CoV-2 infections
Carla Martín Pérez, Sílvia Ruiz-Rius, Anna Ramírez-Morros, Marta Vidal, D. Herbert Opi, Pere Santamaria, Julià Blanco, Josep Vidal-Alaball, James G. Beeson, Luis M. Molinos-Albert, Ruth Aguilar, Anna Ruiz-Comellas, Gemma Moncunill, Carlota Dobaño

Bienvenue sur EM-consulte, la référence des professionnels de santé.
L’accès au texte intégral de cet article nécessite un abonnement.

Déjà abonné à cette revue ?

connectez-vous ou créez un compte

Circulating lncRNAs as biomarkers for severe dengue using a machine learning approach - 08/04/25

Summary

Objectives

Methods

Results

Conclusions

Highlights

Plan

Export citations

Fichier

Contenu

Accès rapides

Mon compte

Aide & support

Plateformes Elsevier Masson

Déclaration CNIL