Machine learning-based identification of inflammatory biomarkers for predicting pulmonary consolidation in children with Chlamydia pneumoniae infection
Identifikation entzündlicher Biomarker mit Machine Learning zur Vorhersage einer pulmonalen Konsolidierung bei Kindern mit Chlamydia-pneumoniae-Infektion
Frontiers in Pediatrics · 04.05.2026 · 14
DOI: 10.3389/fped.2026.1779116 ↗Auf einen Blick
In einer retrospektiven Fall-Kontroll-Studie wurden LDH, CRP und ESR als Kernmarker zur Vorhersage einer pulmonalen Konsolidierung identifiziert. Das Online-Risikotool zeigte eine hohe Vorhersagegüte.
Fragestellung
Welche entzündlichen Biomarker sagen bei Kindern mit Chlamydia-pneumoniae-Infektion eine pulmonale Konsolidierung voraus?
Methode
Retrospektive Fall-Kontroll-Studie mit 42 Kindern; Feature-Selektion mit 5 Machine-Learning-Algorithmen; K-means-Clusteranalyse; Entwicklung eines Online-Risikorechners.
Ergebnisse
LDH, CRP und ESR waren in der Konsolidierungsgruppe höher als in der Nicht-Konsolidierungsgruppe (P < 0,001). AUC 0,993 (95 %-KI 0,966–1,000); Sensitivität 88,9 %, Spezifität 93,9 %.
Schlussfolgerung der Autor:innen
LDH, CRP und ESR sind Schlüsselindikatoren zur Vorhersage einer pulmonalen Konsolidierung bei Kindern mit C. pneumoniae-Infektion.
Kernaussagen
- LDH, CRP und ESR wurden als Kernmarker identifiziert
- AUC des Risikotools: 0,993 (95 %-KI 0,966–1,000)
- Bootstrap-AUC: 0,949 (95 %-KI 0,881–0,995)
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Pediatrics, online erschienen am 04.05.2026. Verfasst von Qianqian Dai und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pediatrics, The First Affiliated Hospital of Xinjiang Medical University, Urumqi, Xinjiang, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Themen: Künstliche Intelligenz in der Pflege, Kinderkrankenpflege
Abstract (Originalsprache)
Objective
This study aimed to identify core inflammatory biomarkers through machine learning approaches and develop an accessible online risk calculator to predict pulmonary consolidation in children with Chlamydia pneumoniae infection, addressing the current lack of effective early warning tools.
Methods
This retrospective case-control study enrolled 42 children with C. pneumoniae infection (consolidation group: 26 cases; non-consolidation group: 16 cases) between January 2020 and December 2024. Five machine learning algorithms, including least absolute shrinkage and selection operator (LASSO) regression, support vector machine-recursive feature elimination (SVM-RFE), Random Forest, XGBoost, and LightGBM, were employed for feature selection, and core predictive factors were identified through consensus validation across these algorithms. K-means clustering analysis was performed on the key inflammatory markers, and an online risk assessment system based on HTML5 technology was developed.
Results
The five machine learning algorithms consistently identified lactate dehydrogenase (LDH), C-reactive protein (CRP), and erythrocyte sedimentation rate (ESR) as core inflammatory markers for predicting pulmonary consolidation. All three indicators were significantly higher in the consolidation group compared with the non-consolidation group ( P < 0.001). K-means clustering analysis stratified patients into a high-inflammation group (9 cases, 21.4%) and a low-inflammation group (33 cases, 78.6%), with a significant difference in consolidation rates between the two groups (100% vs. 51.5%, P = 0.008). The risk assessment system, constructed based on clustering results, demonstrated excellent predictive performance [area under the curve (AUC) = 0.993, 95% confidence interval (CI): 0.966–1.000], with a sensitivity of 88.9% and specificity of 93.9%. Bootstrap resampling validation (1,000 iterations) confirmed the robustness of the clustering solution (stability: 91.2%) and the risk assessment system (bootstrap AUC: 0.949, 95% CI: 0.881–0.995).
Conclusion
LDH, CRP, and ESR are key indicators for predicting pulmonary consolidation in children with C. pneumoniae infection. The online risk assessment system developed based on these three routine laboratory parameters demonstrates good clinical usability and practicality, enabling early identification of high-risk patients to guide individualized treatment decisions.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Pediatrics, The First Affiliated Hospital of Xinjiang Medical University, Urumqi, Xinjiang, China.
Zitieren
APA
Dai, Q., Wang, Z., Zhao, J., Wang, Y., Li, M., Maimaitiniyazi, A., Wang, X., Cui, J., Guo, Z., Qu, S., Zhao, W., & Ru, L. (2026). Machine learning-based identification of inflammatory biomarkers for predicting pulmonary consolidation in children with Chlamydia pneumoniae infection. Frontiers in Pediatrics, 14. https://doi.org/10.3389/fped.2026.1779116
Vancouver
Dai Q, Wang Z, Zhao J, Wang Y, Li M, Maimaitiniyazi A, et al. Machine learning-based identification of inflammatory biomarkers for predicting pulmonary consolidation in children with Chlamydia pneumoniae infection. Frontiers in Pediatrics. 2026;14. doi:10.3389/fped.2026.1779116
BibTeX
@article{Dai2026,
author = {Dai, Qianqian and Wang, Zhiyuan and Zhao, Junlin and Wang, Yanan and Li, Menghua and Maimaitiniyazi, Aliya and Wang, Xueli and Cui, Jianjiang and Guo, Zhenzhen and Qu, Shengmeng and Zhao, Wen and Ru, Liang},
title = {Machine learning-based identification of inflammatory biomarkers for predicting pulmonary consolidation in children with Chlamydia pneumoniae infection},
journal = {Frontiers in Pediatrics},
year = {2026},
volume = {14},
doi = {10.3389/fped.2026.1779116}
}
EUVIMED