CT-based radiomics models for predicting the prognosis of children with mycoplasma pneumonia
CT-basierte Radiomics-Modelle zur Prognosevorhersage bei Kindern mit Mycoplasma-Pneumonie
Frontiers in Cellular and Infection Microbiology · 24.03.2026 · 16
DOI: 10.3389/fcimb.2026.1737753 ↗Auf einen Blick
Bei 356 Kindern mit Mycoplasma-Pneumonie zeigte ein CT-basiertes Radiomics-Modell eine bessere Prognosevorhersage als ein klinisches Modell. Die Kombination aus klinischen Daten und Radiomics schnitt am besten ab.
Fragestellung
Lässt sich die Prognose von Kindern mit Mycoplasma-Pneumonie mit klinischen Daten und CT-basierten Radiomics-Funktionen vorhersagen?
Methode
356 Kinder aus 2 Krankenhäusern; Randomisierung in Trainings-, Test- und Validierungsset. Klinische Daten und CT-Radiomics-Funktionen wurden analysiert; Modellauswahl mit univariater Analyse und LASSO.
Ergebnisse
Klinisches Modell: AUC 0,767, 0,731 und 0,685 in Trainings-, Validierungs- und Testset. Radiomics-Modell: AUC 0,829, 0,775 und 0,701. Kombiniertes Modell: AUC 0,842, 0,825 und 0,748.
Schlussfolgerung der Autor:innen
Das auf CT-Bildmerkmalen basierende Radiomics-Modell zeigte Potenzial als quantitatives Werkzeug zur Prognosevorhersage bei Kindern mit Mycoplasma-Pneumonie. Die Kombination mit klinischen Daten verbesserte die diagnostische Leistung.
Kernaussagen
- Radiomics-Modell mit höheren AUC-Werten als klinisches Modell
- Kombiniertes Modell mit den besten AUC-Werten
- 21 Radiomics-Funktionen wurden ausgewählt
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 Cellular and Infection Microbiology, online erschienen am 24.03.2026. Verfasst von Tianda Wang und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Hebei Key Laboratory of Precise Imaging of Inflammation Related Tumors, The Affiliated Hospital of Hebei University, Baoding…. Hauptthemen laut MEDLINE: Radiomics, Pneumonia, Mycoplasma, Tomography, X-Ray Computed. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Themen: Kinderkrankenpflege
Abstract (Originalsprache)
Background
In recent years, the incidence of mycoplasma pneumonia (MP) in children has gradually increased; however, to date, few studies have assessed its prognosis in children. Hence, the present study aimed to develop a prognostic model for children with MP by using clinical data and radiomics features extracted from chest computed tomography (CT) images.
Methods
A total of 356 children with MP from two hospitals were enrolled in the study. These patients were randomly assigned to a training set (n = 206), a test set (n = 52), and a validation set (n = 98). Clinical data, including patients’ history and demographics, laboratory test results, and CT imaging features, were collected. Radiomics features of the infected lesions were extracted from chest CT images. Univariate analysis was performed to determine the most predictive features with significant differences (P < 0.05) among all imaging and clinical data. Least absolute shrinkage and selection operator was used to select radiomics features and estimate the prediction performance of the clinical factors model and the radiomics model for prognosis.
Results
In the training set, the clinical factors (creatine kinase-MB, lactate dehydrogenase, C-reactive protein, bilateral lobe pneumonia, number of lobes, and lesion volume) showed a significant prognostic value (all P < 0.05) and were selected to construct the clinical model. The area under the curve (AUC) values of the clinical model for the training, validation, and test sets were 0.767, 0.731, and 0.685, respectively. Twenty one radiomics features were selected. The AUC values of the radiomics model for the training, validation, and test sets were 0.829, 0.775, and 0.701, respectively. Decision curve analysis showed that the radiomics model has potential clinical application value for predicting the prognosis of children with MP. The clinical and radiomics model showed the best prediction performance, with AUC values of 0.842, 0.825, and 0.748 for the training, validation, and test sets, respectively.
Conclusion
The radiomics model based on CT imaging features showed potential as a quantitative tool to predict the prognosis of children with MP. The addition of radiomics features to the clinical factors improved the diagnostic efficiency of the clinical and radiomics model. Thus, the combination of clinical data and radiomic features effectively predicted the prognostic outcome of children with MP.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Radiology, Hebei Key Laboratory of Precise Imaging of Inflammation Related Tumors, The Affiliated Hospital of Hebei University, Baoding, China.
- Department of Radiology, Baoding Children's Hospital, Baoding, China.
- Department of Research and Development, United Imaging Intelligence, Beijing, China.
Zitieren
APA
Wang, T., Meng, H., Zhuo, L., Zang, L., Cui, J., Wang, J., & Yin, X. (2026). CT-based radiomics models for predicting the prognosis of children with mycoplasma pneumonia. Frontiers in Cellular and Infection Microbiology, 16. https://doi.org/10.3389/fcimb.2026.1737753
Vancouver
Wang T, Meng H, Zhuo L, Zang L, Cui J, Wang J, et al. CT-based radiomics models for predicting the prognosis of children with mycoplasma pneumonia. Frontiers in Cellular and Infection Microbiology. 2026;16. doi:10.3389/fcimb.2026.1737753
BibTeX
@article{Wang2026,
author = {Wang, Tianda and Meng, Huan and Zhuo, LiYong and Zang, Lili and Cui, Jingjing and Wang, Jianing and Yin, Xiaoping},
title = {CT-based radiomics models for predicting the prognosis of children with mycoplasma pneumonia},
journal = {Frontiers in Cellular and Infection Microbiology},
year = {2026},
volume = {16},
doi = {10.3389/fcimb.2026.1737753}
}
EUVIMED