Radiomics Models to Predict Tumor Response and Pneumonitis in Non-Small Cell Lung Cancer Patients Treated with Immunotherapy
Radiomics-Modelle zur Vorhersage von Tumoransprechen und Pneumonitis bei mit Immuntherapie behandelten Patient:innen mit nicht-kleinzelligem Lungenkarzinom
Journal of Clinical Medicine · 18.06.2025 · 14 (12) · 4330
DOI: 10.3390/jcm14124330 ↗Auf einen Blick
Bei 159 NSCLC-Patient:innen unter Immuntherapie sagten prätherapeutische CT-Radiomics CIP und Tumoransprechen nur begrenzt vorher. Für CIP lag die AUC bei 0,60.
Fragestellung
Können Radiomics-Modelle aus prätherapeutischer CT das Auftreten von checkpoint inhibitor-assozierter Pneumonitis und das Tumoransprechen bei NSCLC unter Immuntherapie vorhersagen?
Methode
Analyse von 159 Patient:innen mit NSCLC Stadium III-IV unter Immuntherapie; 3D-Radiomics aus Tumor und Umgebung; Harmonisierung mit linearem Mixed-Effect-Modell; Random-Forest-Modelle; Bewertung per AUC.
Ergebnisse
Von 159 Patient:innen entwickelten 31 eine CIP. Die AUC betrug 0,60 (95 %-KI 0,55–0,66) für CIP, 0,63 (95 %-KI 0,59–0,67) für irRECIST und 0,66 (95 %-KI 0,61–0,70) für RECIST 1.1.
Schlussfolgerung der Autor:innen
Die Studie zeigt das potenzielle Potenzial radiomischer Modelle zur Vorhersage von CIP und Tumoransprechen aus prätherapeutischen CT-Bildern bei NSCLC unter Immuntherapie.
Kernaussagen
- CIP bei 31 von 159 Patient:innen
- AUC für CIP: 0,60 (95 %-KI 0,55–0,66)
- AUC für Tumoransprechen: 0,63 und 0,66
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 Journal of Clinical Medicine, online erschienen am 18.06.2025. Verfasst von Monica Yadav und 26 weiteren Autor:innen. Beteiligte Einrichtung: Feinberg School of Medicine, Northwestern University, NMH/Arkes Family Pavilion Suite 800, 676 N Saint Clair, Chicago, IL 60611, USA. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Themen: Onkologische Pflege
Abstract (Originalsprache)
Background
Checkpoint inhibitor-associated pneumonitis (CIP) after immunotherapy has become a challenging issue in non-small cell lung cancer (NSCLC) patients. This study leverages artificial intelligence (AI) algorithms to analyze radiomic features, aiming to predict the occurrence of CIP, as well as tumor response.
Methods
This study analyzed data from 159 stage III-IV NSCLC patients undergoing immunotherapy. The patients were categorized into pneumonitis and non-pneumonitis groups, and 3D radiomic features from both tumors and surrounding regions were extracted using LIFEx software. To address scanner-associated variations, a linear mixed-effect radiomics harmonization model was applied. A random forest algorithm was then used to develop models predicting CIP occurrence and tumor responses based on the pre-treatment CT radiomics. The accuracy was evaluated using the area under the curve (AUC).
Results
A total of 159 patients were analyzed, of which only 31 experienced CIP. Most had grade 1 (17/31, 54.8%) or 2 (12/31, 38.7%) pneumonitis; only two (6.5%) patients had grade 3. Patients who developed pneumonitis were more likely to be male (64.5% vs. 38.3%, p = 0.014), had less adenocarcinoma histology (54.8% vs. 78.9%, p = 0.032), and exhibited a higher tumor mutational burden (57.1% vs. 24.5%, p = 0.047). Radiomics analysis reported predictability for CIP with an AUC of 0.60 (95% CI 0.55–0.66). The five-year overall and progression-free survival rates were 24.7% (95% CI 15.2–35.5%) and 9.7% (95% CI 4.4–17.4%), respectively. The radiomics features also exhibited AUCs of 0.63 (95% CI 0.59–0.67) in irRECIST and 0.66 (95% CI 0.61–0.70) in RECIST 1.1 in terms of tumor responses to immunotherapy.
Conclusions
This study provides insights into the potential role of radiomic models in predicting CIP and tumor responses from pre-treatment CT images of NSCLC patients treated with immunotherapy.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Feinberg School of Medicine, Northwestern University, NMH/Arkes Family Pavilion Suite 800, 676 N Saint Clair, Chicago, IL 60611, USA.
- St. Joseph's Medical Center, 1800 N California St, Stockton, CA 95204, USA.
- Department of Breast Surgery, Kyungpook National University, Daegu 37224, Republic of Korea.
- Department of Biochemisty, The University of Texas at Austin, Austin, TX 78712, USA.
- Division of Pulmonary Diseases and Critical Care Medicine, School of Medicine at UCI, Irvine, CA 92617, USA.
- Richmond University Medical Center, Staten Island, NY 10310, USA.
ORCID-Profile: Wongi Woo, Young Kwang Chae, Jeeyeon Lee, Peter Haseok Kim, Seyoung Lee, Taegyu Um, Yury S Velichko
Zitieren
APA
Yadav, M., Woo, W., Chae, Y. K., Lee, J., Kim, P. H., Lee, S., Um, T., Lee, S., Chuchuca, M. J. A., Djunadi, T. A., Chung, L. I., Yu, J., Gennaro, N., Kim, L., Nam, M., Oh, Y., Yoon, S., Shah, Z., Kim, Y., …, & Velichko, Y. S. (2025). Radiomics Models to Predict Tumor Response and Pneumonitis in Non-Small Cell Lung Cancer Patients Treated with Immunotherapy. Journal of Clinical Medicine, 14(12), 4330. https://doi.org/10.3390/jcm14124330
Vancouver
Yadav M, Woo W, Chae YK, Lee J, Kim PH, Lee S, et al. Radiomics Models to Predict Tumor Response and Pneumonitis in Non-Small Cell Lung Cancer Patients Treated with Immunotherapy. Journal of Clinical Medicine. 2025;14(12):4330. doi:10.3390/jcm14124330
BibTeX
@article{Yadav2025,
author = {Yadav, Monica and Woo, Wongi and Chae, Young Kwang and Lee, Jeeyeon and Kim, Peter Haseok and Lee, Seyoung and Um, Taegyu and Lee, Salie and Chuchuca, Maria Jose Aguilera and Djunadi, Trie Arni and Chung, Liam Il-Young and Yu, Jisang and Gennaro, Nicolo and Kim, Leeseul and Nam, Myungwoo and Oh, Youjin and Yoon, Sungmi and Shah, Zunairah and Kim, Yuchan and Hong, Ilene and Jang, Jessica and Kang, Grace and Cho, Amy and Lee, Soowon and Hong, Timothy and Nam, Cecilia and Velichko, Yury S},
title = {Radiomics Models to Predict Tumor Response and Pneumonitis in Non-Small Cell Lung Cancer Patients Treated with Immunotherapy},
journal = {Journal of Clinical Medicine},
year = {2025},
volume = {14},
number = {12},
pages = {4330},
doi = {10.3390/jcm14124330}
}
EUVIMED