Predicting Radiation Pneumonitis in Lung Cancer Patients Using a Radiomic Model
Author Information
Author(s): Jiao Yuxin, Feng Aihui, Li Shihong, Ren Yanping, Gao Hongbo, Chen Di, Sun Li, Zheng Xiangpeng, Lin Guangwu
Primary Institution: Huadong Hospital, Fudan University, Shanghai, China
Hypothesis
Can a multiregional radiomic model improve the prediction of symptomatic radiation pneumonitis in lung cancer patients treated with SBRT?
Conclusion
The combined model improves SRP prediction across various SBRT fractionation schemes.
Supporting Evidence
- VBED70 of the nontarget lung volume was identified as an independent dosimetric risk factor.
- The multiregional radiomic models outperformed single-regional models.
- The combined model achieved an AUC of 0.828, indicating strong predictive performance.
Takeaway
This study created a smart model to help doctors predict if lung cancer patients will have problems after radiation treatment, using special images of their lungs.
Methodology
Data from 189 patients were analyzed using univariate and multivariate regression, and machine learning algorithms were applied to develop predictive models.
Potential Biases
Potential biases from patient selection and confounding factors due to the retrospective nature of the study.
Limitations
The study is retrospective with a relatively small sample size, which may introduce biases.
Participant Demographics
Patients with non-small cell lung cancer treated with SBRT, median age 75.5 years, 59.7% male.
Statistical Information
P-Value
p<0.001
Confidence Interval
95% CI: 0.694–0.938
Statistical Significance
p<0.001
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website