Development and validation of a random forest model for predicting radiation pneumonitis in lung cancer patients receiving moderately hypofractionated radiotherapy: a retrospective cohort study

Yang Zhang; Zongjuan Li; Han Xiao; Zhenjiang Li; Jian He; Shisuo Du; Zhaochong Zeng

doi:10.21037/atm-22-3049

Development and validation of a random forest model for predicting radiation pneumonitis in lung cancer patients receiving moderately hypofractionated radiotherapy: a retrospective cohort study

Ann Transl Med. 2022 Dec;10(23):1264. doi: 10.21037/atm-22-3049.

Authors

Yang Zhang^#¹, Zongjuan Li^#², Han Xiao¹, Zhenjiang Li³, Jian He¹, Shisuo Du¹, Zhaochong Zeng¹

Affiliations

¹ Department of Radiation Oncology, Zhongshan Hospital, Fudan University, Shanghai, China.
² Department of Medical Oncology, Shanghai Pulmonary Hospital and Thoracic Cancer Institute, Tongji University School of Medicine, Shanghai, China.
³ Department of Radiation Physics, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, Jinan, China.

^# Contributed equally.

Abstract

Background: Radiation pneumonitis (RP) is a type of toxicity commonly associated with thoracic radiation therapy. We sought to establish a random forest (RF) model and evaluate its ability to predict RP in patients with non-small cell lung cancer (NSCLC) receiving moderately hypofractionated radiotherapy (hypo-RT).

Methods: A total of 106 patients with stage II-IVa NSCLC who received moderately hypofractionated helical tomotherapy (2.3-3.0 Gy/fraction) at Zhongshan Hospital were included. All enrolled patients were divided chronologically into the training (67 patients) and validation (39 patients) groups. Higher than or equal to grade 2 RP was defined as the end point. Logistic regression and RF models were established and compared using the receiver operating characteristic (ROC) and a confusion matrix in the training and validation groups.

Results: The cumulative incidence of the end point was 25.4% and 17.9% in the training and validation groups, respectively. Logistic regression models were constructed by dosage parameters of total lungs, ipsilateral or contralateral lungs, respectively. ROC analysis revealed that the dosimetric factors of total lungs yielded a superior classification performance than did that of the ipsilateral or contralateral lungs [area under the curve (AUC) =0.920, AUC =0.701, and AUC =0.661, respectively]. Furthermore, the RF model yielded a better prediction capacity than did the traditional logistic model based on the dosimetric factors of the total lungs (accuracy: 88.06%; precision: 84.62%; sensitivity: 64.71%; specificity: 96.00%). Moreover, the RF identified mean lung dose [MLD; mean decrease gini (MDG) =5.74], V20 (MDG =4.62), and V35 (MDG =3.08) of total lungs as the most common primary differentiators of RP.

Conclusions: Our RF model established based on the dosimetric parameters of the total lungs could accurately predict the RP risk in patients with NSCLC treated with moderately hypofractionated tomotherapy.

Keywords: Non-small cell lung cancer (NSCLC); hypofractionated radiotherapy; radiation pneumonitis (RP); random forest (RF).