Symptomatic Radiation Pneumonitis Research Articles

Enhancing the prediction of symptomatic radiation pneumonitis for locally advanced non-small-cell lung cancer by combining 3D deep learning-derived imaging features with dose-volume metrics: atwo-center study.

This study aims to examine the ability of deep learning (DL)-derived imaging features for the prediction of radiation pneumonitis (RP) in locally advanced non-small-cell lung cancer (LA-NSCLC) patients. The study cohort consisted of 90patients from the Fudan University Shanghai Cancer Center and 59patients from the Affiliated Hospital of Jiangnan University. Occurrences of RP were used as the endpoint event. Atotal of 512 3D DL-derived features were extracted from two regions of interest (lung-PTV and PTV-GTV) delineated on the pre-radiotherapy planning CT. Feature selection was done using LASSO regression, and the classification models were built using the multilayered perceptron method. Performances of the developed models were evaluated by receiver operating characteristic curve analysis. In addition, the developed models were supplemented with clinical variables and dose-volume metrics of relevance to search for increased predictive value. The predictive model using DL features derived from lung-PTV outperformed the one based on features extracted from PTV-GTV, with AUCs of 0.921 and 0.892, respectively, in the internal test dataset. Furthermore, incorporating the dose-volume metric V30Gy into the predictive model using features from lung-PTV resulted in an improvement of AUCs from 0.835 to 0.881 for the training data and from 0.690 to 0.746 for the validation data, respectively (DeLong p < 0.05). Imaging features extracted from pre-radiotherapy planning CT using 3D DL networks could predict radiation pneumonitis and may be of clinical value for risk stratification and toxicity management in LA-NSCLC patients. Integrating DL-derived features with dose-volume metrics provides apromising noninvasive method to predict radiation pneumonitis in LA-NSCLC lung cancer radiotherapy, thus improving individualized treatment and patient outcomes.

DNA Repair Genetics and the Risk of Radiation Pneumonitis in Patients With Lung Cancer: A Systematic Review and Meta-analysis

AimsERCC1 rs11615 and ERCC2 rs238406 single nuclear polymorphism (SNPs) are known for their association with treatment outcome, likely related to radiosensitivity of both tumor and normal tissue in patients with non-small-cell lung cancer. This study aimed to review the effect of 1) these ERCC1/2 SNPs and 2) other SNPs of DNA repair genes on radiation pneumonitis (RP) in patients with lung cancer. Materials and methodsSNPs of our interest included ERCC1 rs11615 and ERCC2 rs238406 and other genes of DNA repair pathways that are functional and biologically active. DNA repair SNPs reported by at least two independent studies were pooled for meta-analysis. The study endpoint was radiation pneumonitis (RP) after radiotherapy. Recessive, dominant, homozygous, heterozygous, and allelic genotype models were used where appropriate. ResultsA total of 16 studies (3080 patients) were identified from the systematic review and 12 studies (2090 patients) on 11 SNPs were included in the meta-analysis. The SNPs were ATM rs189037, ATM rs373759, NEIL1 rs4462560, NEIL1 rs7402844, APE1 rs1130409, XRCC3 rs861539, ERCC1 rs11615, ERCC1 rs3212986, ERCC2 rs238406, ERCC2 rs13181, and XRCC1 rs25487. ERCC1 rs11615 (236 patients) and ERCC2 rs238406 (254 patients) were not significantly associated with RP. Using the allelic model, the G allele for NEIL1 gene was significantly associated with a reduced odds of developing symptomatic (grade ≥2) RP compared to the C allele for rs7402844 (OR 0.70, 95% CI: 0.49, 0.99, P = 0.04). Similarly, the T allele for APE1 gene was significantly associated with a reduced odds of developing symptomatic (grade ≥2) RP compared to the G allele for rs1130409 (OR 0.59, 95% CI: 0.43, 0.81, P = 0.001). ConclusionGenetic variation in the DNA repair pathway genes may play a significant role in the risk of developing radiation pneumonitis in patients with lung cancer. Further studies are needed on genotypic features of DNA repair pathway genes and their association with treatment sensitivity, as such knowledge may guide personalized radiation dose prescription.

Integration of dosimetric parameters, clinical factors, and radiomics to predict symptomatic radiation pneumonitis in lung cancer patients undergoing combined immunotherapy and radiotherapy

PurposeThis study aimed to combine clinical/dosimetric factors and handcrafted/deep learning radiomic features to establish a predictive model for symptomatic (grade ≥ 2) radiation pneumonitis (RP) in lung cancer patients who received immunotherapy followed by radiotherapy. Materials and MethodsThis study retrospectively collected data of 73 lung cancer patients with prior receipt of ICIs who underwent thoracic radiotherapy (TRT). Of these 73 patients, 41 (56.2 %) developed symptomatic grade ≥ 2 RP. RP was defined per multidisciplinary clinician consensus using CTCAE v5.0. Regions of interest (ROIs) (from radiotherapy planning CT images) utilized herein were gross tumor volume (GTV), planning tumor volume (PTV), and PTV-GTV. Clinical/dosimetric (mean lung dose and V5-V30) parameters were collected, and 107 handcrafted radiomic (HCR) features were extracted from each ROI. Deep learning-based radiomic (DLR) features were also extracted based on pre-trained 3D residual network models. HCR models, Fusion HCR model, Fusion HCR + ResNet models, and Fusion HCR + ResNet + Clinical models were built and compared using the receiver operating characteristic (ROC) curve with measurement of the area under the curve (AUC). Five-fold cross-validation was performed to avoid model overfitting. ResultsHCR models across various ROIs and the Fusion HCR model showed good predictive ability with AUCs from 0.740 to 0.808 and 0.740–0.802 in the training and testing cohorts, respectively. The addition of DLR features improved the effectiveness of HCR models (AUCs from 0.826 to 0.898 and 0.821–0.898 in both respective cohorts). The best performing prediction model (HCR + ResNet + Clinical) combined HCR & DLR features with 7 clinical/dosimetric characteristics and achieved an average AUC of 0.936 and 0.946 in both respective cohorts. ConclusionsIn patients undergoing combined immunotherapy/RT for lung cancer, integrating clinical/dosimetric factors and handcrafted/deep learning radiomic features can offer a high predictive capacity for RP, and merits further prospective validation.

Combining Dosimetric and Radiomics Features for the Prediction of Radiation Pneumonitis in Locally Advanced Non-Small Cell Lung Cancer by Machine Learning

This study aimed to analyze the dosimetric factors and radiomics features of tumor and lungs in locally advanced non-small cell lung cancer (LANSCLC) to establish machine learning models and improve the prediction of grade (G) 2 radiation pneumonitis (RP). This study retrospectively collected data of 284 LANSCLC patients underwent concurrent chemoradiotherapy (CCRT) to a median dose of 64 Gy in 20-33 fractions between 2013 and 2021. Of this cohort, 21.1% of patients had ≥ G2 RP. There were 4 regions of interest (ROIs) had been identified in planning computed tomography images: gross tumor volume (GTV), ipsilesional lung (IL), contralesional lung (CL), and total lung (TL). We calculated the dose-volume histogram (DVH) from the lowest dose to the maximum dose increasing by degrees with 1 Gy, and extracted a total of 172 radiomics features from all the 4 ROIs. We selected the best predictors for classifying 2 groups of patients using a sequential backward elimination support vector machine model. The best predictors for ≥ G2 RP were the combination of 8 radiomics features and 7 dosimetric factors in training group, and the validation group achieved an area under the curve (AUC) of 0.847 (accuracy, 80.38%; sensitivity, 78.95%; specificity, 81.82%). The eight radiomic features included 2 from GTV while 1, 2 and 3 from IL, CL and TL, respectively. For dosimetric factors, V65 of GTV, V20, V50 and V55 of IL, V10 of CL, V20 and V55 of TL appeared to be significantly related to symptomatic RP. These dosimetric factors should be constrained to less than 99.2%, 50.0%, 17.5%, 13.0%, 39.5%, 32.0%, and 6.6%, respectively. Combining dosimetric factors and radiomics features within GTV, IL, CL and TL can improve the prediction of symptomatic RP in LANSCLC patients treated with CCRT. The results suggested the importance of V65 of GTV, V20, V50 and V55 of IL, V10 of CL, V20 and V55 of TL as predictors of symptomatic RP and provide useful information for optimization of treatment planning in the era of combination of radiotherapy and immunotherapy.

Handcrafted Radiomics, Deep Learning Radiomics in the Prediction of Radiation Pneumonitis for NSCLC Patients Treated with Immunotherapy Followed with Thoracic Radiotherapy

Our previous study has shown that NSCLC patients previously received immune checkpoint inhibitors (ICIs) underwent thoracic intensity modulated radiotherapy have a higher risk of acute radiation pneumonitis (RP). This study aimed to establish machine learning models using handcrafted radiomics (HCR), deep learning-based radiomics (DLR) and clinical characteristics to improve the prediction of symptomatic radiation pneumonitis (RP) (grade ≥ 2) status for NSCLC patients treated with immunotherapy followed with thoracic radiotherapy. This study retrospectively collected data of 61 NSCLC patients meeting the requirements of study enrollment. Of these 61 patients, 35 developed symptomatic graded ≥ 2 RP. We defined 3 regions of interest (ROIs) in planning CT images including gross tumor volume (GTV), planning tumor volume (PTV), PTV-GTV. We calculated the mean dose, V5, V10, V20, and V30 within TL-GTV, and the volume of GTV, PTV and total lung. A total of 516 handcrafted radiomics features and 512 deep features were extracted from each 3 ROIs. Person Correlation Analysis and Least Absolute Shrinkage and Selection Operator (LASSO) were used to reduce the dimension of features. The HCR models, DLR models and the fusion models across different ROIs with machine learning classifiers were built and compared. In multi-classifier modeling, models with PTV under logistic regression (LR) classifiers showed better prediction than other ROIs under different machine learning algorithms. Based on PTV with LR, HCR+ DLR model had better performance, with an area under the curve (AUC) of 0.95 (95% confidence interval (CI): 0.893-1) in the training cohort and 0.87 (95% CI: 0.698-1) in the test cohort, which was higher than that of HCR model, with an AUC of 0.86 (95% CI: 0.755-0.9) in the training cohort and 0.82 (95% CI: 0.624-1) in the test cohort, the results of fusion model with HCR, DLR and 7 clinical characteristics including T, N, clinical stage, age, smoking, radiotherapy alone/combined and V30, demonstrated the best distinguishing performance, with an AUC of 0.99 (95% CI: 0.970-1) in the training cohort and 0.91 (95% CI: 0.784-1) in the test cohort. The combination of HCR, DLR and clinical characteristic underwent machine learning algorithms can improve the prediction of symptomatic RP in NSCLC patients treated with ICIs followed with thoracic radiotherapy.

Risk Factors for Symptomatic Radiation Pneumonitis after Stereotactic Body Radiotherapy (SBRT) for Early-Stage Lung Cancer

To identify risk factors for symptomatic radiation pneumonitis (RP) after stereotactic body radiotherapy (SBRT) in patients with early-stage lung cancer. We reviewed patients with clinical stage IA1-IIA non-small cell lung cancer treated by SBRT in our institution. The primary endpoint was grade ≥ 2 RP. To evaluate the relationship between clinical risk factors and grade ≥ 2 RP, the Gray test was used for univariate analysis and the Fine-Gray model for multivariate analysis. Dose parameters were univariate analyzed using the Fine-Gray model. Optimal thresholds for dose parameters were tested using receiver operating characteristic (ROC) curves. Among a total of 244 patients analyzed. The median age of patients was 77 years. The median follow-up period was 48 months. The 4-year cumulative incidence of grade ≥ 2 RP was 15.3% for all patients. In univariate analysis, tumor size (p = 0.01), central tumor (p < 0.001), interstitial pneumonia (p = 0.002), biological effective dose (BED, α/β ratio of 10 Gy) (p = 0.017), lung volume (%) receiving at least 8 Gy (V8) (p = 0.012), V10 (p = 0.011), V20 (p = 0.022) and mean lung dose (MLD) (p = 0.014) were significantly associated with the risk of grade ≥ 2 RP. In multivariate analysis, central tumor (hazard ratio [HR], 3.77; 95% confidence interval [CI], 1.88-7.55; p < 0.001) and interstitial pneumonia (HR, 4.88; 95% CI, 1.77-13.43; p = 0.002) were significantly associated with the risk of grade ≥ 2 RP. ROC curve analysis showed that the optimal diagnostic thresholds for lung V8, V10, V20, and MLD were 19.5% (the area under the curve [AUC]-0.629), 16.7% (AUC-0.629), 7.9% (AUC-0.621), and 5.2 Gy (AUC-0.623). The incidence of RP2 was found to be significantly high for values higher than the ROC threshold. The 4-year cumulative incidence of grade ≥ 2 RP in the V10 ≤ 16.7% vs V10 > 16.7% groups were 10% vs. 27% (p = 0.0013). Central tumor and interstitial pneumonia were significant risk factors for RP2 after SBRT. We recommend that lung V10 be kept below 16.7%.

Largest Real-World Data of Regional Nodal Irradiation Using Ultra-Hypofractionated 5-Fraction Adjuvant Radiation Therapy for Breast Cancer from a Single Institute in India

Safety data for ultra-hypofractionated (UHFRT) 5-daily fractions of the supraclavicular fossa (SCF) radiation therapy (RT) have been reported only on 384 patients treated in trial setting in UK-FAST-Forward (n = 286) and HYPORT study (n = 98). Internal Mammary nodal (IMN) RT has been reported only in 6 patients from HYPORT study. We report acute and late toxicities in largest real world regional nodal irradiation (RNI) cohort of not only with 5-daily but also with 5-weekly once RT regimen. Of 1435 patients (1463 breasts) who received 5-fraction RT in an IEC approved registry and prospectively followed, we report 999 consecutive cases receiving RNI with a median age of 49 years (IQR:42-56years). During pandemic all patients were treated with 5-fr regimens only to limit hospital visits whereas prior to and subsequently only in patients with advanced age or with issues precluding daily 15-20 treatments. Of these, 431 (43.1%) had locally advanced BC, and 280 (28%) patients presented with ≥cN2 disease. Median cT and pT sizes were 4cm (IQR:3-6cm) and 2.8cm (IQR:1.5-4cm) respectively. Tumor was Her2 positive in 290(29%) and TNBC in 220(22%). Of these 999 cases, 611 received NACT, 647 had mastectomy and 351 had breast conserving surgery (BCS). Simultaneous integrated tumor bed boost (SIB) was given in 341 (97.1%) of BCS cases. The fractionation used was 26 Gy/5-daily fractions (SIB = 32 Gy) in 762 and 28.5 Gy/ 5 once weekly fractionation (SIB = 33 Gy) in 232 cases. RNI included SCF in all 999 and IMN in 168 patients. Of the 831 cases not requiring IMN RT, 573 (70.4%) had 3D conformal RT (n = 573/831,70.4%) whereas Inverse-planned intensity modulated RT was used in 152/168 (90.4%) patients requiring IMN RT. All Mono-isocentric technique was used for all RNI cases treated with 3D CRT. Nearly half of the patients treated with SIB received additional boost dose with electrons (50.5%) and the remaining with IMRT. In these 999 patients treated with UHFRT the peak RTOG grade ≥II skin and pharyngeal toxicity was 7.2% and 8.1% respectively. Among the 341 BCS cases who received SIB with UHFRT, the RTOG acute grade II and III skin toxicity was seen in 6.6% and 0.3% cases respectively. The maximum skin toxicity at 2 weeks after completion of RT of grade ≥II was significantly higher with 5-weekly compared to daily regimen (16.1 vs 4.6, p<0.01). In contrast, the maximum pharyngeal toxicity of grade ≥II was significantly higher with 5-daily compared to weekly fractionation (8.8% vs 5.2%, p = 0.04). At median follow-up of 25 months (CI:23.6-26.3 months), none of our patients had developed symptomatic radiation pneumonitis, brachial plexopathy or any major cardiac event. Five-fraction adjuvant breast cancer RT is well tolerated with low acute toxicity burden even among patients requiring regional nodal irradiation. No brachial plexopathy was observed in cases treated with mono-isocentric RNI but longer follow-up is required to inform about the late toxicities and locoregional control rates.

Clinical and dosimetric factors for symptomatic radiation pneumonitis after stereotactic body radiotherapy for early-stage non-small cell lung cancer

The present study attempted to identify risk factors for symptomatic radiation pneumonitis (RP) after stereotactic body radiotherapy (SBRT) in patients with early-stage non-small cell lung cancer (NSCLC).We reviewed 244 patients with early-stage NSCLC treated with SBRT. The primary endpoint was the incidence of grade ≥2 RP. Gray's test was performed to examine the relationship between clinical risk factors and grade ≥2 RP, and the Fine-Gray model was used for a multivariate analysis. The effects of each dose parameter on grade ≥2 RP were evaluated with the Fine-Gray model and optimal thresholds were tested using receiver operating characteristic (ROC) curves.With a median follow-up period of 48 months, the 4-year cumulative incidence of grade ≥2 RP was 15.3%. Gray's test revealed that tumor size, a central tumor, interstitial pneumonia, and the biologically effective dose correlated with RP. In the multivariate analysis, a central tumor and interstitial pneumonia remained significant factors (p < 0.001, p = 0.002). Among dose parameters, the total lung volume (%) receiving at least 8 Gy (V8), V10, V20, and the mean lung dose correlated with RP (p = 0.012, 0.011, 0.022, and 0.014, respectively). The results of the Fine-Gray model and ROC curve analyses showed that V10 >16.7% was the best indicator of symptomatic RP among dose parameters.The present results suggest that a central tumor and interstitial pneumonia are independent risk factors for symptomatic RP and lung V10 ≤16.7% is recommended as the threshold in SBRT.

Effect of Interstitial Lung Abnormality on Concurrent Chemoradiotherapy-treated Stage III Non-small Cell Lung Cancer Patients.

Pre-treatment interstitial lung abnormality (ILA) is associated with post-cancer treatment adverse events and high mortality rate in lung cancer patients. This study aimed to assess whether ILA affects the survival and development of symptomatic radiation pneumonitis (RP) in unresectable stage III non-small cell lung cancer (NSCLC) patients who had undergone definitive concurrent chemoradiotherapy (CCRT). Data of stage III NSCLC patients who underwent definitive CCRT between January 2010 and November 2017 were retrospectively collected. Univariate and multivariate regression analyses were performed to evaluate the risk factors for symptomatic RP. The association between pre-treatment ILA and survival was assessed using Kaplan-Meier analysis with log-rank test and Cox proportional hazards regression. This study included 201 patients (188 men) of a mean age of 64.7±7.3 years. Pre-treatment ILA and fibrotic ILA were observed in 21.9% and 12.9% of the patients, respectively. Symptomatic RP (grade ≥2) occurred in 13.5% of the patients. Fibrotic ILA was a significant risk factor for grade ≥2 RP and grade ≥3 RP (p=0.004 and 0.033, respectively). The survival rate was significantly poorer in patients with fibrotic ILA than in those without ILA. Cox proportional hazards regression revealed that fibrotic ILA was an independent risk factor for mortality (p<0.001). Pre-treatment fibrotic ILA is significantly associated with symptomatic RP and poor survival in unresectable stage III NSCLC patients who have undergone definitive CCRT. CCRT should be cautiously performed in patients presenting pre-treatment fibrotic ILA to prevent adverse outcomes.

Radiation pneumonitis following Yttrium-90 radioembolization: A Korean multicenter study.

To report the incidence of radiation pneumonitis after radioembolization. In this retrospective study, from May 2009 to July 2021, 782 consecutive patients underwent radioembolization in two institutes. Medical internal radiation dose dosimetry and partition dosimetry were used for glass and resin Yttrium-90-labeled microspheres (90Y-microspheres), respectively. Medical records and radiological findings were retrospectively evaluated with emphasis on the symptomatic radiation pneumonitis. Of the 732 patients with lung shunt study and follow-up, 13 (1.8%) had symptomatic radiation pneumonitis and six patients died due to radiation pneumonitis. Of the 721 patients whose lung doses were calculated, 10 patients who were treated with glass (n = 5) and resin (n = 5) 90Y-microspheres had radiation pneumonitis. No significant statistical difference between glass and resin 90Y-microspheres (p = 0.304) was noted in terms of radiation pneumonitis incidence. Among the patients with radiation pneumonitis, all five patients treated with glass 90Y-microspheres had estimated lung doses > 29 Gy, whereas five patients treated with resin 90Y-microspheres had relatively wide range of lung dose reaching much lower value (13.21Gy). The present study suggests that radiation pneumonitis after radioembolization may occur even though the manufacturer's instructions are followed.

Institutional experience of using active breathing control for paediatric and teenage patients receiving thoraco-abdominal radiotherapy

IntroductionActive Breathing Control (ABC) is a motion management strategy that facilitates reproducible breath-hold for thoracic radiotherapy (RT), which may reduce radiation dose to organs at risk (OARs). Reduction of radiation-induced toxicity is of high importance in younger patients. However, there is little published literature on the feasibility of ABC in this group. The purpose of this study was to report our experience of using ABC for paediatric and teenage patients. MethodsPatients ≤18 years referred for thoracic RT using ABC at our centre from 2013–2021 were identified. Electronic records were retrospectively reviewed to obtain information on diagnosis, RT dose and technique, OAR dosimetry, tolerability of ABC, post-treatment imaging and early toxicity rates. Results12 patients completed RT and were able to comply with ABC during planning and for the duration of RT. Median age was 15.5 years (10–18 years). Diagnoses were: Hodgkin lymphoma (n = 5), mediastinal B-cell lymphoma (n = 1), Ewing sarcoma (n = 5) and rhabdomyosarcoma (n = 1). For mediastinal RT cases (n = 6), median dose delivered was 30.6Gy(19.8–40Gy), median mean heart dose was 11.4Gy(4.8–19.4Gy), median mean lung dose was 9.9Gy(5.7–14.5Gy) and mean lung V20 was 10.9%. For ipsilateral RT cases, (n = 6), median hemithorax and total doses to primary tumour were 18Gy(15–20Gy) and 52.2Gy(36–60Gy) respectively. Median mean heart dose was 19.5Gy(10.6–33.2Gy) and median mean lung dose was 17.7Gy(16.3–30.5Gy). Mean bilateral lung V20 was 39.6%. Median mean contralateral lung dose was 5.2Gy(3.5–11.6Gy) and mean contralateral lung V20 was 1.5%. At a median follow-up of 36 months, only 1 patient had symptomatic radiation pneumonitis having received further thoracic RT following relapse. ConclusionsABC is feasible and well tolerated in younger patients receiving RT. Children as young as 10 years are able to comply. Use of ABC results in OAR dosimetry which is comparable to similar data in adults and can facilitate RT for extensive thoracic sarcoma

Effect of hypofractionated radiotherapy on lung functions in breast cancer patients

Background Adjuvant hypofractionated radiotherapy (RT) used in the management of breast cancer cases, although reduce time and cost, may have serious effects due to the increased dose of radiation. Radiation-induced lung injury is an important side effect of thoracic radiation. Aim In our study, patients assessed by spirometry to detect acute changes in lung functions resulted from radiation exposure during the treatment of breast cancer. Patients and methods In this prospective study, 31 patients with breast cancer, who received adjuvant RT in Ain Shams University Hospitals, were assessed by spirometry before and 8 weeks after the end of RT. Radiation pneumonitis (RP) was graded using the Common Terminology Criteria for Adverse Events, version 5. Pulmonary function was evaluated by spirometry before and 8 weeks after finishing RT to detect changes in forced vital capacity (FVC), forced expiratory volume in the first second (FEV1), FEV1/FVC ratio, forced expiratory flow at 25–75% of FVC (FEF25%–75%), and FEF50% of . Results Five (16.1%) patients developed symptomatic RP. Significant reduction was noticed in FVC and FEV1, while FEV1/FVC ratio, FEF25%–75%, and FEF50% were not significantly affected. It was also observed that FEV1 was sensitive in anticipating RP. Conclusion Spirometry parameters, FEV1 and FVC, significantly decreased after 8 weeks of RT ending, without significant decrease in other parameters, favoring restrictive lung injury pattern. Since most cancer breast patients who developed RP were asymptomatic, spirometry was found to be beneficial in identifying patients with risk of radiation-induced lung injury (RP).

Ensemble Machine Learning Algorithm Using Clinical and Dosimetric Features to Predict Radiation Pneumonitis after Stereotactic Body Radiation Therapy (SBRT) for Lung Cancer

<h3>Purpose/Objective(s)</h3> Radiation pneumonitis (RP) is a significant cause of toxicity in patients receiving radiation therapy (RT) for lung cancer. Machine learning techniques have been utilized to develop models to predict RP, but prior efforts have largely focused on conventionally fractioned RT. The current study's aim is to add to the growing body of literature using machine learning to identify and verify important features related to RP post-RT and to generate an algorithm capable of predicting this adverse outcome. Additionally, this study is differentiated from prior efforts by focusing on SBRT rather than conventionally fractionated RT and using a combination of accessible dosimetric and clinical features, with the goal of creating a clinically useful model to predict RP risk. <h3>Materials/Methods</h3> The study utilized data from 201 lung cancer patients that were treated with SBRT between 2005 and 2015. Patient data including demographics, tumor characteristics, and dosimetric features were analyzed for association with symptomatic RP, defined as CTCAE v. 4.0 ≥ Grade 2. Prior to data modeling the chi-square test was used to rank important features. Data imbalance was corrected for using the Synthetic Minority Oversampling Technique (SMOTE), and commercial software was used to generate classification machine learning models based on the balanced dataset. Models were tested on the original dataset for classification accuracy, area under the curve (AUC), sensitivity, and specificity. The performance of several different algorithms was evaluated including Decision Trees, Discriminant Analysis, Logistic Regression, Naive Bayes Classifiers, Support Vector Machines, Nearest Neighbor Classifiers and Ensemble Classifiers. Each model utilized 10-fold cross-validation to prevent overfitting. <h3>Results</h3> Out of 201 patients receiving SBRT, 24 patients (11.9%) developed symptomatic RP. Based on chi-square test results, increased lung V12.5 (volume receiving 12.5 Gy), multiple tumor sites, prior RT to the thorax or lung surgery, right-sided tumor laterality, and former smoking status were selected as predictors in the machine learning models. After testing, Ensemble classifiers were found to be the most accurate overall. Of the Ensemble models, a Bagged Trees classifier had the most impressive results, correctly classifying 23 out of 24 cases of symptomatic RP. The model had an AUC of 0.93, overall accuracy of 91.5%, sensitivity of 95.8% and specificity of 91.0%. <h3>Conclusion</h3> A machine learning algorithm was developed to predict RP, utilizing a combination of 5 ranked dosimetric and clinical features. The model has an overall accuracy of 91.5% and an AUC of 0.93. The advantage of this model when compared to others is that it was generated using SBRT patient data, as opposed to standard fractionation RT, and easily accessible clinical and tumor characteristics. Future research will test the model's accuracy on an independent dataset and executing prospective studies to verify the model's clinical utility.

Risk of Radiation Pneumonitis in Patients Receiving Osimertinib and Thoracic Radiotherapy

Purpose/Objective(s)Osimertinib has become first-line standard of care for patients with non-small cell lung cancer (NSCLC) and EGFR-sensitive mutations. Radiotherapy use in the setting of osimertinib is becoming more common, often in the setting of oligo-metastatic/progressive disease or palliation. Given the increased rates of symptomatic radiation pneumonitis associated with first-generation EGFR inhibitors given with thoracic radiotherapy (TRT) (up to 40%), there is concern that similar risks exist for osimertinib, though this remains unclear. Given the greater EGFR-mutant selectivity of osimertinib, we hypothesized less pneumonitis risk as compared to older EGFR inhibitors with TRT.Materials/MethodsWe conducted a retrospective cohort study of consecutive patients with EGFR-mutated NSCLC receiving TRT and osimertinib within 30 days prior to TRT start at a single institution from November 2017 to October 2021. The timing of osimertinib receipt relative to the radiation course was recorded, including if osimertinib was given concurrently with TRT. Chart review was conducted to document pneumonitis attributed to radiation therapy within 12 months of TRT and severity was assessed via CTCAE v5.0 grade. Additionally, clinical, radiation, and dosimetric details were abstracted. The primary endpoint of Grade 2+ pneumonitis was evaluated with descriptive statistics. Associations between pneumonitis and osimertinib-TRT overlap along with mean lung V20 and V5 were evaluated with Chi-Square and one-tailed T-tests (α=0.05) as appropriate.ResultsAnalysis included 41 patients with median follow-up of 10.4 months (interquartile range: 5.4-22.6). Mean prescription BED (α/β=10) was 75.8Gy (standard deviation: 30.9 Gy) and 15 (36.6%) were treated with stereotactic TRT. All patients received 80 mg/day osimertinib PO. For 32 patients (78.0%), osimertinib was held at a median of 2 days prior to TRT and resumed at a median of 2 days after TRT. For 9 patients (22.0%), osimertinib was continued during TRT. One patient had a history of chronic obstructive pulmonary disease. Overall, 8 patients (19.5%) developed Grade 2+ pneumonitis (6 Grade 2, 1 Grade 3, 1 Grade 5) at median of 4.7 months (range: 3.1 – 6.9). No episodes of radiation pneumonitis occurred in the osimertinib-concurrent group. Pneumonitis was associated with increased lung V20 (mean: 16.2% vs 10.0%, P=0.038) and V5 (35.7% vs 24.0%, P=0.032). Two patients, both in the osimertinib-held group (6.3%) had central nervous system disease progression during TRT, one with symptomatic leptomeningeal disease.ConclusionIn this single-institution study, the rate of radiation pneumonitis in patients receiving TRT and osimertinib was comparable to historical controls of TRT alone, and concurrent osimertinib did not increase risk compared to holding during TRT. These findings provide useful information for patients and providers weighing the risks and benefits of overlapping TRT with osimertinib and should be validated in larger cohorts. Osimertinib has become first-line standard of care for patients with non-small cell lung cancer (NSCLC) and EGFR-sensitive mutations. Radiotherapy use in the setting of osimertinib is becoming more common, often in the setting of oligo-metastatic/progressive disease or palliation. Given the increased rates of symptomatic radiation pneumonitis associated with first-generation EGFR inhibitors given with thoracic radiotherapy (TRT) (up to 40%), there is concern that similar risks exist for osimertinib, though this remains unclear. Given the greater EGFR-mutant selectivity of osimertinib, we hypothesized less pneumonitis risk as compared to older EGFR inhibitors with TRT. We conducted a retrospective cohort study of consecutive patients with EGFR-mutated NSCLC receiving TRT and osimertinib within 30 days prior to TRT start at a single institution from November 2017 to October 2021. The timing of osimertinib receipt relative to the radiation course was recorded, including if osimertinib was given concurrently with TRT. Chart review was conducted to document pneumonitis attributed to radiation therapy within 12 months of TRT and severity was assessed via CTCAE v5.0 grade. Additionally, clinical, radiation, and dosimetric details were abstracted. The primary endpoint of Grade 2+ pneumonitis was evaluated with descriptive statistics. Associations between pneumonitis and osimertinib-TRT overlap along with mean lung V20 and V5 were evaluated with Chi-Square and one-tailed T-tests (α=0.05) as appropriate. Analysis included 41 patients with median follow-up of 10.4 months (interquartile range: 5.4-22.6). Mean prescription BED (α/β=10) was 75.8Gy (standard deviation: 30.9 Gy) and 15 (36.6%) were treated with stereotactic TRT. All patients received 80 mg/day osimertinib PO. For 32 patients (78.0%), osimertinib was held at a median of 2 days prior to TRT and resumed at a median of 2 days after TRT. For 9 patients (22.0%), osimertinib was continued during TRT. One patient had a history of chronic obstructive pulmonary disease. Overall, 8 patients (19.5%) developed Grade 2+ pneumonitis (6 Grade 2, 1 Grade 3, 1 Grade 5) at median of 4.7 months (range: 3.1 – 6.9). No episodes of radiation pneumonitis occurred in the osimertinib-concurrent group. Pneumonitis was associated with increased lung V20 (mean: 16.2% vs 10.0%, P=0.038) and V5 (35.7% vs 24.0%, P=0.032). Two patients, both in the osimertinib-held group (6.3%) had central nervous system disease progression during TRT, one with symptomatic leptomeningeal disease. In this single-institution study, the rate of radiation pneumonitis in patients receiving TRT and osimertinib was comparable to historical controls of TRT alone, and concurrent osimertinib did not increase risk compared to holding during TRT. These findings provide useful information for patients and providers weighing the risks and benefits of overlapping TRT with osimertinib and should be validated in larger cohorts.

EP16.04-032 Indoleamine 2,3-dioxygenase 1 (IDO1) Blood Metabolites May Improve Predictive Accuracy for Radiation Pneumonitis

Symptomatic radiation pneumonitis (RP) is a critical dose-limiting factor for patients with lung cancer who received definitive radiotherapy. The individual sensitivity of the RP has been observed from numerous studies, which is often associated with baseline lung tissue condition. However, the identified biomarkers were various among different investigations. Indoleamine 2,3-dioxygenase 1 (IDO1) plays a pivotal role in immunosuppression and has been proved to suppress inflammation in infectious and autoimmune pneumonia.

EP05.01-032 The Incidence of Brain Metastasis and Radiation Pneumonitis With Durvalumab After Chemoradiotherapy in Unresectable Stage III NSCLC

PACIFIC trial has manifested a lower incidence of new brain metastasis in the durvalumab group than in the placebo group of patients with unresectable stage III NSCLC. Nevertheless, there are few studies mainly focusing on the effect of durvalumab on brain progression. Patients who receive radiotherapy (RT) may have adverse effects like symptomatic RP (radiation pneumonitis) which could be a life-threatening when combined with drug induced pneumonitis. Because many clinicians hesitate to start durvalumab after concurrent CCRT.

EP05.01-033 Stimulation CT-Based Radiomics Predict Radiation Pneumonitis after Chemoradiotherapy in Locally Advanced NSCLC

This study aimed to establish machine learning model using radiomics features with region of interest (ROI) in treatment planning computed tomography (CT) images to predict symptomatic radiation pneumonitis(RP) (grad≥2) in patients with locally advance non-small cell lung cancer(NSCLC).

Symptomatic Radiation Pneumonitis in NSCLC Patients Receiving EGFR-TKIs and Concurrent Once-daily Thoracic Radiotherapy: Predicting the Value of Clinical and Dose-volume Histogram Parameters.

Background and objectivesThe incidence of symptomatic radiation pneumonitis (RP) and its relationship with dose-volume histogram (DVH) parameters in non-small cell lung cancer (NSCLC) patients receiving epidermal growth factor receptor-tyrosine kinase inhibitors (EGFR-TKIs) and concurrent once-daily thoracic radiotherapy (TRT) remain unclear. We aim to analyze the values of clinical factors and dose-volume histogram (DVH) parameters to predict the risk for symptomatic RP in these patients.MethodsBetween 2011 and 2019, we retrospectively analyzed and identified 85 patients who had received EGFR-TKIs and once-daily TRT simultaneously (EGFR-TKIs group) and 129 patients who had received concurrent chemoradiotherapy (CCRT group). The symptomatic RP was recorded according to the Common Terminology Criteria for Adverse Event (CTCAE) criteria (grade 2 or above). Statistical analyses were performed using SPSS 26.0.ResultsIn total, the incidences of symptomatic (grade≥2) and severe RP (grade≥3) were 43.5% (37/85) and 16.5% (14/85) in EGFR-TKIs group vs 27.1% (35/129) and 10.1% (13/129) in CCRT group respectively. After 1:1 ratio between EGFR-TKIs group and CCRT group was matched by propensity score matching, chi-square test suggested that the incidence of symptomatic RP in the MATCHED EGFR-TKIs group was higher than that in the matched CCRT group (χ2=4.469, P=0.035). In EGFR-TKIs group, univariate and multivariate analyses indicated that the percentage of ipsilateral lung volume receiving ≥30 Gy (ilV30) [odds ratio (OR): 1.163, 95%CI: 1.036-1.306, P=0.011] and the percentage of total lung volume receiving ≥20 Gy (tlV20) (OR: 1.171, 95%CI: 1.031-1.330, P=0.015), with chronic obstructive pulmonary disease (COPD) or not (OR: 0.158, 95%CI: 0.041-0.600, P=0.007), were independent predictors of symptomatic RP. Compared to patients with lower ilV30/tlV20 values (ilV30 and tlV20 < cut-off point values) and without COPD, patients with higher ilV30/tlV20 values (ilV30 and tlV20 > cut-off point values) and COPD had a significantly higher risk for developing symptomatic RP, with a hazard ratio (HR) of 1.350 (95%CI: 1.190-1.531, P < 0.001).ConclusionPatients receiving both EGFR-TKIs and once-daily TRT were more likely to develop symptomatic RP than patients receiving concurrent chemoradiotherapy. The ilV30, tlV20, and comorbidity of COPD may predict the risk of symptomatic RP among NSCLC patients receiving EGFR-TKIs and conventionally fractionated TRT concurrently.

Proton Beam Therapy in Elderly Patients With cT1-3N0M0 Non-small Cell Lung Cancer.

To investigate the outcomes of elderly patients with cT1-3N0M0 non-small cell lung cancer (NSCLC) undergoing proton beam therapy (PBT). Between 2009 and 2019, 110 patients receiving hypofractionated PBT for cT1-3N0M0 NSCLC were retrospectively reviewed. The median follow-up was 36.5 months (range=4.9-131.0 months). In the elderly group (80 years or older), the 3-year overall survival and progression-free survival rates were 79.8% and 73.9%, respectively, and the corresponding rates in the younger group were 80.5% and 61.2%, respectively. Grade 3 radiation pneumonitis (RP) was observed in 4.4% patients in the young group, whereas no grade 3 RP was observed in the elderly group. Age was not a risk factor for symptomatic RP. There were no significant differences in the survival and adverse events between the elderly and younger groups. PBT may be a reasonable approach for treating lung cancer in elderly patients with T1-3N0M0 NSCLC.

Symptomatic Radiation Pneumonitis After Stereotactic Body Radiation Therapy for Multiple Pulmonary Oligometastases or Synchronous Primary Lung Cancer

PurposeStereotactic body radiation therapy (SBRT) can be easily used for patients with tumors in various organs and is a promising local therapy for eradicating tumors in cancer patients. There is a rising clinical need for increasing knowledge of oligometastases in the treatment of multiple pulmonary tumors. This study aimed to explore the predictive factors for symptomatic radiation pneumonitis (RP) after SBRT for multiple pulmonary oligometastases or synchronous primary lung cancer (SPLC). Methods and MaterialsA total of 38 consecutive patients who had 2 or more pulmonary oligometastases (n = 21) or SPLC (n = 17) and who were treated with SBRT were investigated. Patient characteristics, tumor characteristics, and details of radiation therapy were retrospectively collected from a clinical database. The association between RP of grade 2 or worse (grade 2+ RP) and clinical or dosimetric factors was assessed using logistic regression analyses. ResultsThe tumors presented ipsilaterally in 24 patients and bilaterally in 14 patients. During the median follow-up period of 4.9 years, grade 2+ RP, grade 2 RP, and grade 3 RP were observed in 9 patients (23.7%), 7 patients (18.4%), and 2 patients (5.3%), respectively. The mean lung dose (MLD) and the volume of the normal lung receiving ≥5 Gy (lung V5Gy) were significantly associated with grade 2+ RP (P = .023 and P = .012, respectively). The logistic model showed that 20% and 50% of the predicted probability of grade 2+ RP were 6.1 Gy and 9.1 Gy for MLD and 31.6 % and 42.8% for lung V5Gy, respectively. ConclusionAlthough further investigation is required to validate the metrics and establish reliable dose constraints, the dose-volume metrics for the normal lung could be predictive of the development of grade 2+ RP after SBRT for multiple pulmonary oligometastases or SPLCs.