Predicting radiation pneumonitis in locally advanced stage II–III non-small cell lung cancer using machine learning

Luna, José Marcio; Chao, Hann‐Hsiang; Diffenderfer, Eric; Valdés, Gilmer; Chinniah, C.; Ma, Grace; Cengel, Keith A.; Solberg, Timothy D.; Berman, Abigail T.; Simone, Charles B.

doi:10.1016/j.radonc.2019.01.003

Cited by 73 publications

(54 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…random forest as an accurate method to identify known and new predictors of symptomatic radiation pneumonitis. 16 Analysis of our institute's data of 92 unresectable stage III NSCLC patients who underwent definite chemoradiation revealed a median OS of 26 months and a 2-year OS of 53.3%, consistent with the known survival rates in other series. 2 This cohort of patients belonged to different stage subgroups within stage III (►Table 1), treated with different radiotherapy techniques (at the treating physician's discretion, availability of technology, or patient related logistic constraints), varying tumor doses, over a range of treatment time and variable positron emission tomography (PET) response after CRT.…”

Section: Discussionsupporting

confidence: 85%

Identifying Prognostic Groups Using Machine Learning Tools in Patients Undergoing Chemoradiation for Inoperable Locally Advanced Nonsmall Cell Lung Carcinoma

Pahuja

Chufal

Ahmad

et al. 2019

ASJO

View full text Add to dashboard Cite

Introduction Unresectable stage III nonsmall cell lung cancer (NSCLC) continues to have dismal 5-year overall survival (OS) rate. However, a subset of the patients treated with chemoradiation show significantly better outcome. Prediction of treatment outcome can be improved by utilizing machine learning tools, such as cluster analysis (CA), and is capable of identifying complex interactions among many variables. We have utilized CA to identify a cluster with good prognosis within stage III NSCLC. Materials and Methods Retrospective analysis of treatment outcomes was done for 92 patients who underwent chemoradiation for inoperable locally advanced NSCLC from 2012 to 2018. Using various patient- and treatment-related variables, an exploratory factor analysis was performed to extract factors with eigenvalue > 1. An appropriate number of homogeneous groups were identified using agglomerative hierarchical cluster analysis. Further K-mean cluster analysis was applied to classify each patient into their homogeneous clusters. The newly formed cluster variable was used as an independent variable to estimate survival over time using Kaplan–Meier method. Results With a median follow-up of 18 months, median OS was 14 months. Using CA, three prognostic clusters were obtained. Cluster 2 with 36 patients had a median OS of 36 months, whereas Cluster 1 with 34 patients had a median OS of 20 months (p = 0.004). Conclusion A cluster could thus be identified with a relatively good prognosis within stage III NSCLC. Using CA, we have attempted to create a model which may provide more specific prognostic information in addition to that provided by tumor node metastasis-based models.

show abstract

Section: Discussionsupporting

confidence: 85%

Identifying Prognostic Groups Using Machine Learning Tools in Patients Undergoing Chemoradiation for Inoperable Locally Advanced Nonsmall Cell Lung Carcinoma

Pahuja

Chufal

Ahmad

et al. 2019

ASJO

View full text Add to dashboard Cite

show abstract

“…Given the result from our machine learning analysis that none of the 35 features analyzed performed better than a random classifier, this suggests that our currently utilized clinical, demographic, and dosimetric features could be inadequate to reliably predict radiation esophagitis. One can conclude that we are not currently collecting and capturing the appropriate features to allow a machine learning workflow to predict grade 3 radiation esophagitis, as we were successfully able to do when using machine learning to predict for pneumonitis in LA-NSCLC [41] and chest wall toxicity in early stage NSCLC [42]. As such, we encourage other investigators to explore and develop new markers directed at this toxicity.…”

Section: Discussionmentioning

confidence: 98%

Machine learning highlights the deficiency of conventional dosimetric constraints for prevention of high-grade radiation esophagitis in non-small cell lung cancer treated with chemoradiation

Luna

Chao

Shinohara

et al. 2020

Clinical and Translational Radiation Oncology

Self Cite

View full text Add to dashboard Cite

a b s t r a c tBackground and Purpose: Radiation esophagitis is a clinically important toxicity seen with treatment for locally-advanced non-small cell lung cancer. There is considerable disagreement among prior studies in identifying predictors of radiation esophagitis. We apply machine learning algorithms to identify factors contributing to the development of radiation esophagitis to uncover previously unidentified criteria and more robust dosimetric factors. Materials and Methods: We used machine learning approaches to identify predictors of grade 3 radiation esophagitis in a cohort of 202 consecutive locally-advanced non-small cell lung cancer patients treated with definitive chemoradiation from 2008 to 2016. We evaluated 35 clinical features per patient grouped into risk factors, comorbidities, imaging, stage, histology, radiotherapy, chemotherapy and dosimetry. Univariate and multivariate analyses were performed using a panel of 11 machine learning algorithms combined with predictive power assessments. Results: All patients were treated to a median dose of 66.6 Gy at 1.8 Gy per fraction using photon (89.6%) and proton (10.4%) beam therapy, most often with concurrent chemotherapy (86.6%). 11.4% of patients developed grade 3 radiation esophagitis. On univariate analysis, no individual feature was found to predict radiation esophagitis (AUC range 0.45-0.55, p 0.07). In multivariate analysis, all machine learning algorithms exhibited poor predictive performance (AUC range 0.46-0.56, p 0.07). Conclusions: Contemporary machine learning algorithms applied to our modern, relatively large institutional cohort could not identify any reliable predictors of grade 3 radiation esophagitis. Additional patients are needed, and novel patient-specific and treatment characteristics should be investigated to develop clinically meaningful methods to mitigate this survival altering toxicity.

show abstract

“…The difference of V5 was insignificant for right, left, and bilateral lung. Considering the toxicity of radiotherapy in the lung, Luna et al (18) reported that the lung V5 (>43.6%) could predict the presence of radiation pneumonitis consistently. The mean V5 values of manually and automatically delineated bilateral lung were <43.6%, which implies a lower risk of severe radiation pneumonitis in this study.…”

Section: Discussionmentioning

confidence: 99%

Evaluation of Automatic Segmentation Model With Dosimetric Metrics for Radiotherapy of Esophageal Cancer

et al. 2020

View full text Add to dashboard Cite

Results: Average DSC values were greater than 0.92 except for the spinal cord (0.82), and average MDA values were <0.90 mm except for the heart (1.74 mm). Eleven of the 20 dosimetric metrics of the OARs were not significant (P > 0.05). Although there were significant differences (P < 0.05) for the spinal cord (D2%), left lung (V10, V20, V30, and mean dose), and bilateral lung (V10, V20, V30, and mean dose), their absolute differences were small and acceptable for the clinic. The maximum dosimetric metrics differences of OARs between manual and automatic delineations were D2% = 0.35 Gy for the spinal cord and V30 = 0.4% for the bilateral lung, which were within the clinical criteria in this study. Conclusion: Dosimetric metrics were proposed to evaluate the automatic delineation in radiotherapy planning of esophageal cancer. Consequently, the automatic delineation could substitute the manual delineation for esophageal cancer radiotherapy planning based on the dosimetric evaluation in this study.

show abstract

Predicting radiation pneumonitis in locally advanced stage II–III non-small cell lung cancer using machine learning

Cited by 73 publications

References 35 publications

Identifying Prognostic Groups Using Machine Learning Tools in Patients Undergoing Chemoradiation for Inoperable Locally Advanced Nonsmall Cell Lung Carcinoma

Identifying Prognostic Groups Using Machine Learning Tools in Patients Undergoing Chemoradiation for Inoperable Locally Advanced Nonsmall Cell Lung Carcinoma

Machine learning highlights the deficiency of conventional dosimetric constraints for prevention of high-grade radiation esophagitis in non-small cell lung cancer treated with chemoradiation

Evaluation of Automatic Segmentation Model With Dosimetric Metrics for Radiotherapy of Esophageal Cancer

Contact Info

Product

Resources

About