Open AccessExploratory analysis using machine learning to predict for chest wall pain in patients with stage I non‐small‐cell lung cancer treated with stereotactic body radiation therapy
Author(s) -
Chao HannHsiang,
Valdes Gilmer,
Luna Jose M.,
Heskel Marina,
Berman Abigail T.,
Solberg Timothy D.,
Simone Charles B.
Publication year - 2018
Publication title -
journal of applied clinical medical physics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.83
H-Index - 48
ISSN - 1526-9914
DOI - 10.1002/acm2.12415
Subject(s) - medicine , multivariate analysis , lung cancer , univariate analysis , radiosurgery , radiation therapy , multivariate statistics , univariate , nuclear medicine , stage (stratigraphy) , radiology , lung , machine learning , computer science , paleontology , biology
Background and purpose Chest wall toxicity is observed after stereotactic body radiation therapy ( SBRT ) for peripherally located lung tumors. We utilize machine learning algorithms to identify toxicity predictors to develop dose–volume constraints. Materials and methods Twenty‐five patient, tumor, and dosimetric features were recorded for 197 consecutive patients with Stage I NSCLC treated with SBRT , 11 of whom (5.6%) developed CTCAE v4 grade ≥2 chest wall pain. Decision tree modeling was used to determine chest wall syndrome ( CWS ) thresholds for individual features. Significant features were determined using independent multivariate methods. These methods incorporate out‐of‐bag estimation using Random forests ( RF ) and bootstrapping (100 iterations) using decision trees. Results Univariate analysis identified rib dose to 1 cc < 4000 cG y ( P = 0.01), chest wall dose to 30 cc < 1900 cG y ( P = 0.035), rib Dmax < 5100 cG y ( P = 0.05) and lung dose to 1000 cc < 70 cG y ( P = 0.039) to be statistically significant thresholds for avoiding CWS . Subsequent multivariate analysis confirmed the importance of rib dose to 1 cc, chest wall dose to 30 cc, and rib Dmax. Using learning‐curve experiments, the dataset proved to be self‐consistent and provides a realistic model for CWS analysis. Conclusions Using machine learning algorithms in this first of its kind study, we identify robust features and cutoffs predictive for the rare clinical event of CWS . Additional data in planned subsequent multicenter studies will help increase the accuracy of multivariate analysis.