José Marcio Luna1, Hann-Hsiang Chao2, Eric S Diffenderfer2, Gilmer Valdes3, Chidambaram Chinniah4, Grace Ma2, Keith A Cengel2, Timothy D Solberg3, Abigail T Berman2, Charles B Simone5. 1. Department of Radiation Oncology, University of Pennsylvania, Philadelphia, United States. Electronic address: Jose.Luna@uphs.upenn.edu. 2. Department of Radiation Oncology, University of Pennsylvania, Philadelphia, United States. 3. Department of Radiation Oncology, University of California San Francisco, United States. 4. Albany Medical College, United States. 5. Department of Radiation Oncology, University of Maryland School of Medicine, Baltimore, United States.
Abstract
BACKGROUND AND PURPOSE: Radiation pneumonitis (RP) is a radiotherapy dose-limiting toxicity for locally advanced non-small cell lung cancer (LA-NSCLC). Prior studies have proposed relevant dosimetric constraints to limit this toxicity. Using machine learning algorithms, we performed analyses of contributing factors in the development of RP to uncover previously unidentified criteria and elucidate the relative importance of individual factors. MATERIALS AND METHODS: We evaluated 32 clinical features per patient in a cohort of 203 stage II-III LA-NSCLC patients treated with definitive chemoradiation to a median dose of 66.6 Gy in 1.8 Gy daily fractions at our institution from 2008 to 2016. Of this cohort, 17.7% of patients developed grade ≥2 RP. Univariate analysis was performed using trained decision stumps to individually analyze statistically significant predictors of RP and perform feature selection. Applying Random Forest, we performed multivariate analysis to assess the combined performance of important predictors of RP. RESULTS: On univariate analysis, lung V20, lung mean, lung V10 and lung V5 were found to be significant RP predictors with the greatest balance of specificity and sensitivity. On multivariate analysis, Random Forest (AUC = 0.66, p = 0.0005) identified esophagus max (20.5%), lung V20 (16.4%), lung mean (15.7%) and pack-year (14.9%) as the most common primary differentiators of RP. CONCLUSIONS: We highlight Random Forest as an accurate machine learning method to identify known and new predictors of symptomatic RP. Furthermore, this analysis confirms the importance of lung V20, lung mean and pack-year as predictors of RP while also introducing esophagus max as an important RP predictor.
BACKGROUND AND PURPOSE: Radiation pneumonitis (RP) is a radiotherapy dose-limiting toxicity for locally advanced non-small cell lung cancer (LA-NSCLC). Prior studies have proposed relevant dosimetric constraints to limit this toxicity. Using machine learning algorithms, we performed analyses of contributing factors in the development of RP to uncover previously unidentified criteria and elucidate the relative importance of individual factors. MATERIALS AND METHODS: We evaluated 32 clinical features per patient in a cohort of 203 stage II-III LA-NSCLCpatients treated with definitive chemoradiation to a median dose of 66.6 Gy in 1.8 Gy daily fractions at our institution from 2008 to 2016. Of this cohort, 17.7% of patients developed grade ≥2 RP. Univariate analysis was performed using trained decision stumps to individually analyze statistically significant predictors of RP and perform feature selection. Applying Random Forest, we performed multivariate analysis to assess the combined performance of important predictors of RP. RESULTS: On univariate analysis, lung V20, lung mean, lung V10 and lung V5 were found to be significant RP predictors with the greatest balance of specificity and sensitivity. On multivariate analysis, Random Forest (AUC = 0.66, p = 0.0005) identified esophagus max (20.5%), lung V20 (16.4%), lung mean (15.7%) and pack-year (14.9%) as the most common primary differentiators of RP. CONCLUSIONS: We highlight Random Forest as an accurate machine learning method to identify known and new predictors of symptomatic RP. Furthermore, this analysis confirms the importance of lung V20, lung mean and pack-year as predictors of RP while also introducing esophagus max as an important RP predictor.
Authors: Narek Shaverdian; Michael D Offin; Andreas Rimner; Annemarie F Shepherd; Abraham J Wu; Charles M Rudin; Matthew D Hellmann; Jamie E Chaft; Daniel R Gomez Journal: Radiother Oncol Date: 2019-11-28 Impact factor: 6.280
Authors: Ana Barragán-Montero; Umair Javaid; Gilmer Valdés; Dan Nguyen; Paul Desbordes; Benoit Macq; Siri Willems; Liesbeth Vandewinckele; Mats Holmström; Fredrik Löfman; Steven Michiels; Kevin Souris; Edmond Sterpin; John A Lee Journal: Phys Med Date: 2021-05-09 Impact factor: 2.685
Authors: Annemarie F Shepherd; Michelle Iocolano; Jonathan Leeman; Brandon S Imber; Aaron T Wild; Michael Offin; Jamie E Chaft; James Huang; Andreas Rimner; Abraham J Wu; Daphna Y Gelblum; Narek Shaverdian; Charles B Simone; Daniel R Gomez; Ellen D Yorke; Andrew Jackson Journal: Pract Radiat Oncol Date: 2020-10-14
Authors: José Marcio Luna; Hann-Hsiang Chao; Russel T Shinohara; Lyle H Ungar; Keith A Cengel; Daniel A Pryma; Chidambaram Chinniah; Abigail T Berman; Sharyn I Katz; Despina Kontos; Charles B Simone; Eric S Diffenderfer Journal: Clin Transl Radiat Oncol Date: 2020-03-24
Authors: José Marcio Luna; Efstathios D Gennatas; Lyle H Ungar; Eric Eaton; Eric S Diffenderfer; Shane T Jensen; Charles B Simone; Jerome H Friedman; Timothy D Solberg; Gilmer Valdes Journal: Proc Natl Acad Sci U S A Date: 2019-09-16 Impact factor: 11.205