Premium
Sci‐Thur AM: YIS – 10: Modeling Metastasis after Lung SBRT Using Bayesian Network Averaging
Author(s) -
Diamant André,
Seuntjens Jan,
El Naqa Issam,
Ybarra Norma
Publication year - 2016
Publication title -
medical physics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.473
H-Index - 180
eISSN - 2473-4209
pISSN - 0094-2405
DOI - 10.1118/1.4961760
Subject(s) - bayesian probability , markov chain monte carlo , computer science , metastasis , bayesian network , medicine , biomarker , receiver operating characteristic , artificial intelligence , machine learning , cancer , biology , biochemistry
Purpose: The prediction of metastasis after a patient receives lung SBRT has proven to be challenging, due to the complex interactions between an individual's biology and dose‐volume metrics. The aim of this study is to use a Bayesian network approach to uncover possible interactions between an individual patient's characteristics and generate a robust model capable of predicting metastasis. Methods: We investigated a cohort of 32 prospective patients from multiple institutions whom had received curative SBRT to the lung. The number of patients exhibiting metastasis within 6 months of treatment was observed to be 6 (event rate of 19%). The serum concentration of 5 relevant biomarkers was measured pre‐treatment. A total of 21 variables were analyzed including: dose‐volume metrics with BED (biologically effective dose) correction and clinical variables. A Markov Chain Monte Carlo technique estimated the posterior probability distribution of the potential graphical structures. The probability of metastasis was then estimated by averaging the top 100 graphs and applying Baye's rule. Results: The optimal Bayesian model generated throughout this study incorporated the PTV volume, the serum concentration of the biomarker EGFR (epidermal growth factor receptor) and prescription BED. This predictive model recorded an area under the receiver operating characteristic curve of 0.94(1), providing better performance compared to competing methods in the literature. Conclusion: The use of biomarkers in conjunction with dose‐volume metrics allows for the generation of a robust predictive model. The results of this report demonstrate that it is possible to accurately model whether a patient will develop metastasis within 6 months of treatment.