HDR Salvage Brachytherapy: Multiple Hypothesis Testing vs Machine Learning Analysis

Publication date: Available online 13 March 2018
Source:International Journal of Radiation Oncology*Biology*Physics
Author(s): Gilmer Valdes, Albert J. Chang, Yannet Interian, Kenton Owen, Shane T. Jensen, Lyle H. Ungar, Adam Cunnan, Timothy D. Solberg, I-Chow Hsu

Teaser

Approximately only 50% of patients benefit from Salvage High Dose Rate Brachytherapy (sHDRB) with the majority of second recurrences occurring distantly. Therefore, a better patient selection before sHDRB is critical. Using Machine learning we found that patients with a Fraction of Positive Cores > 0.35 and a Disease Free Interval < 4.12 years after their initial radiation treatment experienced a higher failure rate after salvage HDRB of 0.75 vs 0.38 for the rest of the population.


http://ift.tt/2tPYmJk