Random forests to predict rectal toxicity following prostate cancer radiation therapy

Juan D. Ospina, Jian Zhu, Ciprian Chira, Alberto Bossi, Jean B. Delobel, Véronique Beckendorf, Bernard Dubray, Jean Léon Lagrange, Juan C. Correa, Antoine Simon, Oscar Acosta, Renaud De Crevoisier*

*Autor correspondiente de este trabajo

Producción científicarevisión exhaustiva

48 Citas (Scopus)


Purpose To propose a random forest normal tissue complication probability (RF-NTCP) model to predict late rectal toxicity following prostate cancer radiation therapy, and to compare its performance to that of classic NTCP models. Methods and Materials Clinical data and dose-volume histograms (DVH) were collected from 261 patients who received 3-dimensional conformal radiation therapy for prostate cancer with at least 5 years of follow-up. The series was split 1000 times into training and validation cohorts. A RF was trained to predict the risk of 5-year overall rectal toxicity and bleeding. Parameters of the Lyman-Kutcher-Burman (LKB) model were identified and a logistic regression model was fit. The performance of all the models was assessed by computing the area under the receiving operating characteristic curve (AUC). Results The 5-year grade ≥2 overall rectal toxicity and grade ≥1 and grade ≥2 rectal bleeding rates were 16%, 25%, and 10%, respectively. Predictive capabilities were obtained using the RF-NTCP model for all 3 toxicity endpoints, including both the training and validation cohorts. The age and use of anticoagulants were found to be predictors of rectal bleeding. The AUC for RF-NTCP ranged from 0.66 to 0.76, depending on the toxicity endpoint. The AUC values for the LKB-NTCP were statistically significantly inferior, ranging from 0.62 to 0.69. Conclusions The RF-NTCP model may be a useful new tool in predicting late rectal toxicity, including variables other than DVH, and thus appears as a strong competitor to classic NTCP models.

Idioma originalEnglish
Páginas (desde-hasta)1024-1031
Número de páginas8
PublicaciónInternational Journal of Radiation Oncology Biology Physics
EstadoPublished - 1 ago 2014
Publicado de forma externa

Nota bibliográfica

Copyright © 2014 Elsevier Inc. All rights reserved.

All Science Journal Classification (ASJC) codes

  • Radiación
  • Oncología
  • Radiología, medicina nuclear y obtención de imágenes
  • Investigación sobre el cáncer


Profundice en los temas de investigación de 'Random forests to predict rectal toxicity following prostate cancer radiation therapy'. En conjunto forman una huella única.

Citar esto