Journal Article

DKFZ-2022-01162

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Development and Optimization of a Machine-Learning Prediction Model for Acute Desquamation After Breast Radiation Therapy in the Multicenter REQUITE Cohort.

Aldraimli, M. ; Osman, S. ; Grishchuck, D. ; Ingram, S. ; Lyon, R. ; Mistry, A. ; Oliveira, J. ; Samuel, R. ; Shelley, L. E. A. ; Soria, D. ; Dwek, M. V. ; Aguado-Barrera, M. E. ; Azria, D. ; Chang-Claude, J.DKFZ* ; Dunning, A. ; Giraldo, A. ; Green, S. ; Gutiérrez-Enríquez, S. ; Herskind, C. ; van Hulle, H. ; Lambrecht, M. ; Lozza, L. ; Rancati, T. ; Reyes, V. ; Rosenstein, B. S. ; de Ruysscher, D. ; de Santis, M. C. ; Seibold, P.DKFZ* ; Sperk, E. ; Symonds, R. P. ; Stobart, H. ; Taboada-Valadares, B. ; Talbot, C. J. ; Vakaet, V. J. L. ; Vega, A. ; Veldeman, L. ; Veldwijk, M. R. ; Webb, A. ; Weltens, C. ; West, C. M. ; Chaussalet, T. J. ; Rattay, T. ; consortium, R. (Collaboration Author)

2022
Elsevier Amsterdam

This record in other databases:  

Please use a persistent id in citations: doi:10.1016/j.adro.2021.100890

Abstract: Some patients with breast cancer treated by surgery and radiation therapy experience clinically significant toxicity, which may adversely affect cosmesis and quality of life. There is a paucity of validated clinical prediction models for radiation toxicity. We used machine learning (ML) algorithms to develop and optimise a clinical prediction model for acute breast desquamation after whole breast external beam radiation therapy in the prospective multicenter REQUITE cohort study.Using demographic and treatment-related features (m = 122) from patients (n = 2058) at 26 centers, we trained 8 ML algorithms with 10-fold cross-validation in a 50:50 random-split data set with class stratification to predict acute breast desquamation. Based on performance in the validation data set, the logistic model tree, random forest, and naïve Bayes models were taken forward to cost-sensitive learning optimisation.One hundred and ninety-two patients experienced acute desquamation. Resampling and cost-sensitive learning optimisation facilitated an improvement in classification performance. Based on maximising sensitivity (true positives), the 'hero' model was the cost-sensitive random forest algorithm with a false-negative: false-positive misclassification penalty of 90:1 containing m = 114 predictive features. Model sensitivity and specificity were 0.77 and 0.66, respectively, with an area under the curve of 0.77 in the validation cohort.ML algorithms with resampling and cost-sensitive learning generated clinically valid prediction models for acute desquamation using patient demographic and treatment features. Further external validation and inclusion of genomic markers in ML prediction models are worthwhile, to identify patients at increased risk of toxicity who may benefit from supportive intervention or even a change in treatment plan.

---

Contributing Institute(s):

1. C020 Epidemiologie von Krebs (C020)

Research Program(s):

1. 313 - Krebsrisikofaktoren und Prävention (POF4-313) (POF4-313)

Appears in the scientific report 2022

---

Database coverage:
; ; ; Article Processing Charges ; Clarivate Analytics Master Journal List ; DOAJ Seal ; Emerging Sources Citation Index ; Fees ; SCOPUS ; Web of Science Core Collection

---