Aldraimli, M, Osman, S, Grishchuck, D, Ingram, S, Lyon, R, Mistry, A, Oliveira, J, Samuel, R, Shelley, LEA, Soria, D, Dwek, MV, Aguado-Barrera, ME, Azria, D, Chang-Claude, J, Dunning, A, Giraldo, A, Green, S, Gutiérrez-Enríquez, S, Herskind, C, van Hulle, H et al, Lambrecht, M, Lozza, L, Rancati, T, Reyes, V, Rosenstein, BS, de Ruysscher, D, de Santis, MC, Seibold, P, Sperk, E, Symonds, RP, Stobart, H, Taboada-Valadares, B, Talbot, CJ, Vakaet, VJL, Vega, A, Veldeman, L, Veldwijk, MR, Webb, A, Weltens, C, West, CM, Chaussalet, TJ and Rattay, T (2022) Development and Optimization of a Machine-Learning Prediction Model for Acute Desquamation After Breast Radiation Therapy in the Multicenter REQUITE Cohort. Advances in Radiation Oncology, 7 (3). ISSN 2452-1094

Preview

Text Development and optimization of a machine learning predicting model for acute desquamation after breast radiation therapy in the multicenter REQUITE cohort.pdf - Published Version Available under License Creative Commons Attribution. Download (2MB) | Preview

Abstract

Purpose
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.

Methods and Materials
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.

Results
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.

Conclusions
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.

Item Type:	Article
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software R Medicine > R Medicine (General)
Divisions:	Computer Science & Mathematics
Publisher:	Elsevier BV
SWORD Depositor:	A Symplectic
Date Deposited:	15 Sep 2023 13:36
Last Modified:	15 Sep 2023 13:45
DOI or ID number:	10.1016/j.adro.2021.100890
URI:	https://researchonline.ljmu.ac.uk/id/eprint/21457

View Item