Show simple item record

dc.contributor.authorAldraimli, Mahmoud
dc.contributor.authorOsman, Sarah
dc.contributor.authorGrishchuck, Diana
dc.contributor.authorIngram, Samuel
dc.contributor.authorLyon, Robert
dc.contributor.authorMistry, Anil
dc.contributor.authorOliveira, Jorge
dc.contributor.authorSamuel, Robert
dc.contributor.authorShelley, Leila EA
dc.contributor.authorSoria, Daniele
dc.contributor.authorDwek, Miriam V
dc.contributor.authorAguado-Barrera, Miguel E
dc.contributor.authorAzria, David
dc.contributor.authorChang-Claude, Jenny
dc.contributor.authorDunning, Alison
dc.contributor.authorGiraldo, Alexandra
dc.contributor.authorGreen, Sheryl
dc.contributor.authorGutiérrez-Enríquez, Sara
dc.contributor.authorHerskind, Carsten
dc.contributor.authorvan Hulle, Hans
dc.contributor.authorLambrecht, Maarten
dc.contributor.authorLozza, Laura
dc.contributor.authorRancati, Tiziana
dc.contributor.authorReyes, Victoria
dc.contributor.authorRosenstein, Barry S
dc.contributor.authorde Ruysscher, Dirk
dc.contributor.authorde Santis, Maria C
dc.contributor.authorSeibold, Petra
dc.contributor.authorSperk, Elena
dc.contributor.authorSymonds, R Paul
dc.contributor.authorStobart, Hilary
dc.contributor.authorTaboada-Valadares, Begoña
dc.contributor.authorTalbot, Christopher J
dc.contributor.authorVakaet, Vincent JL
dc.contributor.authorVega, Ana
dc.contributor.authorVeldeman, Liv
dc.contributor.authorVeldwijk, Marlon R
dc.contributor.authorWebb, Adam
dc.contributor.authorWeltens, Caroline
dc.contributor.authorWest, Catharine M
dc.contributor.authorChaussalet, Thierry J
dc.contributor.authorRattay, Tim
dc.contributor.authorREQUITE consortium
dc.description.abstractPurpose: 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.
dc.publisherElsevier BV
dc.rightsAttribution 4.0 International
dc.sourceessn: 2452-1094
dc.sourcenlmid: 101677247
dc.titleDevelopment and Optimization of a Machine-Learning Prediction Model for Acute Desquamation After Breast Radiation Therapy in the Multicenter REQUITE Cohort.
prism.publicationNameAdv Radiat Oncol
dc.contributor.orcidDwek, Miriam V [0000-0001-7184-2932]
dc.contributor.orcidAguado-Barrera, Miguel E [0000-0002-7822-6726]
dc.contributor.orcidChaussalet, Thierry J [0000-0001-5507-6158]
pubs.funder-project-idChief Scientist Office (TCS/17/26)

Files in this item


This item appears in the following Collection(s)

Show simple item record

Attribution 4.0 International
Except where otherwise noted, this item's licence is described as Attribution 4.0 International