Enter Note Done
Decrease font size Increase font size

Use of machine learning for prediction of ocular conservation and visual outcomes after proton beam radiotherapy for choroidal melanoma

View Session View Presentation
Add to Schedule Print Abstract

Abstract Number: 962

AuthorBlock: Stylianos Serghiou1,2, Bertil E. Damato2,4, Armin R. Afshar2,3
1Stanford University School of Medicine, Stanford, California, United States; 2Ocular Oncology Service, Department of Ophthalmology, University of California, San Francisco, San Francisco, California, United States; 3Helen Diller Family Comprehensive Cancer Center, University of California, San Francisco, San Francisco, California, United States; 4Oxford Eye Hospital and the Nuffield Department of Clinical Neurosciences, University of Oxford, , United Kingdom;

DisclosureBlock: Stylianos Serghiou, None; Bertil E. Damato, None; Armin R. Afshar, None;

Purpose
While local control rates for proton beam radiotherapy (PBRT) treatment of choroidal malignant melanoma (CMM) are well known, visual acuity outcomes can vary, and are currently roughly predicted by ophthalmologists based on tumor size and location. The purpose of this study is to apply machine learning methods on a large CMM patient cohort, to predict visual acuity and ocular salvage after PBRT.

Methods
This was a prospective cohort study of 1022 adult CMM patients. Our database of 169 features included patient demographics, medical history, ophthalmic history, tumor dimensions, tumor-node-metastasis (TNM) stage, histology, genetics, radiation dosimetry and visual acuity (VA). We predicted final VA and enucleation using cross-validation (CV) to tune and fit the following machine learning methods: Elastic Net, Bayesian Generative Learning, Gradient Tree Boosting and Deep Neural Networks. We finally evaluated our models and a stacked ensemble of our models using cross-validated R2 for VA and cross-validated area under the curve (CV-AUC) for enucleation.

Results
Our cohort consisted of otherwise predominantly healthy adults (834/1022, 82%) with a median age of 59 years (Interquartile Range (IQR), 48-68 years) followed for a median of 8 years (IQR, 3-13 years). Most patients presented with TNM Stage I disease (500/1022, 49%) and VA between 6/5-6/12 (700/1022, 69%). Final vision varied substantially from 6/5-6/12 (384/1022, 38%) to hand-motions or less (114/1022, 11%); 76 (7%) received secondary enucleation. VA was best predicted by Gradient Tree Boosting with a CV-R2 of 28% (95% Confidence Interval (CI), 19-38%) with dosimetry values and CV-R2 of 25% (95% CI, 18-32%) without. The top three most important variables were tumor thickness, radiation received by the macula and radiation received by the globe volume. Enucleation was best predicted by the Elastic Net with a CV-AUC of 80% (95% CI, 72-87%); using dosimetry values did not improve predictive ability. The top three most important variables were tumor thickness, smallest tumor diameter and TNM stage.

Conclusions
Our approach identified models with high predictive ability for enucleation and moderate predictive ability for final visual acuity. Variables related to physical extent of tumor and radiation received appeared most important in predicting enucleation and VA, respectively.

Layman Abstract (optional): Provide a 50-200 word description of your work that non-scientists can understand. Describe the big picture and the implications of your findings, not the study itself and the associated details.