Larynx cancer survival model developed through open-source federated learning

TY - JOUR

T1 - Larynx cancer survival model developed through open-source federated learning

AU - Rønn Hansen, Christian

AU - Price, Gareth

AU - Field, Matthew

AU - Sarup, Nis

AU - Zukauskaite, Ruta

AU - Johansen, Jørgen

AU - Eriksen, Jesper Grau

AU - Aly, Farhannah

AU - McPartlin, Andrew

AU - Holloway, Lois

AU - Thwaites, David

AU - Brink, Carsten

N1 - Publisher Copyright: © 2022 The Authors

PY - 2022/11

Y1 - 2022/11

N2 - Introduction: Federated learning has the potential to perfrom analysis on decentralised data; however, there are some obstacles to survival analyses as there is a risk of data leakage. This study demonstrates how to perform a stratified Cox regression survival analysis specifically designed to avoid data leakage using federated learning on larynx cancer patients from centres in three different countries. Methods: Data were obtained from 1821 larynx cancer patients treated with radiotherapy in three centres. Tumour volume was available for all 786 of the included patients. Parameter selection among eleven clinical and radiotherapy parameters were performed using best subset selection and cross-validation through the federated learning system, AusCAT. After parameter selection, β regression coefficients were estimated using bootstrap. Calibration plots were generated at 2 and 5-years survival, and inner and outer risk groups’ Kaplan-Meier curves were compared to the Cox model prediction. Results: The best performing Cox model included log(GTV), performance status, age, smoking, haemoglobin and N-classification; however, the simplest model with similar statistical prediction power included log(GTV) and performance status only. The Harrell C-indices for the simplest model were for Odense, Christie and Liverpool 0.75[0.71–0.78], 0.65[0.59–0.71], and 0.69[0.59–0.77], respectively. The values are slightly higher for the full model with C-index 0.77[0.74–0.80], 0.67[0.62–0.73] and 0.71[0.61–0.80], respectively. Smoking during treatment has the same hazard as a ten-years older nonsmoking patient. Conclusion: Without any patient-specific data leaving the hospitals, a stratified Cox regression model based on data from centres in three countries was developed without data leakage risks. The overall survival model is primarily driven by tumour volume and performance status.

AB - Introduction: Federated learning has the potential to perfrom analysis on decentralised data; however, there are some obstacles to survival analyses as there is a risk of data leakage. This study demonstrates how to perform a stratified Cox regression survival analysis specifically designed to avoid data leakage using federated learning on larynx cancer patients from centres in three different countries. Methods: Data were obtained from 1821 larynx cancer patients treated with radiotherapy in three centres. Tumour volume was available for all 786 of the included patients. Parameter selection among eleven clinical and radiotherapy parameters were performed using best subset selection and cross-validation through the federated learning system, AusCAT. After parameter selection, β regression coefficients were estimated using bootstrap. Calibration plots were generated at 2 and 5-years survival, and inner and outer risk groups’ Kaplan-Meier curves were compared to the Cox model prediction. Results: The best performing Cox model included log(GTV), performance status, age, smoking, haemoglobin and N-classification; however, the simplest model with similar statistical prediction power included log(GTV) and performance status only. The Harrell C-indices for the simplest model were for Odense, Christie and Liverpool 0.75[0.71–0.78], 0.65[0.59–0.71], and 0.69[0.59–0.77], respectively. The values are slightly higher for the full model with C-index 0.77[0.74–0.80], 0.67[0.62–0.73] and 0.71[0.61–0.80], respectively. Smoking during treatment has the same hazard as a ten-years older nonsmoking patient. Conclusion: Without any patient-specific data leaving the hospitals, a stratified Cox regression model based on data from centres in three countries was developed without data leakage risks. The overall survival model is primarily driven by tumour volume and performance status.

KW - Cox survival model

KW - Data leakage

KW - Distributed learning

KW - Federated learning

KW - Larynx cancer

KW - Stratified Cox model

UR - http://www.scopus.com/inward/record.url?scp=85140718735&partnerID=8YFLogxK

U2 - 10.1016/j.radonc.2022.09.023

DO - 10.1016/j.radonc.2022.09.023

M3 - Journal article

C2 - 36208652

AN - SCOPUS:85140718735

SN - 0167-8140

VL - 176

SP - 179

EP - 186

JO - Radiotherapy and Oncology

JF - Radiotherapy and Oncology

ER -