Larynx cancer survival model developed through open-source federated learning. (November 2022)

• Record Type: Journal Article
• Authors: Rønn Hansen, Christian; Price, Gareth; Field, Matthew; Sarup, Nis; Zukauskaite, Ruta; Johansen, Jørgen; Eriksen, Jesper Grau; Aly, Farhannah; McPartlin, Andrew; Holloway, Lois; Thwaites, David; Brink, Carsten
• Is Part Of: Radiotherapy and oncology. Volume 176(2022)
• Page Start: 179
• Page End: 186
• Publication Date: 2022-11
• Subjects: Distributed learning -- Federated learning -- Larynx cancer -- Stratified Cox model -- Data leakage -- Cox survival model; Oncology -- Periodicals; Radiotherapy -- Periodicals; Tumors -- Periodicals; Medical Oncology -- Periodicals; Neoplasms -- radiotherapy -- Periodicals; Radiotherapy -- Periodicals; Radiothérapie -- Périodiques; Cancérologie -- Périodiques; Tumeurs -- Périodiques; Electronic journals; 616.9940642
• DOI: 10.1016/j.radonc.2022.09.023
• Languages: English
• ISSNs: 0167-8140

Abstract

Highlights: OS of larynx cancer patients treated at Odense DK, Manchester UK and Liverpool AUS is driven by tumour volume and PS. Federated learning can be used to create survival models without patient-sensitive data leaving the individual institutions. The baseline hazards of the three institutions are similar, indicating the GTV volume and PS explain the cohort differences. Smoking during treatment has the same risk profile as a ten year older patient not smoking. Abstract: 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.