Ananya Choudhury1, Stelios Theophanous2, Per-Ivar Lønne3, Robert Samuel2, Marianne Grønlie Guren4, Maaike Berbee1, Peter Brown5, John Lilley6, Johan van Soest7, Andre Dekker1, Alexandra Gilbert2, Eirik Malinen8, Leonard Wee9, Ane L Appelt10. 1. MAASTRO (Dept of Radiotherapy), GROW School of Oncology and Developmental Biology, Maastricht University & Maastricht University Medical Centre+, Limburg, The Netherlands. 2. Leeds Institute of Medical Research at St James's, University of Leeds, United Kingdom. 3. Department of Medical Physics, Oslo University Hospital, Norway. 4. Department of Oncology, Oslo University Hospital, Norway. 5. Department of Clinical Radiology, Leeds Teaching Hospitals NHS Trust, St James's University Hospital, United Kingdom. 6. Department of Medical Physics, Leeds Cancer Centre, St James's University Hospitals, United Kingdom. 7. MAASTRO (Dept of Radiotherapy), GROW School of Oncology and Developmental Biology, Maastricht University & Maastricht University Medical Centre+, Limburg, The Netherlands; Brightlands Institute for Smart Society (BISS), Faculty of Science & Engineering, Maastricht University, CR Heerlen, The Netherlands. 8. Department of Medical Physics, Oslo University Hospital, Norway; Department of Physics, University of Oslo, Norway. 9. MAASTRO (Dept of Radiotherapy), GROW School of Oncology and Developmental Biology, Maastricht University & Maastricht University Medical Centre+, Limburg, The Netherlands. Electronic address: leonard.wee@maastro.nl. 10. Leeds Institute of Medical Research at St James's, University of Leeds, United Kingdom. Electronic address: a.l.appelt@leeds.ac.uk.
Abstract
BACKGROUND AND PURPOSE: Predicting outcomes is challenging in rare cancers. Single-institutional datasets are often small and multi-institutional data sharing is complex. Distributed learning allows machine learning models to use data from multiple institutions without exchanging individual patient-level data. We demonstrate this technique in a proof-of-concept study of anal cancer patients treated with chemoradiotherapy across multiple European countries. MATERIALS AND METHODS: atomCAT is a three-centre collaboration between Leeds Cancer Centre (UK), MAASTRO Clinic (The Netherlands) and Oslo University Hospital (Norway). We trained and validated a Cox proportional hazards regression model in a distributed fashion using data from 281 patients treated with radical, conformal chemoradiotherapy for anal cancer in three institutions. Our primary endpoint was overall survival. We selected disease stage, sex, age, primary tumour size, and planned radiotherapy dose (in EQD2) a priori as predictor variables. RESULTS: The Cox regression model trained across all three centres found worse overall survival for high risk disease stage (HR = 2.02), male sex (HR = 3.06), older age (HR = 1.33 per 10 years), larger primary tumour volume (HR = 1.05 per 10 cm3) and lower radiotherapy dose (HR = 1.20 per 5 Gy). A mean concordance index of 0.72 was achieved during validation, with limited variation between centres (Leeds = 0.72, MAASTRO = 0.74, Oslo = 0.70). The global model performed well for risk stratification for two out of three centres. CONCLUSIONS: Using distributed learning, we accessed and analysed one of the largest available multi-institutional cohorts of anal cancer patients treated with modern radiotherapy techniques. This demonstrates the value of distributed learning in outcome modelling for rare cancers.
BACKGROUND AND PURPOSE: Predicting outcomes is challenging in rare cancers. Single-institutional datasets are often small and multi-institutional data sharing is complex. Distributed learning allows machine learning models to use data from multiple institutions without exchanging individual patient-level data. We demonstrate this technique in a proof-of-concept study of anal cancerpatients treated with chemoradiotherapy across multiple European countries. MATERIALS AND METHODS: atomCAT is a three-centre collaboration between Leeds Cancer Centre (UK), MAASTRO Clinic (The Netherlands) and Oslo University Hospital (Norway). We trained and validated a Cox proportional hazards regression model in a distributed fashion using data from 281 patients treated with radical, conformal chemoradiotherapy for anal cancer in three institutions. Our primary endpoint was overall survival. We selected disease stage, sex, age, primary tumour size, and planned radiotherapy dose (in EQD2) a priori as predictor variables. RESULTS: The Cox regression model trained across all three centres found worse overall survival for high risk disease stage (HR = 2.02), male sex (HR = 3.06), older age (HR = 1.33 per 10 years), larger primary tumour volume (HR = 1.05 per 10 cm3) and lower radiotherapy dose (HR = 1.20 per 5 Gy). A mean concordance index of 0.72 was achieved during validation, with limited variation between centres (Leeds = 0.72, MAASTRO = 0.74, Oslo = 0.70). The global model performed well for risk stratification for two out of three centres. CONCLUSIONS: Using distributed learning, we accessed and analysed one of the largest available multi-institutional cohorts of anal cancerpatients treated with modern radiotherapy techniques. This demonstrates the value of distributed learning in outcome modelling for rare cancers.
Authors: Alexandra Gilbert; Ane L Appelt; Stelios Theophanous; Robert Samuel; John Lilley; Ann Henry; David Sebag-Montefiore Journal: BMC Cancer Date: 2022-06-03 Impact factor: 4.638