Transfer Learning and Machine Learning for Training Five-Year Survival Prognostic Models in Early Breast Cancer: Development and Validation Study
Journal of Medical Internet Research, vol. 28, pp. e88665
Abstract
BACKGROUND: Prognostic information is essential for decision-making in breast cancer management. In recent years, trials and clinical practice have emphasized genomic prognostication tools, despite clinicopathological methods being more affordable and accessible. PREDICT v3 is one such tool with promising results across cohorts. Advances in machine learning (ML), transfer learning, and ensemble methods provide opportunities to enhance these approaches, especially where missing data and model assumptions differ across diverse populations. OBJECTIVE: This study evaluates the potential to improve survival prognostication in breast cancer. More precisely, we compare de novo ML, transfer learning from the pretrained prognostication model PREDICT v3, and a stacked ensemble approach. METHODS: Data from the MA.27 trial (NCT00066573) were used for model training, with external validation on data from the Tamoxifen Exemestane Adjuvant Multinational trial (NCT00279448 and NCT00032136) and a US Surveillance, Epidemiology, and End Results cohort. Transfer learning was applied by re-estimating the parameters of the pretrained prognostic tool PREDICT v3. De novo ML included random survival forests and extreme gradient boosting, and the ensemble was implemented using weighted linear stacking of model predictions. Internal and external validation was assessed in terms of the integrated calibration index and discrimination. Shapley Additive Explanations values were used to explain model predictions and decision-curve analysis to facilitate the interpretation of performance differences. RESULTS: Transfer learning, de novo random survival forest, and the stacked ensemble improved calibration in MA.27 over the pretrained model (integrated calibration index reduced from 0.042 in PREDICT v3 to ≤0.007) while discrimination remained comparable (AUROC increased from 0.738 in PREDICT v3 to 0.744-0.799). In decision-curve analysis, these approaches demonstrated consistently positive net benefit across clinically relevant thresholds, while PREDICT v3 lost net benefit beyond 7.5% predicted risk. Invalid PREDICT v3 predictions were observed in 23.8% to 25.8% of MA.27 individuals due to missing information. In contrast, ML models and the stacked ensemble predicted survival despite missing data. Across all models, patient age, nodal status, pathological grading, and tumor size had the highest Shapley Additive Explanations values, indicating their importance for survival prognostication. External validation in the US Surveillance, Epidemiology, and End Results cohort confirmed the benefits of transfer learning, RSF, and ensemble in terms of calibration while maintaining discrimination at comparable levels. In contrast, generalizability was limited in the Tamoxifen Exemestane Adjuvant Multinational trial, a cohort with a substantially different distribution of clinicopathological characteristics. CONCLUSIONS: This study demonstrates that transfer learning, de novo RSF, and a stacked ensemble can improve prognostication compared with the pretrained PREDICT v3, particularly in the presence of missing or uncertain inputs. Transportability may be limited in cohorts with different clinicopathological profiles, requiring local validation before clinical deployment. Ultimately, better survival estimation can provide more meaningful guidance in breast cancer care. TRIAL REGISTRATION: ClinicalTrials.gov NCT00066573; https://clinicaltrials.gov/study/NCT00066573, NCT00279448; https://clinicaltrials.gov/study/NCT00279448, NCT00032136; https://clinicaltrials.gov/study/NCT00032136.
Authors 25
-
University of Ottawa · Children's Hospital of Eastern Ontario · Charité - Universitätsmedizin Berlin
Affiliation as printed
Department of Nephrology and Medical Intensive Care, Charité - Universitaetsmedizin Berlin, Berlin, Germany
Research Institute, Children's Hospital of Eastern Ontario, Ottawa, ON, Canada
School of Epidemiology and Public Health, Faculty of Medicine, University of Ottawa, Ottawa, ON, Canada
-
University of Ottawa · Children's Hospital of Eastern Ontario
Affiliation as printed
Research Institute, Children's Hospital of Eastern Ontario, Ottawa, ON, Canada
School of Epidemiology and Public Health, Faculty of Medicine, University of Ottawa, Ottawa, ON, Canada
-
Affiliation as printed
Division of Medical Oncology, Faculty of Medicine, University of Ottawa, Ottawa, ON, Canada
-
Affiliation as printed
Department of Oncology, McMaster University, Hamilton, ON, Canada
-
Ottawa Hospital Research Institute
Affiliation as printed
Cancer Therapeutics Program, Ottawa Hospital Research Institute, Ottawa, ON, Canada
-
Ottawa Hospital · Ottawa Hospital Research Institute
Affiliation as printed
Ottawa Hospital Cancer Center, Ottawa Hospital Research Institute, Ottawa, ON, Canada
-
Affiliation as printed
Division of Medical Oncology, Faculty of Medicine, University of Ottawa, Ottawa, ON, Canada
-
Centre Hospitalier de l’Université de Montréal · Université de Montréal
Affiliation as printed
Division of Medical Oncology and Hematology, CHUM, Université de Montréal, Montreal, QC, Canada
-
Queen's University · Canadian Cancer Trials Group
Affiliation as printed
Canadian Canadian Cancer Trials Group, Queen's University, Kingston, ON, Canada
-
Queen's University · Canadian Cancer Trials Group
Affiliation as printed
Canadian Canadian Cancer Trials Group, Queen's University, Kingston, ON, Canada
-
Edinburgh Cancer Research · Institute of Genetics and Cancer · University of Edinburgh
Affiliation as printed
Edinburgh Cancer Research, Institute of Genetics and Cancer, University of Edinburgh, Edinburgh, Scotland, United Kingdom
-
Edinburgh Cancer Research · Institute of Genetics and Cancer · University of Edinburgh
Affiliation as printed
Edinburgh Cancer Research, Institute of Genetics and Cancer, University of Edinburgh, Edinburgh, Scotland, United Kingdom
-
Ontario Institute for Cancer Research · University of Toronto
Affiliation as printed
Department of Laboratory Medicine and Pathobiology, University of Toronto, Ontario, ON, Canada
Diagnostic Development, Ontario Institute for Cancer Research, Toronto, ON, Canada
-
Ontario Institute for Cancer Research
Affiliation as printed
Diagnostic Development, Ontario Institute for Cancer Research, Toronto, ON, Canada
-
Ontario Institute for Cancer Research · University of Toronto
Affiliation as printed
Department of Laboratory Medicine and Pathobiology, University of Toronto, Ontario, ON, Canada
Diagnostic Development, Ontario Institute for Cancer Research, Toronto, ON, Canada
-
Leiden University Medical Center
Affiliation as printed
Department of Surgery, Leiden University Medical Center, Leiden, South Holland, The Netherlands
-
Leiden University Medical Center
Affiliation as printed
Department of Surgery, Leiden University Medical Center, Leiden, South Holland, The Netherlands
-
GZA Ziekenhuizen Campus Sint-Augustinus
Affiliation as printed
St. Augustinus Hospital, Antwerp, Belgium
-
Affiliation as printed
Department of Pathology, NHS Greater Glasgow and Clyde, Glasgow, Scotland, United Kingdom
-
University Medical Center of the Johannes Gutenberg University Mainz
Affiliation as printed
Department of Gynecology and Obstetrics, University Center Mainz, Mainz, Germany
-
National and Kapodistrian University of Athens
Affiliation as printed
Medical School, National and Kapodistrian University of Athens, Athens, Attica, Greece
-
University of Ottawa · Children's Hospital of Eastern Ontario
Affiliation as printed
Research Institute, Children's Hospital of Eastern Ontario, Ottawa, ON, Canada
School of Epidemiology and Public Health, Faculty of Medicine, University of Ottawa, Ottawa, ON, Canada
-
Children's Hospital of Eastern Ontario
Affiliation as printed
Research Institute, Children's Hospital of Eastern Ontario, Ottawa, ON, Canada
-
Ottawa Hospital · Ottawa Hospital Research Institute
Affiliation as printed
Ottawa Hospital Cancer Center, Ottawa Hospital Research Institute, Ottawa, ON, Canada
-
University of Ottawa · Children's Hospital of Eastern Ontario
Affiliation as printed
Research Institute, Children's Hospital of Eastern Ontario, Ottawa, ON, Canada
School of Epidemiology and Public Health, Faculty of Medicine, University of Ottawa, Ottawa, ON, Canada
Cited by 0 stored of 0
No patents citing this paper on Lens.org (checked 2026-10-11).