Machine Learning Accurately Predicts Patient-reported Outcomes 1 Year After Breast Reconstruction
- 5 March 2025
- journal article
- research article
- Published by Wolters Kluwer Health in Annals of Surgery
- Vol. 284 (1) , 176-183
Abstract
Objective: To develop and evaluate machine learning algorithms for predicting patient-reported outcomes following breast reconstruction. Background: Machine learning may inform patient-reported outcomes in breast reconstruction, possibly enhancing shared decision-making and tailoring patient care. Methods: Data on patient characteristics, reconstructive technique, and BREAST-Q scores from women undergoing breast reconstruction at Memorial Sloan Kettering Cancer Center (MSKCC) between January 2010 and March 2024 was retrospectively collected. Five machine learning algorithms were developed and validated on this data to predict improved versus not improved BREAST-Q scores after reconstruction. Models were externally validated models using multicenter data from the Mastectomy Reconstruction Outcomes Consortium. Models were evaluated using the area under the receiver operator curve, sensitivity, specificity, and Brier score. Results: A total of 4776 patients (2687 from MSKCC, 2089 from Mastectomy Reconstruction Outcomes Consortium) were included in model development and validation. Machine learning algorithms demonstrated area under the received operator curves of 0.97 for physical well-being of the abdomen, 0.86 for satisfaction with the breast, 0.79 for sexual well-being, 0.78 for physical well-being of the chest, and 0.74 for psychosocial well-being. Variables that contributed the most to model predictions across all domains were preoperative BREAST-Q scores, timing of radiation, body mass index, age, and reconstructive technique. Conclusions: Machine learning algorithms can accurately predict patient-reported outcomes before breast reconstruction. Ultimately, this data-driven approach may streamline shared decision-making and enhance patient-centered care.Keywords
This publication has 28 references indexed in Scilit:
- Development and Validation of a Machine Learning Model to Identify Patients Before Surgery at High Risk for Postoperative Adverse EventsJAMA Network Open, 2023
- Moving towards patient-reported outcomes in routine clinical practice: implementation lessons from the BREAST-QQuality of Life Research, 2022
- Effects of dataset size and interactions on the prediction performance of logistic regression and deep learning modelsComputer Methods and Programs in Biomedicine, 2022
- Machine learning to predict individual patient-reported outcomes at 2-year follow-up for women undergoing cancer-related mastectomy and breast reconstruction (INSPiRED-001)The Breast, 2021
- Machine learning in gastrointestinal surgerySurgery Today, 2021
- Machine Learning–Guided Adjuvant Treatment of Head and Neck CancerJAMA Network Open, 2020
- Long-term Patient-Reported Outcomes in Postmastectomy Breast ReconstructionJAMA Surgery, 2018
- Statistically reinforced machine learning for nonlinear patterns and variable interactionsEcosphere, 2017
- Random forest classifier for remote sensing classificationInternational Journal of Remote Sensing, 2005
- The use of the area under the ROC curve in the evaluation of machine learning algorithmsPattern Recognition, 1997