André Pfob1, Babak J Mehrara, Jonas A Nelson, Edwin G Wilkins, Andrea L Pusic, Chris Sidey-Gibbons. 1. *PROVE Center, Harvard Medical School & Brigham and Women's Hospital, Boston, MA †Department of Plastic & Reconstructive Surgery, Memorial Sloan Kettering Cancer Center, New York, NY ‡Department of Surgery, University of Michigan, Ann Arbor, MI §Department of Symptom Research, The University of Texas MD Anderson Cancer Center.
Abstract
OBJECTIVE: We developed, tested, and validated machine learning algorithms to predict individual patient-reported outcomes at 1-year follow-up to facilitate individualized, patient-centered decision-making for women with breast cancer. SUMMARY BACKGROUND DATA: Satisfaction with breasts is a key outcome for women undergoing cancer-related mastectomy and reconstruction. Current decision-making relies on group-level evidence which may lead to sub-optimal treatment recommendations for individuals. METHODS: We trained, tested, and validated three machine learning algorithms using data from 1921 women undergoing cancer-related mastectomy and reconstruction conducted at eleven study sites in North America from 2011 to 2016. Data from 1921 women undergoing cancer-related mastectomy and reconstruction were collected prior to surgery and at 1-year follow-up. Data from 10 of the 11 sites was randomly split into training and test samples (2:1 ratio) to develop and test three algorithms (logistic regression with elastic net penalty, Extreme Gradient Boosting tree, and neural network) which were further validated using the additional site's data.Accuracy and area-under-the-receiver-operating-characteristics-curve (AUC) to predict clinically-significant changes in satisfaction with breasts at 1-year follow-up using the validated BREAST-Q were the outcome measures. RESULTS: The three algorithms performed equally well when predicting both improved or decreased satisfaction with breasts in both testing and validation datasets: For the testing dataset median accuracy= 0.81 (range 0.73-0.83), median AUC= 0.84 (range 0.78-0.85). For the validation dataset median accuracy= 0.83 (range 0.81-0.84), median AUC= 0.86 (range 0.83-0.89). CONCLUSION: Individual patient-reported outcomes can be accurately predicted using machine learning algorithms, which may facilitate individualized, patient-centered decision-making for women undergoing breast cancer treatment.
OBJECTIVE: We developed, tested, and validated machine learning algorithms to predict individual patient-reported outcomes at 1-year follow-up to facilitate individualized, patient-centered decision-making for women with breast cancer. SUMMARY BACKGROUND DATA: Satisfaction with breasts is a key outcome for women undergoing cancer-related mastectomy and reconstruction. Current decision-making relies on group-level evidence which may lead to sub-optimal treatment recommendations for individuals. METHODS: We trained, tested, and validated three machine learning algorithms using data from 1921 women undergoing cancer-related mastectomy and reconstruction conducted at eleven study sites in North America from 2011 to 2016. Data from 1921 women undergoing cancer-related mastectomy and reconstruction were collected prior to surgery and at 1-year follow-up. Data from 10 of the 11 sites was randomly split into training and test samples (2:1 ratio) to develop and test three algorithms (logistic regression with elastic net penalty, Extreme Gradient Boosting tree, and neural network) which were further validated using the additional site's data.Accuracy and area-under-the-receiver-operating-characteristics-curve (AUC) to predict clinically-significant changes in satisfaction with breasts at 1-year follow-up using the validated BREAST-Q were the outcome measures. RESULTS: The three algorithms performed equally well when predicting both improved or decreased satisfaction with breasts in both testing and validation datasets: For the testing dataset median accuracy= 0.81 (range 0.73-0.83), median AUC= 0.84 (range 0.78-0.85). For the validation dataset median accuracy= 0.83 (range 0.81-0.84), median AUC= 0.86 (range 0.83-0.89). CONCLUSION: Individual patient-reported outcomes can be accurately predicted using machine learning algorithms, which may facilitate individualized, patient-centered decision-making for women undergoing breast cancer treatment.
Authors: Vivian Koelbel; André Pfob; Benedikt Schaefgen; Peter Sinn; Manuel Feisst; Michael Golatta; Christina Gomez; Anne Stieber; Paul Bach; Geraldine Rauch; Joerg Heil Journal: Ann Surg Oncol Date: 2021-09-28 Impact factor: 5.344