Machine learning to predict individual patient-reported outcomes at 2-year follow-up for women undergoing cancer-related mastectomy and breast reconstruction (INSPiRED-001)

Abstract

Background: Women undergoing cancer-related mastectomy and reconstruction are facing multiple treatment choices where post-surgical satisfaction with breasts is a key outcome. We developed and validated machine learning algorithms to predict patient-reported satisfaction with breasts at 2-year follow-up to better inform the decision-making process for women with breast cancer. Methods: We trained, tested, and validated three machine learning algorithms (logistic regression (LR) with elastic net penalty, Extreme Gradient Boosting (XGBoost) tree, and neural network) to predict clinically important differences in satisfaction with breasts at 2-year follow-up using the validated BREAST-Q. We used data from 1553 women undergoing cancer-related mastectomy and reconstruction who were followed-up for two years at eleven study sites in North America from 2011 to 2016. 10-fold cross-validation was used to train and test the algorithms on data from 10 of the 11 sites which were further validated using the additional site's data. Area-under-the-receiver-operating-characteristicscurve (AUC) was the primary outcome measure. Results: Of 1553 women, 702 (45.2%) experienced an improved satisfaction with breasts and 422 (27.2%) a decreased satisfaction. In the validation set (n ¼ 221), the algorithms showed equally high performance to predict improved or decreased satisfaction with breasts (all P > 0.05): For improved satisfaction AUCs were 0.86e0.87 and for decreased satisfaction AUCs were 0.84e0.85. Conclusion: Long-term, individual patient-reported outcomes for women undergoing mastectomy and breast reconstruction can be accurately predicted using machine learning algorithms. Our algorithms may be used to better inform clinical treatment decisions for these patients by providing accurate estimates of expected quality of life.

Development and validation of a clinicoradiomic nomogram to assess the HER2 status of patients with invasive ductal carcinoma

“…To achieve high and robust performance of the developed classifiers, six machine learning algorithms, Logistic Regression (LR), Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), Random Forest (RF), Naive Bayesian (NB), XGBoost (XGB), were used to classifier construction. The reason for selecting and comparing these methods in this study was that they were common classifiers in the related study for breast in previous studies, such as undergoing mastectomy prediction [ 24 ], breast cancer prediction [ 25 ], axillary lymph node metastasis [ 26 ]. To avoid over-fitting in the modeling process, the hyper-parameter searching for optimal classifiers were completed by grid-search method using the tenfold cross-validation repeatedly.…”

Developing Machine Learning Algorithms to Support Patient-centered, Value-based Carpal Tunnel Decompression Surgery

“…There is evidence that baseline patient-reported outcomes play a substantial role in the prediction of postoperative outcomes. Pfob et al 28 demonstrate that high baseline breast satisfaction is a principal determinant of poor patient satisfaction following breast reconstruction (quantified via the BREAST-Q PROM). The relationship between baseline PROs and postoperative outcomes are further convoluted in the context of CTS as determinants of baseline health may be distinct from determinants of baseline upper extremity health.…”

Ethical, Legal, and Financial Considerations of Artificial Intelligence in Surgery

“…Current ML tools in surgery exist in the realm of augmenting rather than replacing the doctor, such as predicting surgical outcomes and complications for patients, which can be a useful tool for shared decision-making. [11][12][13] However, in future instances where algorithms are advising real-time surgical decisions in the operating room, questions arise whether liability rests with the surgeon or with the developer of the ML tool. 14 In the instance where a surgeon chooses to override an ML based prediction, the question arises as to how the physician should report their actions.…”