Patient-Reported Outcomes, Value & Experience (PROVE) Center, Harvard Medical School & Brigham and Women's Hospital, Boston, Massachusetts.
Department of Plastic & Reconstructive Surgery, Memorial Sloan Kettering Cancer Center, New York, New York.
Ann Surg. 2023 Jan 1;277(1):e144-e152. doi: 10.1097/SLA.0000000000004862. Epub 2021 Mar 18.
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.
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 suboptimal treatment recommendations for individuals.
We trained, tested, and validated 3 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 before surgery and at 1-year follow-up. Data from 10 of the 11 sites were randomly split into training and test samples (2:1 ratio) to develop and test 3 algorithms (logistic regression with elastic net penalty, extreme gradient boosting tree, and neural network) which were further validated using the additional site's data.AUC to predict clinically-significant changes in satisfaction with breasts at 1-year follow-up using the validated BREAST-Q were the outcome measures.
The 3 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).
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.
我们开发、测试和验证了机器学习算法，以预测接受乳腺癌相关乳房切除术和重建的患者在 1 年随访时的个体报告结局，从而为接受乳腺癌治疗的女性提供个体化、以患者为中心的决策。
对接受癌症相关乳房切除术和重建的女性而言，对乳房的满意度是一个关键结局。目前的决策依赖于基于群体的证据，这可能导致对个体的治疗建议不够理想。
我们使用 2011 年至 2016 年期间北美 11 个研究点接受癌症相关乳房切除术和重建的 1921 名女性的数据，训练、测试和验证了 3 种机器学习算法。在手术前和 1 年随访时收集了 1921 名接受癌症相关乳房切除术和重建的女性的数据。11 个研究点中的 10 个随机分为训练和测试样本（2:1 比例），以开发和测试 3 种算法（逻辑回归与弹性网络罚分、极端梯度提升树和神经网络），然后使用其他研究点的数据对其进行验证。使用验证后的 BREAST-Q 预测 1 年随访时对乳房满意度的临床显著变化的 AUC 是结局指标。
当预测测试和验证数据集中的乳房满意度提高或降低时，这 3 种算法的性能相当：对于测试数据集，中位数准确性=0.81（范围 0.73-0.83），中位数 AUC=0.84（范围 0.78-0.85）。对于验证数据集，中位数准确性=0.83（范围 0.81-0.84），中位数 AUC=0.86（范围 0.83-0.89）。
使用机器学习算法可以准确预测个体患者报告结局，从而为接受乳腺癌治疗的女性提供个体化、以患者为中心的决策。
