Department of Symptom Research, University of Texas MD Anderson Cancer Center, Houston, TX.
Department of Obstetrics and Gynecology, Heidelberg University, Heidelberg, Germany.
JCO Clin Cancer Inform. 2021 Mar;5:338-347. doi: 10.1200/CCI.20.00088.
Financial burden caused by cancer treatment is associated with material loss, distress, and poorer outcomes. Financial resources exist to support patients but identification of need is difficult. We sought to develop and test a tool to accurately predict an individual's risk of financial toxicity based on clinical, demographic, and patient-reported data prior to initiation of breast cancer treatment.
We surveyed 611 patients undergoing breast cancer therapy at MD Anderson Cancer Center. We collected data using the validated COmprehensive Score for financial Toxicity (COST) patient-reported outcome measure alongside other financial indicators (credit score, income, and insurance status). We also collected clinical and perioperative data. We trained and tested an ensemble of machine learning (ML) algorithms (neural network, regularized linear model, support vector machines, and a classification tree) to predict financial toxicity. Data were randomly partitioned into training and test samples (2:1 ratio). Predictive performance was assessed using area-under-the-receiver-operating-characteristics-curve (AUROC), accuracy, sensitivity, and specificity.
In our test sample (N = 203), 48 of 203 women (23.6%) reported significant financial burden. The algorithm ensemble performed well to predict financial burden with an AUROC of 0.85, accuracy of 0.82, sensitivity of 0.85, and specificity of 0.81. Key clinical predictors of financial burden from the linear model were neoadjuvant therapy (β, .11) and autologous, rather than implant-based, reconstruction (β, .06). Notably, radiation and clinical tumor stage had no effect on financial burden.
ML models accurately predicted financial toxicity related to breast cancer treatment. These predictions may inform decision making and care planning to avoid financial distress during cancer treatment or enable targeted financial support. Further research is warranted to validate this tool and assess applicability for other types of cancer.
癌症治疗带来的经济负担与物质损失、痛苦和较差的治疗结局相关。有经济资源可以用来支持患者，但确定需求很困难。我们试图开发和测试一种工具，以便在开始乳腺癌治疗前，基于临床、人口统计学和患者报告的数据，准确预测个体发生财务毒性的风险。
我们调查了在 MD 安德森癌症中心接受乳腺癌治疗的 611 名患者。我们使用经过验证的 COmprehensive Score for financial Toxicity（COST）患者报告结局测量工具以及其他财务指标（信用评分、收入和保险状况）收集数据。我们还收集了临床和围手术期数据。我们使用机器学习（ML）算法（神经网络、正则化线性模型、支持向量机和分类树）的集成来训练和测试预测财务毒性的模型。数据随机分为训练和测试样本（2:1 比例）。使用受试者工作特征曲线下的面积（AUROC）、准确性、敏感性和特异性来评估预测性能。
在我们的测试样本（N=203）中，203 名女性中有 48 名（23.6%）报告了严重的经济负担。算法集成在预测财务负担方面表现良好，AUROC 为 0.85，准确性为 0.82，敏感性为 0.85，特异性为 0.81。线性模型中预测财务负担的关键临床预测因子是新辅助治疗（β，0.11）和自体而不是植入物重建（β，0.06）。值得注意的是，放疗和临床肿瘤分期对财务负担没有影响。
ML 模型准确预测了与乳腺癌治疗相关的财务毒性。这些预测可以为避免癌症治疗期间的经济困境或为有针对性的财务支持提供信息，以帮助决策和护理计划。需要进一步研究来验证该工具，并评估其在其他类型癌症中的适用性。
