Harvard Medical School, Boston, MA, USA(1); Department of Oral Oncology, Roswell Park Comprehensive Cancer Center, Buffalo, NY, USA.
Division of Hospital Medicine, Cambridge Health Alliance and Harvard Medical School, Cambridge, MA, USA; Division of Gastroenterology, Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, MA, USA.
Int J Med Inform. 2021 Oct;154:104563. doi: 10.1016/j.ijmedinf.2021.104563. Epub 2021 Aug 27.
Ulcerative mucositis (UM) is a devastating complication of most cancer therapies with less recognized risk factors. Whilst risk predictions are most vital in adverse events, we utilized Machine learning (ML) approaches for predicting chemotherapy-induced UM.
We utilized 2017 National Inpatient Sample database to identify discharges with antineoplastic chemotherapy-induced UM among those received chemotherapy as part of their cancer treatment. We used forward selection and backward elimination for feature selection; lasso and Gradient Boosting Method were used for building our linear and non-linear models.
In 2017, there were 253 (unweighted numbers) chemotherapy-induced UM patient discharges from 21,626 (unweighted numbers) adult patients who received antineoplastic chemotherapy as part of their cancer treatment. Our linear model, lasso showed performance (C-statistics) AUC: 0.75 (test dataset), 0.75 (training dataset); the Gradient Boosting Method (GBM) model showed AUC: 0.76 in the training and 0.79 in the test datasets. The feature selection derived from stepwise forward selection and backward elimination methods showed variables of importance--antineoplastic chemotherapy-induced pancytopenia, agranulocytosis due to cancer chemotherapy, fluid and electrolyte imbalance, age, anemia due to chemotherapy, median household income, and depression. Higher importance variable derived from GBM in the order of importance were antineoplastic chemotherapy-induced pancytopenia > co-morbidity score > agranulocytosis due to cancer chemotherapy > age > and fluid and electrolyte imbalance. Further, when the analysis was stratified to females only, the ML models performed better than the unstratified model.
Our study showed ML methods performed well in predicting the chemotherapy-induced UM. Predictors identified through ML approach matched to the clinically meaningful and previously discussed predictors of the chemotherapy-induced UM.
溃疡性黏膜炎（UM）是大多数癌症治疗的一种破坏性并发症，但风险因素认识不足。虽然风险预测在不良事件中最为重要，但我们利用机器学习（ML）方法预测化疗引起的 UM。
我们利用 2017 年国家住院患者样本数据库，在接受癌症治疗中接受化疗的患者中，确定抗肿瘤化疗引起的 UM 出院人数。我们使用向前选择和向后消除进行特征选择；使用 LASSO 和梯度提升方法构建我们的线性和非线性模型。
2017 年，有 253 名（未加权数量）抗肿瘤化疗引起的 UM 患者出院，其中 21626 名（未加权数量）接受抗肿瘤化疗作为癌症治疗一部分的成年患者。我们的线性模型 LASSO 显示了性能（C 统计量）AUC：0.75（测试数据集），0.75（训练数据集）；梯度提升方法（GBM）模型在训练和测试数据集的 AUC 分别为 0.76 和 0.79。逐步向前选择和向后消除方法得出的特征选择显示了重要变量 - 抗肿瘤化疗引起的全血细胞减少症、癌症化疗引起的粒细胞缺乏症、液体和电解质失衡、年龄、化疗引起的贫血、家庭中位数收入和抑郁。从重要性顺序来看，GBM 中衍生的更高重要性变量是抗肿瘤化疗引起的全血细胞减少症>合并症评分>癌症化疗引起的粒细胞缺乏症>年龄>和液体和电解质失衡。此外，当分析仅限于女性时，ML 模型的表现优于非分层模型。
我们的研究表明，ML 方法在预测化疗引起的 UM 方面表现良好。通过 ML 方法确定的预测因子与临床上有意义的和先前讨论过的化疗引起的 UM 预测因子相匹配。
