Satheeshkumar Poolakkad S, Pili Roberto, Epstein Joel B, Thazhe Sudheer B Kurunthatil, Sukumar Rhine, Mohan Minu Ponnamma
Division of Hematology and Oncology, Department of Medicine, University at Buffalo, Buffalo, NY, 14203, USA.
City of Hope Comprehensive Cancer Center, Duarte CA and Samuel Oschin Comprehensive Cancer Institute, Cedars-Sinai Medical System, Los Angeles, CA, USA.
J Cancer Res Clin Oncol. 2023 Nov;149(15):13875-13888. doi: 10.1007/s00432-023-05197-w. Epub 2023 Aug 4.
Cancer-related fatigue (CRF) is a devastating complication with limited recognized clinical risk factors. We examined characteristics among solid and liquid cancers utilizing Machine learning (ML) approaches for predicting CRF.
We utilized 2017 National Inpatient Sample database and employed generalized linear models to assess the association between CRF and the outcome of burden of illness among hospitalized solid and non-solid tumors patients. And further applied lasso, ridge and Random Forest (RF) for building our linear and non-linear ML models.
The 2017 database included 196,330 prostate (PCa), 66,385 leukemia (Leuk), 107,245 multiple myeloma (MM), and 41,185 cancers of lip, oral cavity and pharynx (CLOP) patients, and among them, there were 225, 140, 125 and 115 CRF patients, respectively. CRF was associated with a higher burden of illness among Leuk and MM, and higher mortality among PCa. For the PCa patients, both the test and the training data had best areas under the ROC curve [AUC = 0.91 (test) vs. 0.90 (train)] for both lasso and ridge ML. For the CLOP, this was 0.86 and 0.79 for ridge; 0.87 and 0.84 for lasso; 0.82 for both test and train for RF and for the Leuk cohort, 0.81 (test) and 0.76 (train) for both ridge and lasso.
This study provided an effective platform to assess potential risks and outcomes of CRF in patients hospitalized for the management of solid and non-solid tumors. Our study showed ML methods performed well in predicting the CRF among solid and liquid tumors.
癌症相关疲劳（CRF）是一种具有严重破坏性的并发症，其公认的临床风险因素有限。我们利用机器学习（ML）方法研究实体癌和液体癌中的特征，以预测CRF。
我们使用2017年全国住院患者样本数据库，并采用广义线性模型评估CRF与住院实体瘤和非实体瘤患者疾病负担结果之间的关联。并进一步应用套索、岭回归和随机森林（RF）来构建我们的线性和非线性ML模型。
2017年数据库包括196,330例前列腺癌（PCa）、66,385例白血病（Leuk）、107,245例多发性骨髓瘤（MM）和41,185例唇、口腔和咽癌（CLOP）患者，其中分别有225、140、125和115例CRF患者。CRF与Leuk和MM患者较高的疾病负担相关，与PCa患者较高的死亡率相关。对于PCa患者，套索和岭回归ML的测试数据和训练数据在ROC曲线下的面积均最佳[AUC = 0.91（测试）对0.90（训练）]。对于CLOP，岭回归的这一数值分别为0.86和0.79；套索为0.87和0.84；RF的测试和训练数据均为0.82；对于Leuk队列，岭回归和套索的数值分别为0.81（测试）和0.76（训练）。
本研究提供了一个有效的平台，用于评估因实体瘤和非实体瘤治疗而住院患者中CRF的潜在风险和结果。我们的研究表明，ML方法在预测实体瘤和液体瘤中的CRF方面表现良好。
