Cancer-related fatigue (CRF) is a widespread symptom with high prevalence in cancer patients, seriously affecting their quality of life. In the context of precision care, constructing machine learning-based prediction models for early screening and assessment of CRF is beneficial to this situation. To further understand the predictors of CRF for model construction, we conducted a comprehensive search in PubMed, Web of Science, Embase, and Scopus databases, combining CRF with predictor-related terms. A total of 27 papers met the inclusion criteria. We evaluated the above studies into three subgroups following the predisposing, precipitating, and perpetuating (3P) factor model. (1) Predisposing factors—baseline fatigue, demographic characteristics, clinical characteristics, psychosocial traits and physical symptoms. (2) Precipitating factors—type and stage of chemotherapy, inflammatory factors, laboratory indicators and metabolic changes. (3) Perpetuating factors—a low level of physical activity and poorer nutritional status. Future research should prioritize large-scale prospective studies with emerging technologies to identify accurate predictors of CRF. The assessment and management of CRF should also focus on the above factors, especially the controllable precipitating factors, to improve the quality of life of cancer survivors.
癌因性疲乏（CRF）是癌症患者中普遍存在且发生率较高的症状，严重影响患者生活质量。在精准护理背景下，构建基于机器学习的预测模型对CRF进行早期筛查与评估有助于改善这一现状。为深入理解CRF预测因子以支撑模型构建，本研究系统检索了PubMed、Web of Science、Embase和Scopus数据库，结合CRF与预测因子相关术语进行文献筛选，最终纳入27篇符合标准的研究。依据易感因素、诱发因素和维持因素（3P）模型框架，将现有研究归纳为三个亚组：（1）易感因素——基线疲乏水平、人口学特征、临床特征、心理社会特质及躯体症状；（2）诱发因素——化疗方案与周期、炎症因子、实验室指标及代谢变化；（3）维持因素——低体力活动水平与不良营养状态。未来研究应优先采用新兴技术开展大规模前瞻性研究，以确立CRF的精准预测因子。对CRF的评估与管理亦需重点关注上述因素，特别是可调控的诱发因素，从而提升癌症幸存者的生活质量。
肿瘤(癌症)患者之家