Maihemuti Maierdanjiang, Kamaierjiang Maiheliya, Maimaiti Aierpati, Wu Junshen, Dai Zhibing, Jiang Renbing
Department of Bone and Soft Tissue, Affiliated Tumor Hospital of Xinjiang Medical University, Xinjiang, China.
Department of Cardiovascular Medicine, General Hospital of Xinjiang Military Region, Urumqi, Xinjiang, China.
Front Oncol. 2025 Jul 8;15:1517961. doi: 10.3389/fonc.2025.1517961. eCollection 2025.
Melanoma has the third highest rate of brain metastases among all cancers and is associated with poor long-term survival. This study aimed to develop machine learning models to predict early death in melanoma brain metastasis (MBM) patients to guide clinical decision-making.
We analyzed MBM patients from the SEER database and Xinjiang Medical University. Patients were randomly divided into training and testing cohorts (7:3 ratio). Seven machine learning models were developed and validated using cross-validation, ROC analysis, decision curve analysis, and calibration curves to predict cancer-specific early death (CSED) and all-cause early death (ACED) within 3 months of diagnosis.
Among 1,547 MBM patients, 531 (34.3%) experienced CSED, and 554 (35.8%) experienced ACED. Key predictive factors included age, treatment modalities (radiation, chemotherapy, surgery), tumor characteristics (ulceration), and extracranial metastases (bone, liver). XGBoost achieved the best performance for ACED prediction (AUC=0.776), while logistic regression performed best for CSED prediction (AUC=0.694). External validation confirmed model reliability with comparable performance.
These machine learning models demonstrate strong predictive performance and may assist clinicians in early risk stratification and treatment planning for MBM patients. The models provide objective risk assessment tools that could improve patient counseling and guide aggressive versus palliative care decisions.
黑色素瘤在所有癌症中脑转移率排名第三，且与长期生存率低相关。本研究旨在开发机器学习模型，以预测黑色素瘤脑转移（MBM）患者的早期死亡，从而指导临床决策。
我们分析了来自监测、流行病学和最终结果（SEER）数据库以及新疆医科大学的MBM患者。患者被随机分为训练组和测试组（比例为7:3）。开发了七种机器学习模型，并使用交叉验证、ROC分析、决策曲线分析和校准曲线进行验证，以预测诊断后3个月内的癌症特异性早期死亡（CSED）和全因早期死亡（ACED）。
在1547例MBM患者中，531例（34.3%）发生了CSED，554例（35.8%）发生了ACED。关键预测因素包括年龄、治疗方式（放疗、化疗、手术）、肿瘤特征（溃疡）和颅外转移（骨、肝）。XGBoost在ACED预测方面表现最佳（AUC = 0.776），而逻辑回归在CSED预测方面表现最佳（AUC = 0.694）。外部验证证实了模型具有可比性能的可靠性。
这些机器学习模型显示出强大的预测性能，可能有助于临床医生对MBM患者进行早期风险分层和治疗规划。这些模型提供了客观的风险评估工具，可以改善患者咨询，并指导积极治疗与姑息治疗决策。
