Spreafico Marta, Hazewinkel Audinga-Dea, van de Sande Michiel A J, Gelderblom Hans, Fiocco Marta
Mathematical Institute, Leiden University, Einsteinweg 55, 2333 CC Leiden, The Netherlands.
Department of Biomedical Data Sciences-Medical Statistics, Leiden University Medical Center, Albinusdreef 2, 2333 ZA Leiden, The Netherlands.
Cancers (Basel). 2024 Aug 19;16(16):2880. doi: 10.3390/cancers16162880.
Since the mid-1980s, there has been little progress in improving survival of patients diagnosed with osteosarcoma. Survival prediction models play a key role in clinical decision-making, guiding healthcare professionals in tailoring treatment strategies based on individual patient risks. The increasing interest of the medical community in using machine learning (ML) for predicting survival has sparked an ongoing debate on the value of ML techniques versus more traditional statistical modelling (SM) approaches. This study investigates the use of SM versus ML methods in predicting overall survival (OS) using osteosarcoma data from the EURAMOS-1 clinical trial (NCT00134030). The well-established Cox proportional hazard model is compared to the extended Cox model that includes time-varying effects, and to the ML methods random survival forests and survival neural networks. The impact of eight variables on OS predictions is explored. Results are compared on different model performance metrics, variable importance, and patient-specific predictions. The article provides comprehensive insights to aid healthcare researchers in evaluating diverse survival prediction models for low-dimensional clinical data.
自20世纪80年代中期以来，在提高骨肉瘤确诊患者的生存率方面进展甚微。生存预测模型在临床决策中起着关键作用，指导医疗保健专业人员根据个体患者风险制定治疗策略。医学界对使用机器学习（ML）预测生存的兴趣日益浓厚，引发了关于ML技术与更传统的统计建模（SM）方法价值的持续争论。本研究使用来自EURAMOS-1临床试验（NCT00134030）的骨肉瘤数据，调查SM与ML方法在预测总生存期（OS）方面的应用。将成熟的Cox比例风险模型与包含时变效应的扩展Cox模型以及ML方法随机生存森林和生存神经网络进行比较。探讨八个变量对OS预测的影响。在不同的模型性能指标、变量重要性和患者特异性预测方面比较结果。本文提供了全面的见解，以帮助医疗保健研究人员评估针对低维临床数据的各种生存预测模型。
