治疗转移性疾病：哪种生存模型最适合临床？
Treating metastatic disease: Which survival model is best suited for the clinic?
机构信息
Regenerative Medicine, Naval Medical Research Center, 503 Robert Grant Ave, Silver Spring, MD 20910, USA.
出版信息
Clin Orthop Relat Res. 2013 Mar;471(3):843-50. doi: 10.1007/s11999-012-2577-z.
BACKGROUND
To avoid complications associated with under- or overtreatment of patients with skeletal metastases, doctors need accurate survival estimates. Unfortunately, prognostic models for patients with skeletal metastases of the extremities are lacking, and physician-based estimates are generally inaccurate.
QUESTIONS/PURPOSES: We developed three types of prognostic models and compared them using calibration plots, receiver operating characteristic (ROC) curves, and decision curve analysis to determine which one is best suited for clinical use.
METHODS
A training set consisted of 189 patients who underwent surgery for skeletal metastases. We created models designed to predict 3- and 12-month survival using three methods: an Artificial Neural Network (ANN), a Bayesian Belief Network (BBN), and logistic regression. We then performed crossvalidation and compared the models in three ways: calibration plots plotting predicted against actual risk; area under the ROC curve (AUC) to discriminate the probability that a patient who died has a higher predicted probability of death compared to a patient who did not die; and decision curve analysis to quantify the clinical consequences of over- or undertreatment.
RESULTS
All models appeared to be well calibrated, with the exception of the BBN, which underestimated 3-month survival at lower probability estimates. The ANN models had the highest discrimination, with an AUC of 0.89 and 0.93, respectively, for the 3- and 12-month models. Decision analysis revealed all models could be used clinically, but the ANN models consistently resulted in the highest net benefit, outperforming the BBN and logistic regression models.
CONCLUSIONS
Our observations suggest use of the ANN model to aid decisions about surgery would lead to better patient outcomes than other alternative approaches to decision making.
LEVEL OF EVIDENCE
Level II, prognostic study. See Instructions for Authors for a complete description of levels of evidence.
背景
为避免治疗骨骼转移患者过度或不足的并发症，医生需要准确的生存估计。不幸的是，缺乏四肢骨骼转移患者的预后模型，基于医生的估计通常不准确。
问题/目的：我们开发了三种类型的预后模型，并通过校准图、接受者操作特征（ROC）曲线和决策曲线分析来比较它们，以确定哪种最适合临床使用。
方法
训练集由 189 名接受手术治疗骨骼转移的患者组成。我们使用三种方法创建了预测 3 个月和 12 个月生存率的模型：人工神经网络（ANN）、贝叶斯信念网络（BBN）和逻辑回归。然后我们进行了交叉验证，并通过三种方式比较了模型：校准图绘制预测风险与实际风险的关系；ROC 曲线下面积（AUC）以区分死亡患者的预测死亡概率是否高于未死亡患者；决策曲线分析以量化过度或不足治疗的临床后果。
结果
所有模型似乎都经过了良好的校准，除了 BBN 模型，它在较低的概率估计下低估了 3 个月的生存率。ANN 模型的判别能力最高，其 3 个月和 12 个月模型的 AUC 分别为 0.89 和 0.93。决策分析表明所有模型都可以在临床上使用，但 ANN 模型始终导致最高的净收益，优于 BBN 和逻辑回归模型。
结论
我们的观察结果表明，使用 ANN 模型辅助手术决策将导致比其他替代决策方法更好的患者结局。
证据水平
II 级，预后研究。请参阅作者说明以获取完整的证据水平描述。
Zotero 插件