Lourdault Kristel, Cowman Arthur W, Hanes Douglas, Scholer Anthony J, Aguilar Tyler, Essner Richard
Saint John's Cancer Institute at Providence St. John's Health Center, Santa Monica, California, USA.
Providence Research Network, Portland, Oregon, USA.
J Surg Oncol. 2025 Mar;131(4):685-693. doi: 10.1002/jso.27976. Epub 2024 Nov 17.
Clinical nomograms have been developed to predict sentinel lymph node (SLN) status in early-stage melanoma patients, but the clinical utility of these tools remains debatable. We created and validated a nomogram using data from a randomized clinical trial and assessed its accuracy against the well-validated Melanoma Institute Australia (MIA) nomogram.
We developed our model to predict SLN status using logistic regression on clinicopathological patient data from the Multicenter Selective Lymphadenectomy Trial-I. The model was externally validated using the National Cancer Database (NCDB) data set, and its performance was compared to that of the MIA nomogram.
Our model had good discrimination between positive and negative SLNs, with a training set area under the curve (AUC) of 0.706 (0.661-0.751). Our model achieved an AUC of 0.715 (0.706-0.724) compared to 0.723 (0.715-0.731) with the MIA model, using the NCDB set.
Our model performed similarly to the MIA model, confirming that despite using different clinical features and data sets, no clinical nomogram is currently accurate enough for clinical use.
已开发出临床列线图来预测早期黑色素瘤患者前哨淋巴结（SLN）状态，但这些工具的临床实用性仍存在争议。我们利用一项随机临床试验的数据创建并验证了一个列线图，并将其准确性与经过充分验证的澳大利亚黑色素瘤研究所（MIA）列线图进行了评估。
我们使用多中心选择性淋巴结清扫试验-I中患者的临床病理数据，通过逻辑回归开发了预测SLN状态的模型。该模型使用国家癌症数据库（NCDB）数据集进行外部验证，并将其性能与MIA列线图进行比较。
我们的模型在阳性和阴性SLN之间具有良好的区分能力，训练集曲线下面积（AUC）为0.706（0.661-0.751）。使用NCDB数据集时，我们的模型AUC为0.715（0.706-0.724），而MIA模型为0.723（0.715-0.731）。
我们的模型表现与MIA模型相似，证实尽管使用了不同的临床特征和数据集，但目前没有临床列线图准确到足以用于临床。
