Barfejani Arnavaz Hajizadeh, Rahimi Mohammad, Safdari Hassan, Gholizadeh Shahab, Borzooei Shiva, Roshanaei Ghodratollah, Golparian Mitra, Tarokhian Aidin
Royal College of Surgeons in Ireland, Dublin, Ireland.
Student Research Committee, Hamadan University of Medical Sciences, Hamadan, Iran.
Eur Arch Otorhinolaryngol. 2025 Mar;282(3):1577-1583. doi: 10.1007/s00405-024-08918-0. Epub 2024 Aug 22.
Despite the rising incidence of differentiated thyroid cancer (DTC), mortality rates have remained relatively low yet crucial for effective patient management. This study aims to develop a deep neural network capable of predicting mortality in patients with differentiated thyroid cancer.
Leveraging data from the Surveillance, Epidemiology, and End Results (SEER) database, we developed Thy-DAMP (Deep Artificial Neural Network Model for Prediction of Thyroid Cancer) to forecast mortality in DTC patients. The dataset comprised demographic, histologic, and staging information. Following data normalization and feature encoding, the dataset was partitioned into training, testing, and validation subsets, with model hyperparameters fine-tuned via cross-validation.
Among the 63,513 patients, the mean age was 48.22 years (SD = 14.8), with 77.32% being female. Papillary carcinoma emerged as the predominant subtype, representing 62.94% of cases. The majority presented with stage I disease (73.96%). Thy-DAMP demonstrated acceptable performance metrics on both the test and validation sets. Sensitivity was 83.24% (95% CI 76.95-88.40%), specificity was 93.53% (95% CI 93.01-94.02%), and accuracy stood at 93.33% (95% CI 92.82-93.83%). The model exhibited a positive predictive value of 19.76% (95% CI 18.20-21.42%) and a negative predictive value of 99.66% (95% CI 99.53-99.75%). Additionally, Thy-DAMP demonstrated a positive likelihood ratio of 12.86 (95% CI 11.62-14.23), a negative likelihood ratio of 0.18 (95% CI 0.13-0.25), and an area under the receiver operating characteristic curve (AUROC) of 0.95. The model was externally validated on a separate dataset with nearly identical performance.
Thy-DAMP showcases considerable promise in accurately predicting mortality in DTC patients, leveraging limited set of patient data.
尽管分化型甲状腺癌（DTC）的发病率不断上升，但其死亡率相对较低，但对于有效的患者管理至关重要。本研究旨在开发一种能够预测分化型甲状腺癌患者死亡率的深度神经网络。
利用监测、流行病学和最终结果（SEER）数据库的数据，我们开发了Thy-DAMP（用于预测甲状腺癌的深度人工神经网络模型）来预测DTC患者的死亡率。数据集包括人口统计学、组织学和分期信息。在进行数据归一化和特征编码后，将数据集划分为训练集、测试集和验证集，并通过交叉验证对模型超参数进行微调。
在63513例患者中，平均年龄为48.22岁（标准差=14.8），女性占77.32%。乳头状癌是主要亚型，占病例的62.94%。大多数患者为I期疾病（73.96%）。Thy-DAMP在测试集和验证集上均表现出可接受的性能指标。敏感性为83.24%（95%置信区间76.95-88.40%），特异性为93.53%（95%置信区间93.01-94.02%），准确率为93.33%（95%置信区间92.82-93.83%）。该模型的阳性预测值为19.76%（95%置信区间18.20-21.42%），阴性预测值为99.66%（95%置信区间99.53-99.75%）。此外，Thy-DAMP的阳性似然比为12.86（95%置信区间11.62-14.23），阴性似然比为0.18（95%置信区间0.13-0.25），受试者工作特征曲线下面积（AUROC）为0.95。该模型在一个单独的数据集上进行了外部验证，性能几乎相同。
Thy-DAMP在利用有限的患者数据准确预测DTC患者死亡率方面显示出巨大的前景。
