Park Yae Won, Eom Jihwan, Kim Sooyon, Kim Hwiyoung, Ahn Sung Soo, Ku Cheol Ryong, Kim Eui Hyun, Lee Eun Jig, Kim Sun Ho, Lee Seung-Koo
Department of Radiology and Research Institute of Radiological Science and Center for Clinical Imaging Data Science, Yonsei University College of Medicine, Seoul, Korea.
Pituitary Tumor Center, Severance Hospital, Seoul, Korea.
J Clin Endocrinol Metab. 2021 Jul 13;106(8):e3069-e3077. doi: 10.1210/clinem/dgab159.
Early identification of the response of prolactinoma patients to dopamine agonists (DA) is crucial in treatment planning.
To develop a radiomics model using an ensemble machine learning classifier with conventional magnetic resonance images (MRIs) to predict the DA response in prolactinoma patients.
Retrospective study.
Severance Hospital, Seoul, Korea.
A total of 177 prolactinoma patients who underwent baseline MRI (109 DA responders and 68 DA nonresponders) were allocated to the training (n = 141) and test (n = 36) sets. Radiomic features (n = 107) were extracted from coronal T2-weighed MRIs. After feature selection, single models (random forest, light gradient boosting machine, extra-trees, quadratic discrimination analysis, and linear discrimination analysis) with oversampling methods were trained to predict the DA response. A soft voting ensemble classifier was used to achieve the final performance. The performance of the classifier was validated in the test set.
The ensemble classifier showed an area under the curve (AUC) of 0.81 [95% confidence interval (CI), 0.74-0.87] in the training set. In the test set, the ensemble classifier showed an AUC, accuracy, sensitivity, and specificity of 0.81 (95% CI, 0.67-0.96), 77.8%, 78.6%, and 77.3%, respectively. The ensemble classifier achieved the highest performance among all the individual models in the test set.
Radiomic features may be useful biomarkers to predict the DA response in prolactinoma patients.
早期识别泌乳素瘤患者对多巴胺激动剂（DA）的反应对于治疗方案的制定至关重要。
利用集成机器学习分类器和传统磁共振成像（MRI）开发一种放射组学模型，以预测泌乳素瘤患者对DA的反应。
回顾性研究。
韩国首尔Severance医院。
总共177例接受基线MRI检查的泌乳素瘤患者（109例DA反应者和68例DA无反应者）被分配到训练组（n = 141）和测试组（n = 36）。从冠状位T2加权MRI中提取放射组学特征（n = 107）。经过特征选择后，使用过采样方法训练单模型（随机森林、轻梯度提升机、极端随机树、二次判别分析和线性判别分析）来预测DA反应。使用软投票集成分类器来实现最终性能。在测试组中验证分类器的性能。
在训练组中，集成分类器的曲线下面积（AUC）为0.81[95%置信区间（CI），0.74 - 0.87]。在测试组中，集成分类器的AUC、准确率、灵敏度和特异度分别为0.81（95%CI，0.67 - 0.96）、77.8%、78.6%和77.3%。在测试组中，集成分类器在所有单模型中表现出最高性能。
放射组学特征可能是预测泌乳素瘤患者对DA反应的有用生物标志物。
