利用白细胞区分轻度自主皮质醇分泌和无功能肾上腺腺瘤的新模型。
A novel model using leukocytes to differentiating mild autonomous cortisol secretion and non-functioning adrenal adenoma.
机构信息
Department of Urology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences, Peking Union Medical College, Beijing, China.
Department of Urology, Hainan Affiliated Hospital of Hainan Medical University (Hainan General Hospital), Haikou, China.
出版信息
Sci Rep. 2024 Oct 9;14(1):23557. doi: 10.1038/s41598-024-74452-y.
BACKGROUND
Mild autonomous cortisol secretion (MACS) accounts for a significant proportion of adrenal incidentaloma. Current endocrinological screening tests for MACS are complex, particularly in areas with limited medical resources. This study aimed to develop a diagnostic tool based on leukocyte-related parameters to differentiate between MACS and non-functioning adrenal adenoma (NFA).
METHODS
Inthis retrospective case-control study, propensity score-matching was used to select 567 patients from a cohort of 1108 patients (201 MACS, 907 NFA). External validation cohort included 52MACS and 48 NFA from two hospitals, which did not overlap with the modeling cohort patients. Leukocyte-related parameters were evaluated, and the diagnostic efficacy of each parameter was assessed by calculating Youden's J index (J) and the area under the curve (AUC). The study population was divided into training and testing samples using a 10-fold cross-validation method. Machine learning (ML) and classification and regression tree (CART) model were established.
RESULTS
After propensity score matching, 567 patients were enrolled, including 197 MACS and 370 NFA. With the exception of basophil percentage, all other parameters differed significantly between the two groups. Lymphocyte count, lymphocyte percentage, eosinophils count, eosinophils percentage, and basophil percentage were lower in the MACS group compared to the NFA group. Eosinophils percentage demonstrated the highest AUC (0.650), with a sensitivity of 51.3% and specificity of 73.2%. The ML model, based on multiple parameters,exhibited better performance in diagnosing MACS (sensitivity 76%, specificity 77.4%, and AUC 0.818). A clinically usable CART model achieved an AUC of 0.872, with a sensitivity of 95% and a specificity of 75.7%. In the validation cohort, the prediction accuracy of the ML model and the CART model were 0.784 and 0.798, respectively.
CONCLUSION
TheCART diagnostic model, constructed based on leukocyte-related parameters, could assist clinicians in distinguishing between MACS and NFA.
背景
轻度自主皮质醇分泌（MACS）占肾上腺意外瘤的很大比例。目前用于 MACS 的内分泌筛查测试较为复杂，特别是在医疗资源有限的地区。本研究旨在开发一种基于白细胞相关参数的诊断工具，以区分 MACS 和无功能肾上腺腺瘤（NFA）。
方法
在这项回顾性病例对照研究中，使用倾向评分匹配从 1108 例患者队列中选择了 567 例患者（201 例 MACS，907 例 NFA）。外部验证队列包括来自两家医院的 52 例 MACS 和 48 例 NFA，与建模队列患者无重叠。评估了白细胞相关参数，并通过计算 Youden's J 指数（J）和曲线下面积（AUC）来评估每个参数的诊断效果。使用 10 折交叉验证法将研究人群分为训练和测试样本。建立了机器学习（ML）和分类回归树（CART）模型。
结果
经过倾向评分匹配后，共纳入 567 例患者，其中 MACS 组 197 例，NFA 组 370 例。除嗜碱性粒细胞百分比外，两组间其他参数差异均有统计学意义。MACS 组的淋巴细胞计数、淋巴细胞百分比、嗜酸性粒细胞计数、嗜酸性粒细胞百分比和嗜碱性粒细胞百分比均低于 NFA 组。嗜酸性粒细胞百分比的 AUC 最高（0.650），其敏感性为 51.3%，特异性为 73.2%。基于多个参数的 ML 模型在诊断 MACS 方面表现出更好的性能（敏感性 76%，特异性 77.4%，AUC 0.818）。一个可临床应用的 CART 模型的 AUC 为 0.872，敏感性为 95%，特异性为 75.7%。在验证队列中，ML 模型和 CART 模型的预测准确性分别为 0.784 和 0.798。
结论
基于白细胞相关参数构建的 CART 诊断模型可帮助临床医生区分 MACS 和 NFA。
Zotero 插件