Background

Using machine learning (ML) to explore the noninvasive differential diagnosis of Cushing’s disease (CD) and ectopic corticotropin (ACTH) secretion (EAS) model is the next hot research topic. This study was to develop and evaluate ML models for differentially diagnosing CD and EAS in ACTH-dependent Cushing’s syndrome (CS).

Methods

Two hundred sixty-four CD and forty-seven EAS were randomly divided into training and validation and test datasets. We applied 8 ML algorithms to select the most suitable model. The diagnostic performance of the optimal model and bilateral petrosal sinus sampling (BIPSS) were compared in the same cohort.

Results

Eleven adopted variables included age, gender, BMI, duration of disease, morning cortisol, serum ACTH, 24-h UFC, serum potassium, HDDST, LDDST, and MRI. After model selection, the Random Forest (RF) model had the most extraordinary diagnostic performance, with a ROC AUC of 0.976 ± 0.03, a sensitivity of 98.9% ± 4.4%, and a specificity of 87.9% ± 3.0%. The serum potassium, MRI, and serum ACTH were the top three most important features in the RF model. In the validation dataset, the RF model had an AUC of 0.932, a sensitivity of 95.0%, and a specificity of 71.4%. In the complete dataset, the ROC AUC of the RF model was 0.984 (95% CI 0.950–0.993), which was significantly higher than HDDST and LDDST (both p < 0.001). There was no significant statistical difference in the comparison of ROC AUC between the RF model and BIPSS (baseline ROC AUC 0.988 95% CI 0.983–1.000, after stimulation ROC AUC 0.992 95% CI 0.983–1.000). This diagnostic model was shared as an open-access website.

Conclusions

A machine learning-based model could be a practical noninvasive approach to distinguishing CD and EAS. The diagnostic performance might be close to BIPSS.

中文翻译：

---

用于库欣病和异位 ACTH 分泌综合征鉴别诊断的机器学习模型

背景

利用机器学习（ML）探索库欣病（CD）和异位促肾上腺皮质激素（ACTH）分泌（EAS）模型的无创鉴别诊断是下一个研究热点。本研究旨在开发和评估用于鉴别诊断 ACTH 依赖性库欣综合征 (CS) 中 CD 和 EAS 的 ML 模型。

方法

264 个 CD 和 47 个 EAS 被随机分为训练、验证和测试数据集。我们应用 8 种 ML 算法来选择最合适的模型。在同一队列中比较了最佳模型和双侧岩窦取样（BIPSS）的诊断性能。

结果

采用的 11 个变量包括年龄、性别、BMI、病程、早晨皮质醇、血清 ACTH、24 小时 UFC、血清钾、HDDST、LDDST 和 MRI。模型选择后，随机森林（RF）模型具有最出色的诊断性能，ROC AUC为0.976±0.03，敏感性为98.9%±4.4%，特异性为87.9%±3.0%。血清钾、MRI 和血清 ACTH 是 RF 模型中最重要的三个特征。在验证数据集中，RF模型的AUC为0.932，敏感性为95.0%，特异性为71.4%。在完整数据集中，RF模型的ROC AUC为0.984（95% CI 0.950-0.993），显着高于HDDST和LDDST（均p  < 0.001）。RF模型和BIPSS之间的ROC AUC比较没有显着的统计学差异（基线ROC AUC 0.988 95% CI 0.983–1.000，刺激后ROC AUC 0.992 95% CI 0.983–1.000）。该诊断模型作为开放访问网站共享。

结论

基于机器学习的模型可能是区分 CD 和 EAS 的实用非侵入性方法。诊断性能可能接近 BIPSS。