Supplementary Material for: Prediction of Recurrence after Transsphenoidal Surgery for Cushing’s Disease: The Use of Machine Learning Algorithms

Background: There are no reliable predictive models for recurrence after transsphenoidal surgery (TSS) for Cushing’s disease (CD). Objectives: This study aimed to develop machine learning (ML)-based predictive models for CD recurrence after initial TSS and to evaluate their performance. Method: A total of 354 CD patients were included in this retrospective, supervised learning, data mining study. Predictive models for recurrence were developed according to 17 variables using 7 algorithms. Models were evaluated based on the area under the receiver operating characteristic curve (AUC). Results: All patients were followed up for over 12 months (mean ± SD 43.80 ± 35.61). The recurrence rate was 13.0%. Age (p < 0.001), postoperative morning serum cortisol nadir (p = 0.002), and postoperative (p < 0.001) and preoperative (p = 0.04) morning adrenocorticotropin (ACTH) level were significantly related to recurrence. AUCs of the 7 models ranged from 0.608 to 0.781. The best performance (AUC = 0.781, 95% CI 0.706, 0.856) appeared when 8 variables were introduced to the random forest (RF) algorithm, which was much better than that of logistic regression (AUC = 0.684, p = 0.008) and that of using only postoperative morning serum cortisol (AUC = 0.635, p < 0.001). According to the feature selection algorithms, the top 3 predictors were age, postoperative serum cortisol, and postoperative ACTH. Conclusions: Using ML-based models for prediction of the recurrence after initial TSS for CD is feasible, and RF performs best. The performance of most of ML-based models was significantly better than that of some conventional models.背景：目前尚无针对库欣病（Cushing’s disease, CD）患者行经蝶窦手术（transsphenoidal surgery, TSS）后复发的可靠预测模型。 研究目的：本研究旨在构建库欣病患者初次经蝶窦手术后复发风险的机器学习（machine learning, ML）预测模型，并评估其预测性能。 研究方法：本项回顾性监督学习数据挖掘研究共纳入354例库欣病患者。研究基于17项临床变量，采用7种算法构建疾病复发预测模型，并以受试者工作特征曲线下面积（area under the receiver operating characteristic curve, AUC）作为模型性能评估指标。 研究结果：所有患者的随访时长均超过12个月，平均随访时长±标准差为43.80±35.61。总体复发率为13.0%。单因素分析显示，年龄（p<0.001）、术后清晨血清皮质醇最低点（p=0.002）、术前及术后清晨促肾上腺皮质激素（adrenocorticotropin, ACTH）水平（分别为p=0.04和p<0.001）与疾病复发显著相关。7种模型的AUC值区间为0.608至0.781。其中，纳入8项变量的随机森林（random forest, RF）模型表现最优，AUC为0.781（95%置信区间：0.706~0.856），其性能显著优于逻辑回归（logistic regression）模型（AUC=0.684，p=0.008）及仅采用术后清晨血清皮质醇的单因素模型（AUC=0.635，p<0.001）。通过特征选择算法筛选出的前3位预测因子依次为年龄、术后血清皮质醇及术后促肾上腺皮质激素。 研究结论：采用机器学习模型预测库欣病患者初次经蝶窦手术后复发风险具有可行性，其中随机森林模型的预测性能最优。多数机器学习模型的预测性能显著优于部分传统预测模型。