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

<b><i>Background:</i></b> There are no reliable predictive models for recurrence after transsphenoidal surgery (TSS) for Cushing’s disease (CD). <b><i>Objectives:</i></b> This study aimed to develop machine learning (ML)-based predictive models for CD recurrence after initial TSS and to evaluate their performance. <b><i>Method:</i></b> 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). <b><i>Results:</i></b> All patients were followed up for over 12 months (mean ± SD 43.80 ± 35.61). The recurrence rate was 13.0%. Age (<i>p</i> &#x3c; 0.001), postoperative morning serum cortisol nadir (<i>p</i> = 0.002), and postoperative (<i>p</i> &#x3c; 0.001) and preoperative (<i>p</i> = 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, <i>p</i> = 0.008) and that of using only postoperative morning serum cortisol (AUC = 0.635, <i>p</i> &#x3c; 0.001). According to the feature selection algorithms, the top 3 predictors were age, postoperative serum cortisol, and postoperative ACTH. <b><i>Conclusions:</i></b> 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.