Machine-Learning Prediction of Postoperative Pituitary Hormonal Outcomes in Nonfunctioning Pituitary Adenomas: A Multicenter Study

Objective: There were no accurate predictive models for hormonal prognosis in nonfunctioning pituitary adenoma (NFPA). This study aimed to develop machine learning (ML) models to facilitate the prognostic assessment of pituitary hormone outcomes after surgery. Methods: A total of 215 male patients with NFPA, who underwent surgery in four medical centers from 2015 to 2021, were retrospectively reviewed. The data were pooled after heterogeneity assessment, and they were randomly divided into training and testing sets (172:43). Six ML models and logistic regression models were developed using six anterior pituitary hormones. Results: Only thyroid-stimulating hormone (p < 0.001), follicle-stimulating hormone (p < 0.001), and prolactin (PRL) (p < 0.001) decreased significantly following surgery, whereas growth hormone (GH) (p < 0.001) increased significantly. The postoperative GH (p = 0.07) levels were slightly higher in patients with gross total resection, but the PRL (p = 0.03) level was significantly lower than that in patients with subtotal resection. The optimal model achieved area-under-the-receiver-operating-characteristic-curve values of 0.82, 0.74, and 0.85 in predicting hormonal hypofunction, new deficiency, and hormonal recovery following surgery. According to feature importance analyses, the preoperative levels of the same type and other hormones were all important in predicting postoperative individual hormonal hypofunction. Conclusion: Fluctuation in anterior pituitary hormones varies with increases and decreases due to transsphenoidal surgery. The ML models could accurately predict postoperative pituitary hormone outcomes based on preoperative anterior pituitary hormones in NFPA.