Machine learning models predict delayed hyponatremia post-transsphenoidal surgery using clinically available features

PurposeDelayed hyponatremia (DHN), a unique complication, is the leading cause of unexpected readmission after pituitary surgery. Therefore, this study aimed to develop tools for predicting postoperative DHN in patients undergoing endoscopic transsphenoidal surgery (eTSS) for pituitary neuroendocrine tumors (PitNETs).MethodsThis was a single-center, retrospective study involving 193 patients with PitNETs who underwent eTSS. The objective variable was DHN, defined as serum sodium levels < 135 mmol/L at >= 1 time between post operative days 3 and 9. We trained four machine learning models to predict this objective variable using the clinical variables available preoperatively and on the first postoperative day. The clinical variables included patient characteristics, pituitary-related hormone levels, blood test results, radiological findings, and postoperative complications.ResultsThe random forest (RF) model demonstrated the highest (0.759 +/- 0.039) area under the curve of the receiver operating characteristic curve (ROC-AUC), followed by the support vector machine (0.747 +/- 0.034), the light gradient boosting machine (LGBM: 0.738 +/- 0.026), and the logistic regression (0.710 +/- 0.028). The highest accuracy (0.746 +/- 0.029) was observed in the LGBM model. The best-performing RF model was based on 24 features, nine of which were clinically available preoperatively.ConclusionsThe proposed machine learning models with pre- and post-resection features predicted DHN after the resection of PitNETs.

Automated summary

This study aimed to develop tools for predicting delayed hyponatremia (DHN) in patients undergoing endoscopic transsphenoidal surgery (eTSS) for pituitary neuroendocrine tumors (PitNETs). Machine learning models using pre- and post-operative clinical variables were able to accurately predict the occurrence of DHN.