Development and validation of a predictive model for predicting cardiovascular morbidity in patients after pheochromocytoma surgery.

Objective: Although surgical resection is the primary treatment method for pheochromocytoma, it carries a high risk of morbidity, especially cardiovascular-related morbidity. There are no models for predicting cardiovascular morbidity after pheochromocytoma surgery. Thus, we developed and validated a model for the preoperative prediction of cardiovascular morbidity after pheochromocytoma surgery.

Design: The development cohort consisted of 262 patients who underwent unilateral laparoscopic or open pheochromocytoma surgery at our centre between 1 January 2007 and 31 December 2016. Patient's clinicopathologic data were recorded. The LASSO regression was used for data dimension reduction and feature selection; then, multivariable logistic regression analysis was used to develop the prediction model. An independent cohort consisting of 112 consecutive patients from 1 January 2017 and 31 December 2018 was used for validation. The performance of this prediction model was assessed with respect to discrimination, calibration and clinical usefulness.

Results: The predictors in this prediction model included body mass index, history of coronary heart disease, tumour size, intraoperative hemodynamic instability and use of crystal/colloid fluids preoperatively. In the validation cohort, the model showed good discrimination with an AUROC of 0.869 (95% CI, 0.797, 0.940) and good calibration (unreliability test, P = .852). Decision curve analysis demonstrated that the model was also clinically useful.

Conclusion: This study presented a good nomogram that could facilitate the preoperative individualized prediction of cardiovascular morbidity after pheochromocytoma surgery, which may help improve perioperative strategy and good treatment outcomes.