Machine learning approach to predict subtypes of primary aldosteronism is helpful to estimate indication of adrenal vein sampling

Introduction Primary aldosteronism (PA) is a common disease. Especially in unilateral PA (UPA), the risk of cardiovascular disease is high and proper localization is important. Adrenal vein sampling (AVS) is commonly used to localize PA, but its availability is limited. Therefore, it is important to predict the unilateral or bilateral PA and to choose the appropriate cases for AVS or watchful observation. Aim The purpose of this study is to develop a model using machine learning to predict bilateral or unilateral PA to extract cases for AVS or watchful observation. Methods We retrospectively analyzed 154 patients diagnosed with PA and who underwent AVS at our hospital between January 2010 and June 2021. Based on machine learning, we determined predictors of PA subtypes diagnosis from the results of blood and loading tests. Results The accuracy of the machine learning was 88% and the top predictors of the UPA were plasma aldosterone concentration after the saline infusion test, aldosterone to renin ratio after the captopril challenge test, serum potassium and aldosterone-to-renin ratio. By using these factors, the accuracy, sensitivity, specificity and the area under the curve (AUC) were 91%, 70%, 99% and 0.91, respectively. Furthermore, we examined the surgical outcomes of UPA and found that the group diagnosed as unilateral by the predictors showed improvement in clinical findings, while the group diagnosed as bilateral by the predictors showed no improvement. Conclusion Our predictive model based on machine learning can support to choose the performance of adrenal vein sampling or watchful observation.