Machine learning-based models for predicting clinical outcomes after surgery in unilateral primary aldosteronism

Abstract

Unilateral subtype of primary aldosteronism (PA) is a common surgically curable form of endocrine hypertension. However, more than half of the patients with PA who undergo unilateral adrenalectomy suffer from persistent hypertension, which may discourage those with PA from undergoing adrenalectomy even when appropriate. The aim of this retrospective cross-sectional study was to develop machine learning-based models for predicting postoperative hypertensive remission using preoperative predictors that are readily available in routine clinical practice. A total of 107 patients with PA who achieved complete biochemical success after adrenalectomy were included and randomly assigned to the training and test datasets. Predictive models of complete clinical success were developed using supervised machine learning algorithms. Of 107 patients, 40 achieved complete clinical success after adrenalectomy in both datasets. Six clinical features associated with complete clinical success (duration of hypertension, defined daily dose (DDD) of antihypertensive medication, plasma aldosterone concentration (PAC), sex, body mass index (BMI), and age) were selected based on predictive performance in the machine learning-based model. The predictive accuracy and area under the curve (AUC) for the developed model in the test dataset were 77.3% and 0.884 (95% confidence interval: 0.737–1.000), respectively. In an independent external cohort, the performance of the predictive model was found to be comparable with an accuracy of 80.4% and AUC of 0.867 (95% confidence interval: 0.763–0.971). The duration of hypertension, DDD of antihypertensive medication, PAC, and BMI were non-linearly related to the prediction of complete clinical success. The developed predictive model may be useful in assessing the benefit of unilateral adrenalectomy and in selecting surgical treatment and antihypertensive medication for patients with PA in clinical practice.

A new machine learning-based prediction model for subtype diagnosis in primary aldosteronism

“…In addition, Kaneko et al. recently developed a model aimed at predicting PA subtype in general practice settings using 21 available clinical and routine biochemical variables ( 29 ).…”

“…However, a flow-chart integrating the 20-point scoring system was also developed, with an accuracy of 96.3%, and it enabled almost half of AVS procedures to be avoided, with similar performance in the external validation (17). In addition, Kaneko et al recently developed a model aimed at predicting PA subtype in general practice settings using 21 available clinical and routine biochemical variables (29).…”

Prognostic models to predict complete resolution of hypertension after adrenalectomy in primary aldosteronism: A systematic review and meta‐analysis

“…• Wachtel et al's scoring system 18 • Morisaki et al's scoring system 15 • Nomogram-based prediction score 21 • Machine learning-based model 43 • Primary aldosteronism predicting surgical outcome score 29…”

Do multiple types of confirmatory tests improve performance in predicting subtypes of primary aldosteronism?

“…Machine learning provides techniques that can automatically build computational models of complex relationships between observable and objective variables by processing available data and maximizing the performance criteria 12 . We recently developed machine learning‐based predictive models for subtype classification and postoperative outcomes of PA from baseline characteristics, including variables with multicollinearity and nonlinear relationships with the objective variables 13,14 . Therefore, machine learning analysis may be more suitable than conventional generalized linear models for clarifying the significance of multiple types of confirmatory tests in the clinical practice of PA.…”

“…12 We recently developed machine learning-based predictive models for subtype classification and postoperative outcomes of PA from baseline characteristics, including variables with multicollinearity and nonlinear relationships with the objective variables. 13,14 Therefore, machine learning analysis may be more suitable than conventional generalized linear models for clarifying the significance of multiple types of confirmatory tests in the clinical practice of PA.…”