The Primary Aldosteronism Surgical Outcome Score for the Prediction of Clinical Outcomes After Adrenalectomy for Unilateral Primary Aldosteronism

Abstract

Objective: To develop a prediction model for clinical outcomes after unilateral adrenalectomy for unilateral primary aldosteronism. Summary Background Data: Unilateral primary aldosteronism is the most common surgically curable form of endocrine hypertension. Surgical resection of the dominant overactive adrenal in unilateral primary aldosteronism results in complete clinical success with resolution of hypertension without antihypertensive medication in less than half of patients with a wide between-center variability. Methods: A linear discriminant analysis (LDA) model was built using data of 380 patients treated by adrenalectomy for unilateral primary aldosteronism to classify post-surgical clinical outcomes. The total cohort was then randomly divided into training (280 patients) and test (100 patients) datasets to create and validate a score system to predict clinical outcomes. An online tool (PASO [Primary Aldosteronism Surgical Outcome] predictor) was developed to facilitate the use of the predictive score. Results: Six presurgical factors associated with complete clinical success (known duration of hypertension, sex, antihypertensive medication dosage, body mass index, target organ damage and size of largest nodule at imaging) were selected based on classification performance in the LDA model. A 25-point predictive score was built with an optimal cutoff of greater than 16 points (accuracy of prediction = 79.2%; specificity = 84.4%; sensitivity = 71.3%) with an area under the curve of 0.839. Conclusions: The predictive score and the PASO predictor can be used in a clinical setting to differentiate patients who are likely to be clinically cured after surgery from those who will need continuous surveillance after surgery due to persistent hypertension.

An extracellular vesicle epitope profile is associated with acute myocardial infarction

“…Supervised machine learning algorithms and in particular linear discriminant analysis (LDA) and random forest (RF) models have been exploited in the context of diagnostic modelling for clinical research, as described previously 29,30 . LDA was used as a strategy for feature reduction to build the canonical plot.…”

Immune profiling of plasma-derived extracellular vesicles identifies Parkinson disease

“…Machine learning supervised algorithms are exploited in clinical practice to formulate predictions of selected outcomes based on a given set of labeled paired input-output training sample data. 22,23 The linear discriminant analysis was used to build the 3D canonical plot (figure 2B); canonical components 1, 2, and 3 were calculated from weighted linear combinations of variables to maximize separation between the 4 groups (HC, PD, MSA, and AP-Tau); in the plot, each patient is represented by a point, the center of the spheres indicates the mean of (canonical 1; canonical 2; canonical 3) for each diagnosis, and spheres include patients with a linear combination coefficient that falls within the mean ± SD (canonical 1 ± SD; canonical 2 ± SD; canonical 3 ± SD). A diagnostic model was built through a random forest (RF) classification algorithm on the training cohort (n = 63); the algorithm created 20 different classification trees with a maximum number of 8 splits for each tree.…”

Mass Spectrometry Imaging Establishes 2 Distinct Metabolic Phenotypes of Aldosterone-Producing Cell Clusters in Primary Aldosteronism

“…Defined daily dose is the assumed average maintenance dose per day for a drug used from its main indication in adults according to ATC/DDD Index 2018 (https://www.whocc.no/atc_ddd_index/) and can be calculated using an online tool (https://github.com/ABurrello/ PASO-Predictor/raw/master/00 -PASO Predictor.xlsm). 45 Aldo indicates plasma aldosterone concentration; APA, aldosterone-producing adenoma; APCC, aldosterone-producing cell cluster; ARR_DRC, aldosterone-to-renin ratio calculated using direct renin concentrations; BMI, body mass index; DBP, diastolic blood pressure; DDD, defined daily dose; DRC, direct renin concentration; F, female; HTN, hypertension; ID, identification; M, male; SBP, systolic blood pressure; and serum K + , lowest serum potassium ion concentration.…”