1
|
Chen PT, Li PY, Liu KL, Wu VC, Lin YH, Chueh JS, Chen CM, Chang CC. Machine Learning Model with Computed Tomography Radiomics and Clinicobiochemical Characteristics Predict the Subtypes of Patients with Primary Aldosteronism. Acad Radiol 2024; 31:1818-1827. [PMID: 38042624 DOI: 10.1016/j.acra.2023.10.015] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/04/2023] [Revised: 10/04/2023] [Accepted: 10/05/2023] [Indexed: 12/04/2023]
Abstract
RATIONALE AND OBJECTIVES Adrenal venous sampling (AVS) is the primary method for differentiating between primary aldosterone (PA) subtypes. The aim of study is to develop prediction models for subtyping of patients with PA using computed tomography (CT) radiomics and clinicobiochemical characteristics associated with PA. MATERIALS AND METHODS This study retrospectively enrolled 158 patients with PA who underwent AVS between January 2014 and March 2021. Neural network machine learning models were developed using a two-stage analysis of triple-phase abdominal CT and clinicobiochemical characteristics. In the first stage, the models were constructed to classify unilateral or bilateral PA; in the second stage, they were designed to determine the predominant side in patients with unilateral PA. The final proposed model combined the best-performing models from both stages. The model's performance was evaluated using repeated stratified five-fold cross-validation. We employed paired t-tests to compare its performance with the conventional imaging evaluations made by radiologists, which categorize patients as either having bilateral PA or unilateral PA on one side. RESULTS In the first stage, the integrated model that combines CT radiomic and clinicobiochemical characteristics exhibited the highest performance, surpassing both the radiomic-alone and clinicobiochemical-alone models. It achieved an accuracy and F1 score of 80.6% ± 3.0% and 74.8% ± 5.2% (area under the receiver operating curve [AUC] = 0.778 ± 0.050). In the second stage, the accuracy and F1 score of the radiomic-based model were 88% ± 4.9% and 81.9% ± 6.2% (AUC=0.831 ± 0.087). The proposed model achieved an accuracy and F1 score of 77.5% ± 3.9% and 70.5% ± 7.1% (AUC=0.771 ± 0.046) in subtype diagnosis and lateralization, surpassing the accuracy and F1 score achieved by radiologists' evaluation (p < .05). CONCLUSION The proposed machine learning model can predict the subtypes and lateralization of PA. It yields superior results compared to conventional imaging evaluation and has potential to supplement the diagnostic process in PA.
Collapse
Affiliation(s)
- Po-Ting Chen
- Institute of Biomedical Engineering, College of Medicine and College of Engineering, National Taiwan University, Taipei, Taiwan (P.T.C, P.Y.L., C.M.C.); Department of Medical Imaging, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei, Taiwan (P.T.C., K.L.L., C.C.C.); Department of Medical Imaging, National Taiwan University Cancer Center and National Taiwan University College of Medicine, Taipei, Taiwan (P.T.C., K.L.L.); Department of Medical Imaging, National Taiwan University Hospital Hsinchu Branch, Hsinchu, Taiwan (P.T.C.)
| | - Pei-Yan Li
- Institute of Biomedical Engineering, College of Medicine and College of Engineering, National Taiwan University, Taipei, Taiwan (P.T.C, P.Y.L., C.M.C.)
| | - Kao-Lang Liu
- Department of Medical Imaging, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei, Taiwan (P.T.C., K.L.L., C.C.C.); Department of Medical Imaging, National Taiwan University Cancer Center and National Taiwan University College of Medicine, Taipei, Taiwan (P.T.C., K.L.L.)
| | - Vin-Cent Wu
- Division of Nephrology, Department of Internal Medicine, National Taiwan University Hospital, National Taiwan University College of Medicine, Taipei, Taiwan (V.C.W.)
| | - Yen-Hung Lin
- Division of Cardiology, Department of Internal Medicine, National Taiwan University Hospital, National Taiwan University College of Medicine, Taipei, Taiwan (Y.H.L.)
| | - Jeff S Chueh
- Department of Urology, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei, Taiwan (J.S.C.)
| | - Chung-Ming Chen
- Institute of Biomedical Engineering, College of Medicine and College of Engineering, National Taiwan University, Taipei, Taiwan (P.T.C, P.Y.L., C.M.C.)
| | - Chin-Chen Chang
- Department of Medical Imaging, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei, Taiwan (P.T.C., K.L.L., C.C.C.).
| |
Collapse
|
3
|
Ekman N, Grossman AB, Dworakowska D. What We Know about and What Is New in Primary Aldosteronism. Int J Mol Sci 2024; 25:900. [PMID: 38255973 PMCID: PMC10815558 DOI: 10.3390/ijms25020900] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/14/2023] [Revised: 01/08/2024] [Accepted: 01/09/2024] [Indexed: 01/24/2024] Open
Abstract
Primary aldosteronism (PA), a significant and curable cause of secondary hypertension, is seen in 5-10% of hypertensive patients, with its prevalence contingent upon the severity of the hypertension. The principal aetiologies of PA include bilateral idiopathic hypertrophy (BIH) and aldosterone-producing adenomas (APAs), while the less frequent causes include unilateral hyperplasia, familial hyperaldosteronism (FH) types I-IV, aldosterone-producing carcinoma, and ectopic aldosterone synthesis. This condition, characterised by excessive aldosterone secretion, leads to augmented sodium and water reabsorption alongside potassium loss, culminating in distinct clinical hallmarks: elevated aldosterone levels, suppressed renin levels, and hypertension. Notably, hypokalaemia is present in only 28% of patients with PA and is not a primary indicator. The association of PA with an escalated cardiovascular risk profile, independent of blood pressure levels, is notable. Patients with PA exhibit a heightened incidence of cardiovascular events compared to counterparts with essential hypertension, matched for age, sex, and blood pressure levels. Despite its prevalence, PA remains frequently undiagnosed, underscoring the imperative for enhanced screening protocols. The diagnostic process for PA entails a tripartite assessment: the aldosterone/renin ratio (ARR) as the initial screening tool, followed by confirmatory and subtyping tests. A positive ARR necessitates confirmatory testing to rule out false positives. Subtyping, achieved through computed tomography and adrenal vein sampling, aims to distinguish between unilateral and bilateral PA forms, guiding targeted therapeutic strategies. New radionuclide imaging may facilitate and accelerate such subtyping and localisation. For unilateral adrenal adenoma or hyperplasia, surgical intervention is optimal, whereas bilateral idiopathic hyperplasia warrants treatment with mineralocorticoid antagonists (MRAs). This review amalgamates established and emerging insights into the management of primary aldosteronism.
Collapse
Affiliation(s)
- Natalia Ekman
- Department of Hypertension & Diabetology, Medical University of Gdańsk, 80-214 Gdańsk, Poland;
| | - Ashley B. Grossman
- Centre for Endocrinology, Barts and the London School of Medicine and Dentistry, Queen Mary University of London, London E1 4NS, UK;
| | - Dorota Dworakowska
- Department of Hypertension & Diabetology, Medical University of Gdańsk, 80-214 Gdańsk, Poland;
| |
Collapse
|