Metabolic Subtyping of Adrenal Tumors: Prospective Multi-Center Cohort Study in Korea
- Abstract
- BACKGROUND: Conventional diagnostic approaches for adrenal tumors require multi-step processes, including imaging studies and dynamic hormone tests. Therefore, this study aimed to discriminate adrenal tumors from a single blood sample based on the combination of liquid chromatography-mass spectrometry (LC-MS) and machine learning algorithms in serum profiling of adrenal steroids. METHODS: The LC-MS-based steroid profiling was applied to serum samples obtained from patients with nonfunctioning adenoma (NFA, n=73), Cushing's syndrome (CS, n=30), and primary aldosteronism (PA, n=40) in a prospective multicenter study of adrenal disease. The decision tree (DT), random forest (RF), and extreme gradient boost (XGBoost) were performed to categorize the subtypes of adrenal tumors. RESULTS: The CS group showed higher serum levels of 11-deoxycortisol than the NFA group, and increased levels of tetrahydrocortisone (THE), 20α-dihydrocortisol, and 6β-hydroxycortisol were found in the PA group. However, the CS group showed lower levels of dehydroepiandrosterone (DHEA) and its sulfate derivative (DHEA-S) than both the NFA and PA groups. Patients with PA expressed higher serum 18-hydroxycortisol and DHEA but lower THE than NFA patients. The balanced accuracies of DT, RF, and XGBoost for classifying each type were 78%, 96%, and 97%, respectively. In receiver operating characteristics (ROC) analysis for CS, XGBoost, and RF showed a significantly greater diagnostic power than the DT. However, in ROC analysis for PA, only RF exhibited better diagnostic performance than DT. CONCLUSION: The combination of LC-MS-based steroid profiling with machine learning algorithms could be a promising one-step diagnostic approach for the classification of adrenal tumor subtypes.
- All Author(s)
- E. J. Ku
; C. Lee
; J. Shim
; S. Lee
; K. A. Kim
; S. W. Kim
; Y. Rhee
; H. J. Kim
; J. S. Lim
; C. H. Chung
; S. W. Chun
; S. J. Yoo
; O. H. Ryu
; H. C. Cho
; A. R. Hong
; C. H. Ahn
; J. H. Kim
; M. H. Choi
- Issued Date
- 2021
- Type
- Article
- Keyword
- Steroid metabolism; Supervised machine learning; Adrenal neoplasms; Cushing syndrome; Primary hyperaldosteronism
- Publisher
- 대한내분비학회
- ISSN
- 2093-596X
- Citation Title
- Endocrinology and Metabolism
- Citation Volume
- 36
- Citation Number
- 5
- Citation Start Page
- 1131
- Citation End Page
- 1141
- Language(ISO)
- eng
- DOI
- 10.3803/EnM.2021.1149
- URI
- http://schca-ir.schmc.ac.kr/handle/2022.oak/2329
- 공개 및 라이선스
-
- 파일 목록
-
Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.