Robustness of steroidomics-based machine learning for diagnosis of primary aldosteronism: a laboratory medicine perspective
ML-based steroid-probability-scores for diagnosis of PA display remarkably high robustness according to reproducibility of measurements within and between laboratories as well as within patients.
Authors
- Christina Pamporaki (ORCID: https://orcid.org/0000-0003-0772-1604)
- Hanna Remde (ORCID: https://orcid.org/0000-0002-3499-5910)
- Kevin Mantik
- Jacques W.M. Lenders (ORCID: https://orcid.org/0000-0002-7658-4466)
- Manuel Schulze (ORCID: https://orcid.org/0009-0008-5819-0835)
- Mirko Peitzsch (ORCID: https://orcid.org/0000-0002-2472-675X)
- Andrea R. Horvath (ORCID: https://orcid.org/0000-0002-7474-3240)
- Tracy Ann Williams (ORCID: https://orcid.org/0000-0002-2388-6444)
- Carmina Teresa Fuß (ORCID: https://orcid.org/0000-0002-1466-5287)
- Graeme Eisenhofer (ORCID: https://orcid.org/0000-0002-8601-9903)
- Georgiana Constantinescu (ORCID: https://orcid.org/0000-0002-7304-2557)
- Sven Gruber (ORCID: https://orcid.org/0000-0003-0601-4334)
- Zhong X. Lu (ORCID: https://orcid.org/0009-0008-5553-8824)
Institutions
- New South Wales Department of Health (AU)
- Radboud University Nijmegen (NL)
- Radboud University Medical Center (NL)
- University Hospital of Zurich (CH)
- Prince of Wales Hospital (AU)
- Monash Health (AU)
- Universitätsklinikum Würzburg (DE)
- University Hospital Carl Gustav Carus (DE)
- Monash University (AU)
- Technische Universität Dresden (DE)
- Ludwig-Maximilians-Universität München (DE)
Publication Details
- Journal
- Clinical Chemistry and Laboratory Medicine (CCLM)
- Published
- 2025-07-24
- DOI
- https://doi.org/10.1515/cclm-2025-0200
- Citations
- 1
- Primary Topic
- Hormonal Regulation and Hypertension
- Type
- article
- Field-Weighted Citation Impact
- 1.29
Funders
- Deutsche Forschungsgemeinschaft