CONTEXT: Primary aldosteronism (PA) comprises unilateral (lateralized, LPA) and bilateral disease (BPA). The identification of LPA is important to recommend potentially curative adrenalectomy. Adrenal venous sampling (AVS) is considered the gold standard for PA subtyping, but the procedure is available in few referral centers. OBJECTIVE: To develop prediction models for subtype diagnosis of PA using patient clinical and biochemical characteristics. DESIGN, PATIENTS AND SETTING: Patients referred to a tertiary hypertension unit. Diagnostic algorithms were built and tested in a training (N=150) and in an internal validation cohort (N=65), respectively. The models were validated in an external independent cohort (N=118). MAIN OUTCOME MEASURE: Regression analyses and supervised machine learning algorithms were used to develop and validate two diagnostic models and a 20-point score to classify patients with PA according to subtype diagnosis. RESULTS: Six parameters were associated with a diagnosis of LPA (aldosterone at screening and after confirmatory testing, lowest potassium value, presence/absence of nodules, nodule diameter, and computed tomography results) and were included in the diagnostic models. Machine learning algorithms displayed high accuracy at training and internal validation (79.1% to 93%), whereas a 20-point score reached an AUC of 0.896, and a sensitivity/specificity of 91.7/79.3%. An integrated flow-chart correctly addressed 96.3% of patients to surgery and would have avoided AVS in 43.7% of patients. The external validation on an independent cohort confirmed a similar diagnostic performance. CONCLUSIONS: Diagnostic modelling techniques can be used for subtype diagnosis and guide surgical decision in patients with PA in centers where AVS is unavailable.

Development and validation of prediction models for subtype diagnosis of patients with primary aldosteronism

Burrello J.
First
;
Pieroni J.;Sconfienza E.;Forestiero V.;Rabbia P.;Adolf C.;Veglio F.;Williams T. A.;Monticone S.
Co-last
;
Mulatero P.
2020-01-01

Abstract

CONTEXT: Primary aldosteronism (PA) comprises unilateral (lateralized, LPA) and bilateral disease (BPA). The identification of LPA is important to recommend potentially curative adrenalectomy. Adrenal venous sampling (AVS) is considered the gold standard for PA subtyping, but the procedure is available in few referral centers. OBJECTIVE: To develop prediction models for subtype diagnosis of PA using patient clinical and biochemical characteristics. DESIGN, PATIENTS AND SETTING: Patients referred to a tertiary hypertension unit. Diagnostic algorithms were built and tested in a training (N=150) and in an internal validation cohort (N=65), respectively. The models were validated in an external independent cohort (N=118). MAIN OUTCOME MEASURE: Regression analyses and supervised machine learning algorithms were used to develop and validate two diagnostic models and a 20-point score to classify patients with PA according to subtype diagnosis. RESULTS: Six parameters were associated with a diagnosis of LPA (aldosterone at screening and after confirmatory testing, lowest potassium value, presence/absence of nodules, nodule diameter, and computed tomography results) and were included in the diagnostic models. Machine learning algorithms displayed high accuracy at training and internal validation (79.1% to 93%), whereas a 20-point score reached an AUC of 0.896, and a sensitivity/specificity of 91.7/79.3%. An integrated flow-chart correctly addressed 96.3% of patients to surgery and would have avoided AVS in 43.7% of patients. The external validation on an independent cohort confirmed a similar diagnostic performance. CONCLUSIONS: Diagnostic modelling techniques can be used for subtype diagnosis and guide surgical decision in patients with PA in centers where AVS is unavailable.
2020
105
10
3706
3717
adrenal venous sampling; aldosterone; machine learning; primary aldosteronism
Burrello J.; Burrello A.; Pieroni J.; Sconfienza E.; Forestiero V.; Rabbia P.; Adolf C.; Reincke M.; Veglio F.; Williams T.A.; Monticone S.; Mulatero P.
File in questo prodotto:
File Dimensione Formato  
Burrello_jc.2020-00720_Manuscript Clean.docx

Accesso riservato

Tipo di file: POSTPRINT (VERSIONE FINALE DELL’AUTORE)
Dimensione 120.1 kB
Formato Microsoft Word XML
120.1 kB Microsoft Word XML   Visualizza/Apri   Richiedi una copia
Burrello_jc.2020-00720_fig1.tif

Open Access dal 30/06/2021

Tipo di file: POSTPRINT (VERSIONE FINALE DELL’AUTORE)
Dimensione 562.54 kB
Formato TIFF
562.54 kB TIFF Visualizza/Apri
Burrello_jc.2020-00720_fig2.tif

Open Access dal 30/06/2021

Tipo di file: POSTPRINT (VERSIONE FINALE DELL’AUTORE)
Dimensione 579.14 kB
Formato TIFF
579.14 kB TIFF Visualizza/Apri
Burrello_jc.2020-00720_fig3.tif

Open Access dal 30/06/2021

Tipo di file: POSTPRINT (VERSIONE FINALE DELL’AUTORE)
Dimensione 1.07 MB
Formato TIFF
1.07 MB TIFF Visualizza/Apri
Burrello_jc.2020-00720_fig4.tif

Open Access dal 30/06/2021

Tipo di file: POSTPRINT (VERSIONE FINALE DELL’AUTORE)
Dimensione 420.42 kB
Formato TIFF
420.42 kB TIFF Visualizza/Apri
Burrello_jc.2020-00720_Manuscript Clean.pdf

Accesso aperto

Tipo di file: POSTPRINT (VERSIONE FINALE DELL’AUTORE)
Dimensione 335.92 kB
Formato Adobe PDF
335.92 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2318/1742456
Citazioni
  • ???jsp.display-item.citation.pmc??? 23
  • Scopus 46
  • ???jsp.display-item.citation.isi??? 36
social impact