Cargando…

Use of Steroid Profiling Combined With Machine Learning for Identification and Subtype Classification in Primary Aldosteronism

IMPORTANCE: Most patients with primary aldosteronism, a major cause of secondary hypertension, are not identified or appropriately treated because of difficulties in diagnosis and subtype classification. Applications of artificial intelligence combined with mass spectrometry–based steroid profiling...

Descripción completa

Detalles Bibliográficos
Autores principales: Eisenhofer, Graeme, Durán, Claudio, Cannistraci, Carlo Vittorio, Peitzsch, Mirko, Williams, Tracy Ann, Riester, Anna, Burrello, Jacopo, Buffolo, Fabrizio, Prejbisz, Aleksander, Beuschlein, Felix, Januszewicz, Andrzej, Mulatero, Paolo, Lenders, Jacques W. M., Reincke, Martin
Formato: Online Artículo Texto
Lenguaje:English
Publicado: American Medical Association 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7525346/
https://www.ncbi.nlm.nih.gov/pubmed/32990741
http://dx.doi.org/10.1001/jamanetworkopen.2020.16209
_version_ 1783588727528882176
author Eisenhofer, Graeme
Durán, Claudio
Cannistraci, Carlo Vittorio
Peitzsch, Mirko
Williams, Tracy Ann
Riester, Anna
Burrello, Jacopo
Buffolo, Fabrizio
Prejbisz, Aleksander
Beuschlein, Felix
Januszewicz, Andrzej
Mulatero, Paolo
Lenders, Jacques W. M.
Reincke, Martin
author_facet Eisenhofer, Graeme
Durán, Claudio
Cannistraci, Carlo Vittorio
Peitzsch, Mirko
Williams, Tracy Ann
Riester, Anna
Burrello, Jacopo
Buffolo, Fabrizio
Prejbisz, Aleksander
Beuschlein, Felix
Januszewicz, Andrzej
Mulatero, Paolo
Lenders, Jacques W. M.
Reincke, Martin
author_sort Eisenhofer, Graeme
collection PubMed
description IMPORTANCE: Most patients with primary aldosteronism, a major cause of secondary hypertension, are not identified or appropriately treated because of difficulties in diagnosis and subtype classification. Applications of artificial intelligence combined with mass spectrometry–based steroid profiling could address this problem. OBJECTIVE: To assess whether plasma steroid profiling combined with machine learning might facilitate diagnosis and treatment stratification of primary aldosteronism, particularly for patients with unilateral adenomas due to pathogenic KCNJ5 sequence variants. DESIGN, SETTING, AND PARTICIPANTS: This diagnostic study was conducted at multiple tertiary care referral centers. Steroid profiles were measured from June 2013 to March 2017 in 462 patients tested for primary aldosteronism and 201 patients with hypertension. Data analyses were performed from September 2018 to August 2019. MAIN OUTCOMES AND MEASURES: The aldosterone to renin ratio and saline infusion tests were used to diagnose primary aldosteronism. Subtyping was done by adrenal venous sampling and follow-up of patients who underwent adrenalectomy. Statistical tests and machine-learning algorithms were applied to plasma steroid profiles. Areas under receiver operating characteristic curves, sensitivity, specificity, and other diagnostic performance measures were calculated. RESULTS: Primary aldosteronism was confirmed in 273 patients (165 men [60%]; mean [SD] age, 51 [10] years), including 134 with bilateral disease and 139 with unilateral adenomas (58 with and 81 without somatic KCNJ5 sequence variants). Plasma steroid profiles varied according to disease subtype and were particularly distinctive in patients with adenomas due to KCNJ5 variants, who showed better rates of biochemical cure after adrenalectomy than other patients. Among patients tested for primary aldosteronism, a selection of 8 steroids in combination with the aldosterone to renin ratio showed improved effectiveness for diagnosis over either strategy alone. In contrast, the steroid profile alone showed superior performance over the aldosterone to renin ratio for identifying unilateral disease, particularly adenomas due to KCNJ5 variants. Among 632 patients included in the analysis, machine learning–designed combinatorial marker profiles of 7 steroids alone both predicted primary aldosteronism in 1 step and subtyped patients with unilateral adenomas due to KCNJ5 variants at diagnostic sensitivities of 69% (95% CI, 68%-71%) and 85% (95% CI, 81%-88%), respectively, and at specificities of 94% (95% CI, 93%-94%) and 97% (95% CI, 97%-98%), respectively. The validation series yielded comparable diagnostic performance. CONCLUSIONS AND RELEVANCE: Machine learning–designed combinatorial plasma steroid profiles may facilitate both screening for primary aldosteronism and identification of patients with unilateral adenomas due to pathogenic KCNJ5 variants, who are most likely to show benefit from surgical intervention.
format Online
Article
Text
id pubmed-7525346
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher American Medical Association
record_format MEDLINE/PubMed
spelling pubmed-75253462020-10-05 Use of Steroid Profiling Combined With Machine Learning for Identification and Subtype Classification in Primary Aldosteronism Eisenhofer, Graeme Durán, Claudio Cannistraci, Carlo Vittorio Peitzsch, Mirko Williams, Tracy Ann Riester, Anna Burrello, Jacopo Buffolo, Fabrizio Prejbisz, Aleksander Beuschlein, Felix Januszewicz, Andrzej Mulatero, Paolo Lenders, Jacques W. M. Reincke, Martin JAMA Netw Open Original Investigation IMPORTANCE: Most patients with primary aldosteronism, a major cause of secondary hypertension, are not identified or appropriately treated because of difficulties in diagnosis and subtype classification. Applications of artificial intelligence combined with mass spectrometry–based steroid profiling could address this problem. OBJECTIVE: To assess whether plasma steroid profiling combined with machine learning might facilitate diagnosis and treatment stratification of primary aldosteronism, particularly for patients with unilateral adenomas due to pathogenic KCNJ5 sequence variants. DESIGN, SETTING, AND PARTICIPANTS: This diagnostic study was conducted at multiple tertiary care referral centers. Steroid profiles were measured from June 2013 to March 2017 in 462 patients tested for primary aldosteronism and 201 patients with hypertension. Data analyses were performed from September 2018 to August 2019. MAIN OUTCOMES AND MEASURES: The aldosterone to renin ratio and saline infusion tests were used to diagnose primary aldosteronism. Subtyping was done by adrenal venous sampling and follow-up of patients who underwent adrenalectomy. Statistical tests and machine-learning algorithms were applied to plasma steroid profiles. Areas under receiver operating characteristic curves, sensitivity, specificity, and other diagnostic performance measures were calculated. RESULTS: Primary aldosteronism was confirmed in 273 patients (165 men [60%]; mean [SD] age, 51 [10] years), including 134 with bilateral disease and 139 with unilateral adenomas (58 with and 81 without somatic KCNJ5 sequence variants). Plasma steroid profiles varied according to disease subtype and were particularly distinctive in patients with adenomas due to KCNJ5 variants, who showed better rates of biochemical cure after adrenalectomy than other patients. Among patients tested for primary aldosteronism, a selection of 8 steroids in combination with the aldosterone to renin ratio showed improved effectiveness for diagnosis over either strategy alone. In contrast, the steroid profile alone showed superior performance over the aldosterone to renin ratio for identifying unilateral disease, particularly adenomas due to KCNJ5 variants. Among 632 patients included in the analysis, machine learning–designed combinatorial marker profiles of 7 steroids alone both predicted primary aldosteronism in 1 step and subtyped patients with unilateral adenomas due to KCNJ5 variants at diagnostic sensitivities of 69% (95% CI, 68%-71%) and 85% (95% CI, 81%-88%), respectively, and at specificities of 94% (95% CI, 93%-94%) and 97% (95% CI, 97%-98%), respectively. The validation series yielded comparable diagnostic performance. CONCLUSIONS AND RELEVANCE: Machine learning–designed combinatorial plasma steroid profiles may facilitate both screening for primary aldosteronism and identification of patients with unilateral adenomas due to pathogenic KCNJ5 variants, who are most likely to show benefit from surgical intervention. American Medical Association 2020-09-29 /pmc/articles/PMC7525346/ /pubmed/32990741 http://dx.doi.org/10.1001/jamanetworkopen.2020.16209 Text en Copyright 2020 Eisenhofer G et al. JAMA Network Open. http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the CC-BY License.
spellingShingle Original Investigation
Eisenhofer, Graeme
Durán, Claudio
Cannistraci, Carlo Vittorio
Peitzsch, Mirko
Williams, Tracy Ann
Riester, Anna
Burrello, Jacopo
Buffolo, Fabrizio
Prejbisz, Aleksander
Beuschlein, Felix
Januszewicz, Andrzej
Mulatero, Paolo
Lenders, Jacques W. M.
Reincke, Martin
Use of Steroid Profiling Combined With Machine Learning for Identification and Subtype Classification in Primary Aldosteronism
title Use of Steroid Profiling Combined With Machine Learning for Identification and Subtype Classification in Primary Aldosteronism
title_full Use of Steroid Profiling Combined With Machine Learning for Identification and Subtype Classification in Primary Aldosteronism
title_fullStr Use of Steroid Profiling Combined With Machine Learning for Identification and Subtype Classification in Primary Aldosteronism
title_full_unstemmed Use of Steroid Profiling Combined With Machine Learning for Identification and Subtype Classification in Primary Aldosteronism
title_short Use of Steroid Profiling Combined With Machine Learning for Identification and Subtype Classification in Primary Aldosteronism
title_sort use of steroid profiling combined with machine learning for identification and subtype classification in primary aldosteronism
topic Original Investigation
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7525346/
https://www.ncbi.nlm.nih.gov/pubmed/32990741
http://dx.doi.org/10.1001/jamanetworkopen.2020.16209
work_keys_str_mv AT eisenhofergraeme useofsteroidprofilingcombinedwithmachinelearningforidentificationandsubtypeclassificationinprimaryaldosteronism
AT duranclaudio useofsteroidprofilingcombinedwithmachinelearningforidentificationandsubtypeclassificationinprimaryaldosteronism
AT cannistracicarlovittorio useofsteroidprofilingcombinedwithmachinelearningforidentificationandsubtypeclassificationinprimaryaldosteronism
AT peitzschmirko useofsteroidprofilingcombinedwithmachinelearningforidentificationandsubtypeclassificationinprimaryaldosteronism
AT williamstracyann useofsteroidprofilingcombinedwithmachinelearningforidentificationandsubtypeclassificationinprimaryaldosteronism
AT riesteranna useofsteroidprofilingcombinedwithmachinelearningforidentificationandsubtypeclassificationinprimaryaldosteronism
AT burrellojacopo useofsteroidprofilingcombinedwithmachinelearningforidentificationandsubtypeclassificationinprimaryaldosteronism
AT buffolofabrizio useofsteroidprofilingcombinedwithmachinelearningforidentificationandsubtypeclassificationinprimaryaldosteronism
AT prejbiszaleksander useofsteroidprofilingcombinedwithmachinelearningforidentificationandsubtypeclassificationinprimaryaldosteronism
AT beuschleinfelix useofsteroidprofilingcombinedwithmachinelearningforidentificationandsubtypeclassificationinprimaryaldosteronism
AT januszewiczandrzej useofsteroidprofilingcombinedwithmachinelearningforidentificationandsubtypeclassificationinprimaryaldosteronism
AT mulateropaolo useofsteroidprofilingcombinedwithmachinelearningforidentificationandsubtypeclassificationinprimaryaldosteronism
AT lendersjacqueswm useofsteroidprofilingcombinedwithmachinelearningforidentificationandsubtypeclassificationinprimaryaldosteronism
AT reinckemartin useofsteroidprofilingcombinedwithmachinelearningforidentificationandsubtypeclassificationinprimaryaldosteronism