Cargando…
Treatment response to spironolactone in patients with heart failure with preserved ejection fraction: a machine learning-based analysis of two randomized controlled trials
BACKGROUND: Whether there is a subset of patients with heart failure with preserved ejection fraction (HFpEF) that benefit from spironolactone therapy is unclear. We applied a machine learning approach to identify responders and non-responders to spironolactone among patients with HFpEF in two large...
Autores principales: | , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Elsevier
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10498181/ https://www.ncbi.nlm.nih.gov/pubmed/37689023 http://dx.doi.org/10.1016/j.ebiom.2023.104795 |
_version_ | 1785105463223779328 |
---|---|
author | Kresoja, Karl-Patrik Unterhuber, Matthias Wachter, Rolf Rommel, Karl-Philipp Besler, Christian Shah, Sanjiv Thiele, Holger Edelmann, Frank Lurz, Philipp |
author_facet | Kresoja, Karl-Patrik Unterhuber, Matthias Wachter, Rolf Rommel, Karl-Philipp Besler, Christian Shah, Sanjiv Thiele, Holger Edelmann, Frank Lurz, Philipp |
author_sort | Kresoja, Karl-Patrik |
collection | PubMed |
description | BACKGROUND: Whether there is a subset of patients with heart failure with preserved ejection fraction (HFpEF) that benefit from spironolactone therapy is unclear. We applied a machine learning approach to identify responders and non-responders to spironolactone among patients with HFpEF in two large randomized clinical trials. METHODS: Using a reiterative cluster allocating permutation approach, patients from the derivation cohort (Aldo-DHF) were identified according to their treatment response to spironolactone with respect to improvement in E/e’. Heterogenous features of response (‘responders’ and ‘non-responders’) were characterized by an extreme gradient boosting (XGBoost) algorithm. XGBoost was used to predict treatment response in the validation cohort (TOPCAT). The primary endpoint of the validation cohort was a combined endpoint of cardiovascular mortality, aborted cardiac arrest, or heart failure hospitalization. Patients with missing variables for the XGboost model were excluded from the validation analysis. FINDINGS: Out of 422 patients from the derivation cohort, reiterative cluster allocating permutation identified 159 patients (38%) as spironolactone responders, in whom E/e’ significantly improved (p = 0.005). Within the validation cohort (n = 525) spironolactone treatment significantly reduced the occurrence of the primary outcome among responders (n = 185, p log rank = 0.008), but not among patients in the non-responder group (n = 340, p log rank = 0.52). INTERPRETATION: Machine learning approaches might aid in identifying HFpEF patients who are likely to show a favorable therapeutic response to spironolactone. FUNDING: See Acknowledgements section at the end of the manuscript. |
format | Online Article Text |
id | pubmed-10498181 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | Elsevier |
record_format | MEDLINE/PubMed |
spelling | pubmed-104981812023-09-14 Treatment response to spironolactone in patients with heart failure with preserved ejection fraction: a machine learning-based analysis of two randomized controlled trials Kresoja, Karl-Patrik Unterhuber, Matthias Wachter, Rolf Rommel, Karl-Philipp Besler, Christian Shah, Sanjiv Thiele, Holger Edelmann, Frank Lurz, Philipp eBioMedicine Articles BACKGROUND: Whether there is a subset of patients with heart failure with preserved ejection fraction (HFpEF) that benefit from spironolactone therapy is unclear. We applied a machine learning approach to identify responders and non-responders to spironolactone among patients with HFpEF in two large randomized clinical trials. METHODS: Using a reiterative cluster allocating permutation approach, patients from the derivation cohort (Aldo-DHF) were identified according to their treatment response to spironolactone with respect to improvement in E/e’. Heterogenous features of response (‘responders’ and ‘non-responders’) were characterized by an extreme gradient boosting (XGBoost) algorithm. XGBoost was used to predict treatment response in the validation cohort (TOPCAT). The primary endpoint of the validation cohort was a combined endpoint of cardiovascular mortality, aborted cardiac arrest, or heart failure hospitalization. Patients with missing variables for the XGboost model were excluded from the validation analysis. FINDINGS: Out of 422 patients from the derivation cohort, reiterative cluster allocating permutation identified 159 patients (38%) as spironolactone responders, in whom E/e’ significantly improved (p = 0.005). Within the validation cohort (n = 525) spironolactone treatment significantly reduced the occurrence of the primary outcome among responders (n = 185, p log rank = 0.008), but not among patients in the non-responder group (n = 340, p log rank = 0.52). INTERPRETATION: Machine learning approaches might aid in identifying HFpEF patients who are likely to show a favorable therapeutic response to spironolactone. FUNDING: See Acknowledgements section at the end of the manuscript. Elsevier 2023-09-07 /pmc/articles/PMC10498181/ /pubmed/37689023 http://dx.doi.org/10.1016/j.ebiom.2023.104795 Text en © 2023 The Author(s) https://creativecommons.org/licenses/by-nc-nd/4.0/This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). |
spellingShingle | Articles Kresoja, Karl-Patrik Unterhuber, Matthias Wachter, Rolf Rommel, Karl-Philipp Besler, Christian Shah, Sanjiv Thiele, Holger Edelmann, Frank Lurz, Philipp Treatment response to spironolactone in patients with heart failure with preserved ejection fraction: a machine learning-based analysis of two randomized controlled trials |
title | Treatment response to spironolactone in patients with heart failure with preserved ejection fraction: a machine learning-based analysis of two randomized controlled trials |
title_full | Treatment response to spironolactone in patients with heart failure with preserved ejection fraction: a machine learning-based analysis of two randomized controlled trials |
title_fullStr | Treatment response to spironolactone in patients with heart failure with preserved ejection fraction: a machine learning-based analysis of two randomized controlled trials |
title_full_unstemmed | Treatment response to spironolactone in patients with heart failure with preserved ejection fraction: a machine learning-based analysis of two randomized controlled trials |
title_short | Treatment response to spironolactone in patients with heart failure with preserved ejection fraction: a machine learning-based analysis of two randomized controlled trials |
title_sort | treatment response to spironolactone in patients with heart failure with preserved ejection fraction: a machine learning-based analysis of two randomized controlled trials |
topic | Articles |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10498181/ https://www.ncbi.nlm.nih.gov/pubmed/37689023 http://dx.doi.org/10.1016/j.ebiom.2023.104795 |
work_keys_str_mv | AT kresojakarlpatrik treatmentresponsetospironolactoneinpatientswithheartfailurewithpreservedejectionfractionamachinelearningbasedanalysisoftworandomizedcontrolledtrials AT unterhubermatthias treatmentresponsetospironolactoneinpatientswithheartfailurewithpreservedejectionfractionamachinelearningbasedanalysisoftworandomizedcontrolledtrials AT wachterrolf treatmentresponsetospironolactoneinpatientswithheartfailurewithpreservedejectionfractionamachinelearningbasedanalysisoftworandomizedcontrolledtrials AT rommelkarlphilipp treatmentresponsetospironolactoneinpatientswithheartfailurewithpreservedejectionfractionamachinelearningbasedanalysisoftworandomizedcontrolledtrials AT beslerchristian treatmentresponsetospironolactoneinpatientswithheartfailurewithpreservedejectionfractionamachinelearningbasedanalysisoftworandomizedcontrolledtrials AT shahsanjiv treatmentresponsetospironolactoneinpatientswithheartfailurewithpreservedejectionfractionamachinelearningbasedanalysisoftworandomizedcontrolledtrials AT thieleholger treatmentresponsetospironolactoneinpatientswithheartfailurewithpreservedejectionfractionamachinelearningbasedanalysisoftworandomizedcontrolledtrials AT edelmannfrank treatmentresponsetospironolactoneinpatientswithheartfailurewithpreservedejectionfractionamachinelearningbasedanalysisoftworandomizedcontrolledtrials AT lurzphilipp treatmentresponsetospironolactoneinpatientswithheartfailurewithpreservedejectionfractionamachinelearningbasedanalysisoftworandomizedcontrolledtrials |