Machine learning cluster analysis identifies increased 12-month mortality risk in transcatheter aortic valve replacement recipients
BackgroundLong-term mortality risk is seldom re-assessed in contemporary clinical practice following successful transcatheter aortic valve implantation (TAVR). Unsupervised machine learning permits pattern discovery within complex multidimensional patient data and may facilitate recognition of group...
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-02-01
|
| Series: | Frontiers in Cardiovascular Medicine |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fcvm.2025.1444658/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832096727576870912 |
|---|---|
| author | Thomas Meredith Thomas Meredith Thomas Meredith Farhan Mohammed Amy Pomeroy Sebastiano Barbieri Sebastiano Barbieri Erik Meijering Louisa Jorm David Roy Jason Kovacic Jason Kovacic Jason Kovacic Jason Kovacic Michael Feneley Michael Feneley Michael Feneley Christopher Hayward Christopher Hayward Christopher Hayward David Muller David Muller David Muller Mayooran Namasivayam Mayooran Namasivayam Mayooran Namasivayam |
| author_facet | Thomas Meredith Thomas Meredith Thomas Meredith Farhan Mohammed Amy Pomeroy Sebastiano Barbieri Sebastiano Barbieri Erik Meijering Louisa Jorm David Roy Jason Kovacic Jason Kovacic Jason Kovacic Jason Kovacic Michael Feneley Michael Feneley Michael Feneley Christopher Hayward Christopher Hayward Christopher Hayward David Muller David Muller David Muller Mayooran Namasivayam Mayooran Namasivayam Mayooran Namasivayam |
| author_sort | Thomas Meredith |
| collection | DOAJ |
| description | BackgroundLong-term mortality risk is seldom re-assessed in contemporary clinical practice following successful transcatheter aortic valve implantation (TAVR). Unsupervised machine learning permits pattern discovery within complex multidimensional patient data and may facilitate recognition of groups requiring closer post-TAVR surveillance.MethodsWe analysed and differentiated routinely collected demographic, biochemical, and cardiac imaging data into distinct clusters using unsupervised machine learning. k-means clustering was performed on data from 200 patients who underwent TAVR for severe aortic stenosis (AS). Input features were ranked according to their influence on cluster assignment. Survival analyses were performed with Kaplan–Meier and Cox proportional hazards models. Nested cox models were used to identify any incremental prognostic benefit cluster assignment achieved beyond conventional risk scores.ResultsAnalysis identified two distinct clusters. Compared to Cluster 1, Cluster 2 demonstrated significantly worse all-cause mortality at 12 months (HR 6.3, p < 0.01), and was characterised by more advanced cardiac remodelling with worse indices of multi-chamber cardiac function, as quantified by strain imaging. Cluster assignment demonstrated greater predictive power for 12-month mortality as compared with conventional risk and frailty calculators.Conclusionk-means clustering identified two prognostically distinct phenogroups of patients who had undergone TAVR with better discriminatory power than conventional risk and frailty calculators. Our results highlight the utility of machine learning applications for clinical risk prediction and scope to improve patient surveillance. |
| format | Article |
| id | doaj-art-1b049559ea5b4322bf97b9c5f5724fac |
| institution | Kabale University |
| issn | 2297-055X |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Cardiovascular Medicine |
| spelling | doaj-art-1b049559ea5b4322bf97b9c5f5724fac2025-02-05T11:24:47ZengFrontiers Media S.A.Frontiers in Cardiovascular Medicine2297-055X2025-02-011210.3389/fcvm.2025.14446581444658Machine learning cluster analysis identifies increased 12-month mortality risk in transcatheter aortic valve replacement recipientsThomas Meredith0Thomas Meredith1Thomas Meredith2Farhan Mohammed3Amy Pomeroy4Sebastiano Barbieri5Sebastiano Barbieri6Erik Meijering7Louisa Jorm8David Roy9Jason Kovacic10Jason Kovacic11Jason Kovacic12Jason Kovacic13Michael Feneley14Michael Feneley15Michael Feneley16Christopher Hayward17Christopher Hayward18Christopher Hayward19David Muller20David Muller21David Muller22Mayooran Namasivayam23Mayooran Namasivayam24Mayooran Namasivayam25Department of Cardiology, St Vincent's Hospital, Sydney, NSW, AustraliaHeart Valve Disease & Artificial Intelligence Laboratory, Victor Chang Cardiac Research Institute, Sydney, NSW, AustraliaFaculty of Medicine and Health, University of New South Wales, Sydney, NSW, AustraliaHeart Valve Disease & Artificial Intelligence Laboratory, Victor Chang Cardiac Research Institute, Sydney, NSW, AustraliaHeart Valve Disease & Artificial Intelligence Laboratory, Victor Chang Cardiac Research Institute, Sydney, NSW, AustraliaCentre forBig Data in Health Research, University of New South Wales, Sydney, NSW, AustraliaQueensland Digital Health Centre, University of Queensland, Brisbane, QLD, AustraliaSchool of Computer Science and Engineering, University of New South Wales, Sydney, NSW, AustraliaCentre forBig Data in Health Research, University of New South Wales, Sydney, NSW, AustraliaDepartment of Cardiology, St Vincent's Hospital, Sydney, NSW, AustraliaDepartment of Cardiology, St Vincent's Hospital, Sydney, NSW, AustraliaHeart Valve Disease & Artificial Intelligence Laboratory, Victor Chang Cardiac Research Institute, Sydney, NSW, AustraliaFaculty of Medicine and Health, University of New South Wales, Sydney, NSW, AustraliaCardiovascular Research Institute, Icahn School of Medicine at Mount Sinai, New York, NY, United StatesDepartment of Cardiology, St Vincent's Hospital, Sydney, NSW, AustraliaHeart Valve Disease & Artificial Intelligence Laboratory, Victor Chang Cardiac Research Institute, Sydney, NSW, AustraliaFaculty of Medicine and Health, University of New South Wales, Sydney, NSW, AustraliaDepartment of Cardiology, St Vincent's Hospital, Sydney, NSW, AustraliaHeart Valve Disease & Artificial Intelligence Laboratory, Victor Chang Cardiac Research Institute, Sydney, NSW, AustraliaFaculty of Medicine and Health, University of New South Wales, Sydney, NSW, AustraliaDepartment of Cardiology, St Vincent's Hospital, Sydney, NSW, AustraliaHeart Valve Disease & Artificial Intelligence Laboratory, Victor Chang Cardiac Research Institute, Sydney, NSW, AustraliaFaculty of Medicine and Health, University of New South Wales, Sydney, NSW, AustraliaDepartment of Cardiology, St Vincent's Hospital, Sydney, NSW, AustraliaHeart Valve Disease & Artificial Intelligence Laboratory, Victor Chang Cardiac Research Institute, Sydney, NSW, AustraliaFaculty of Medicine and Health, University of New South Wales, Sydney, NSW, AustraliaBackgroundLong-term mortality risk is seldom re-assessed in contemporary clinical practice following successful transcatheter aortic valve implantation (TAVR). Unsupervised machine learning permits pattern discovery within complex multidimensional patient data and may facilitate recognition of groups requiring closer post-TAVR surveillance.MethodsWe analysed and differentiated routinely collected demographic, biochemical, and cardiac imaging data into distinct clusters using unsupervised machine learning. k-means clustering was performed on data from 200 patients who underwent TAVR for severe aortic stenosis (AS). Input features were ranked according to their influence on cluster assignment. Survival analyses were performed with Kaplan–Meier and Cox proportional hazards models. Nested cox models were used to identify any incremental prognostic benefit cluster assignment achieved beyond conventional risk scores.ResultsAnalysis identified two distinct clusters. Compared to Cluster 1, Cluster 2 demonstrated significantly worse all-cause mortality at 12 months (HR 6.3, p < 0.01), and was characterised by more advanced cardiac remodelling with worse indices of multi-chamber cardiac function, as quantified by strain imaging. Cluster assignment demonstrated greater predictive power for 12-month mortality as compared with conventional risk and frailty calculators.Conclusionk-means clustering identified two prognostically distinct phenogroups of patients who had undergone TAVR with better discriminatory power than conventional risk and frailty calculators. Our results highlight the utility of machine learning applications for clinical risk prediction and scope to improve patient surveillance.https://www.frontiersin.org/articles/10.3389/fcvm.2025.1444658/fullaortic stenosismachine learningoutcomescardiac imagingtranscatheter aortic valve replacement |
| spellingShingle | Thomas Meredith Thomas Meredith Thomas Meredith Farhan Mohammed Amy Pomeroy Sebastiano Barbieri Sebastiano Barbieri Erik Meijering Louisa Jorm David Roy Jason Kovacic Jason Kovacic Jason Kovacic Jason Kovacic Michael Feneley Michael Feneley Michael Feneley Christopher Hayward Christopher Hayward Christopher Hayward David Muller David Muller David Muller Mayooran Namasivayam Mayooran Namasivayam Mayooran Namasivayam Machine learning cluster analysis identifies increased 12-month mortality risk in transcatheter aortic valve replacement recipients Frontiers in Cardiovascular Medicine aortic stenosis machine learning outcomes cardiac imaging transcatheter aortic valve replacement |
| title | Machine learning cluster analysis identifies increased 12-month mortality risk in transcatheter aortic valve replacement recipients |
| title_full | Machine learning cluster analysis identifies increased 12-month mortality risk in transcatheter aortic valve replacement recipients |
| title_fullStr | Machine learning cluster analysis identifies increased 12-month mortality risk in transcatheter aortic valve replacement recipients |
| title_full_unstemmed | Machine learning cluster analysis identifies increased 12-month mortality risk in transcatheter aortic valve replacement recipients |
| title_short | Machine learning cluster analysis identifies increased 12-month mortality risk in transcatheter aortic valve replacement recipients |
| title_sort | machine learning cluster analysis identifies increased 12 month mortality risk in transcatheter aortic valve replacement recipients |
| topic | aortic stenosis machine learning outcomes cardiac imaging transcatheter aortic valve replacement |
| url | https://www.frontiersin.org/articles/10.3389/fcvm.2025.1444658/full |
| work_keys_str_mv | AT thomasmeredith machinelearningclusteranalysisidentifiesincreased12monthmortalityriskintranscatheteraorticvalvereplacementrecipients AT thomasmeredith machinelearningclusteranalysisidentifiesincreased12monthmortalityriskintranscatheteraorticvalvereplacementrecipients AT thomasmeredith machinelearningclusteranalysisidentifiesincreased12monthmortalityriskintranscatheteraorticvalvereplacementrecipients AT farhanmohammed machinelearningclusteranalysisidentifiesincreased12monthmortalityriskintranscatheteraorticvalvereplacementrecipients AT amypomeroy machinelearningclusteranalysisidentifiesincreased12monthmortalityriskintranscatheteraorticvalvereplacementrecipients AT sebastianobarbieri machinelearningclusteranalysisidentifiesincreased12monthmortalityriskintranscatheteraorticvalvereplacementrecipients AT sebastianobarbieri machinelearningclusteranalysisidentifiesincreased12monthmortalityriskintranscatheteraorticvalvereplacementrecipients AT erikmeijering machinelearningclusteranalysisidentifiesincreased12monthmortalityriskintranscatheteraorticvalvereplacementrecipients AT louisajorm machinelearningclusteranalysisidentifiesincreased12monthmortalityriskintranscatheteraorticvalvereplacementrecipients AT davidroy machinelearningclusteranalysisidentifiesincreased12monthmortalityriskintranscatheteraorticvalvereplacementrecipients AT jasonkovacic machinelearningclusteranalysisidentifiesincreased12monthmortalityriskintranscatheteraorticvalvereplacementrecipients AT jasonkovacic machinelearningclusteranalysisidentifiesincreased12monthmortalityriskintranscatheteraorticvalvereplacementrecipients AT jasonkovacic machinelearningclusteranalysisidentifiesincreased12monthmortalityriskintranscatheteraorticvalvereplacementrecipients AT jasonkovacic machinelearningclusteranalysisidentifiesincreased12monthmortalityriskintranscatheteraorticvalvereplacementrecipients AT michaelfeneley machinelearningclusteranalysisidentifiesincreased12monthmortalityriskintranscatheteraorticvalvereplacementrecipients AT michaelfeneley machinelearningclusteranalysisidentifiesincreased12monthmortalityriskintranscatheteraorticvalvereplacementrecipients AT michaelfeneley machinelearningclusteranalysisidentifiesincreased12monthmortalityriskintranscatheteraorticvalvereplacementrecipients AT christopherhayward machinelearningclusteranalysisidentifiesincreased12monthmortalityriskintranscatheteraorticvalvereplacementrecipients AT christopherhayward machinelearningclusteranalysisidentifiesincreased12monthmortalityriskintranscatheteraorticvalvereplacementrecipients AT christopherhayward machinelearningclusteranalysisidentifiesincreased12monthmortalityriskintranscatheteraorticvalvereplacementrecipients AT davidmuller machinelearningclusteranalysisidentifiesincreased12monthmortalityriskintranscatheteraorticvalvereplacementrecipients AT davidmuller machinelearningclusteranalysisidentifiesincreased12monthmortalityriskintranscatheteraorticvalvereplacementrecipients AT davidmuller machinelearningclusteranalysisidentifiesincreased12monthmortalityriskintranscatheteraorticvalvereplacementrecipients AT mayoorannamasivayam machinelearningclusteranalysisidentifiesincreased12monthmortalityriskintranscatheteraorticvalvereplacementrecipients AT mayoorannamasivayam machinelearningclusteranalysisidentifiesincreased12monthmortalityriskintranscatheteraorticvalvereplacementrecipients AT mayoorannamasivayam machinelearningclusteranalysisidentifiesincreased12monthmortalityriskintranscatheteraorticvalvereplacementrecipients |