1
|
Sazzad F, Ler AAL, Furqan MS, Tan LKZ, Leo HL, Kuntjoro I, Tay E, Kofidis T. Harnessing the power of artificial intelligence in predicting all-cause mortality in transcatheter aortic valve replacement: a systematic review and meta-analysis. Front Cardiovasc Med 2024; 11:1343210. [PMID: 38883982 PMCID: PMC11176615 DOI: 10.3389/fcvm.2024.1343210] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/23/2023] [Accepted: 05/16/2024] [Indexed: 06/18/2024] Open
Abstract
Objectives In recent years, the use of artificial intelligence (AI) models to generate individualised risk assessments and predict patient outcomes post-Transcatheter Aortic Valve Implantation (TAVI) has been a topic of increasing relevance in literature. This study aims to evaluate the predictive accuracy of AI algorithms in forecasting post-TAVI mortality as compared to traditional risk scores. Methods Following the Preferred Reporting Items for Systematic Reviews and Meta-analyses for Systematic Reviews (PRISMA) standard, a systematic review was carried out. We searched four databases in total-PubMed, Medline, Embase, and Cochrane-from 19 June 2023-24 June, 2023. Results From 2,239 identified records, 1,504 duplicates were removed, 735 manuscripts were screened, and 10 studies were included in our review. Our pooled analysis of 5 studies and 9,398 patients revealed a significantly higher mean area under curve (AUC) associated with AI mortality predictions than traditional score predictions (MD: -0.16, CI: -0.22 to -0.10, p < 0.00001). Subgroup analyses of 30-day mortality (MD: -0.08, CI: -0.13 to -0.03, p = 0.001) and 1-year mortality (MD: -0.18, CI: -0.27 to -0.10, p < 0.0001) also showed significantly higher mean AUC with AI predictions than traditional score predictions. Pooled mean AUC of all 10 studies and 22,933 patients was 0.79 [0.73, 0.85]. Conclusion AI models have a higher predictive accuracy as compared to traditional risk scores in predicting post-TAVI mortality. Overall, this review demonstrates the potential of AI in achieving personalised risk assessment in TAVI patients. Registration and protocol This systematic review and meta-analysis was registered under the International Prospective Register of Systematic Reviews (PROSPERO), under the registration name "All-Cause Mortality in Transcatheter Aortic Valve Replacement Assessed by Artificial Intelligence" and registration number CRD42023437705. A review protocol was not prepared. There were no amendments to the information provided at registration. Systematic Review Registration https://www.crd.york.ac.uk/, PROSPERO (CRD42023437705).
Collapse
Affiliation(s)
- Faizus Sazzad
- Department of Surgery, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore
| | - Ashlynn Ai Li Ler
- Department of Surgery, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore
| | - Mohammad Shaheryar Furqan
- Department of Biomedical Informatics, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore
| | - Linus Kai Zhe Tan
- Department of Surgery, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore
| | - Hwa Liang Leo
- Department of Biomedical Engineering, College of Design and Engineering, National University of Singapore, Singapore, Singapore
| | - Ivandito Kuntjoro
- Department of Cardiology, National University Heart Centre, Singapore, National University Hospital, Singapore, Singapore
| | - Edgar Tay
- Department of Cardiology, National University Heart Centre, Singapore, National University Hospital, Singapore, Singapore
- Asian Heart & Vascular Centre (AHVC), Mount Elizabeth Medical Centre, Singapore, Singapore
| | - Theo Kofidis
- Department of Surgery, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore
| |
Collapse
|
2
|
Jacquemyn X, Van Onsem E, Dufendach K, Brown JA, Kliner D, Toma C, Serna-Gallegos D, Sá MP, Sultan I. Machine-learning approaches for risk prediction in transcatheter aortic valve implantation: Systematic review and meta-analysis. J Thorac Cardiovasc Surg 2024:S0022-5223(24)00448-3. [PMID: 38815806 DOI: 10.1016/j.jtcvs.2024.05.017] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/30/2024] [Revised: 05/20/2024] [Accepted: 05/21/2024] [Indexed: 06/01/2024]
Abstract
OBJECTIVES With the expanding integration of artificial intelligence (AI) and machine learning (ML) into the structural heart domain, numerous ML models have emerged for the prediction of adverse outcomes after transcatheter aortic valve implantation (TAVI). We aim to identify, describe, and critically appraise ML prediction models for adverse outcomes after TAVI. Key objectives consisted in summarizing model performance, evaluating adherence to reporting guidelines, and transparency. METHODS We searched PubMed, SCOPUS, and Embase through August 2023. We selected published machine learning models predicting TAVI outcomes. Two reviewers independently screened articles, extracted data, and assessed the study quality according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Outcomes included summary C-statistics and model risk of bias assessed with the Prediction Model Risk of Bias Assessment Tool. C-statistics were pooled using a random-effects model. RESULTS Twenty-one studies (118,153 patients) employing various ML algorithms (76 models) were included in the systematic review. Predictive ability of models varied: 11.8% inadequate (C-statistic <0.60), 26.3% adequate (C-statistic 0.60-0.70), 31.6% acceptable (C-statistic 0.70-0.80), and 30.3% demonstrated excellent (C-statistic >0.80) performance. Meta-analyses revealed excellent predictive performance for early mortality (C-statistic: 0.81; 95% confidence interval [CI], 0.65-0.91), acceptable performance for 1-year mortality (C-statistic: 0.76; 95% CI, 0.67-0.84), and acceptable performance for predicting permanent pacemaker implantation (C-statistic: 0.75; 95% CI, 0.51-0.90). CONCLUSIONS ML models for TAVI outcomes exhibit adequate-to-excellent performance, suggesting potential clinical utility. We identified concerns in methodology and transparency, emphasizing the need for improved scientific reporting standards.
Collapse
Affiliation(s)
- Xander Jacquemyn
- Department of Cardiovascular Sciences, KU Leuven, Leuven, Belgium.
| | | | - Keith Dufendach
- Department of Cardiothoracic Surgery, University of Pittsburgh, Pittsburgh, Pa; UPMC Heart and Vascular Institute, University of Pittsburgh Medical Center, Pittsburgh, Pa
| | - James A Brown
- Department of Cardiothoracic Surgery, University of Pittsburgh, Pittsburgh, Pa; UPMC Heart and Vascular Institute, University of Pittsburgh Medical Center, Pittsburgh, Pa
| | - Dustin Kliner
- UPMC Heart and Vascular Institute, University of Pittsburgh Medical Center, Pittsburgh, Pa; Department of Interventional Cardiology, University of Pittsburgh, Pittsburgh, Pa
| | - Catalin Toma
- UPMC Heart and Vascular Institute, University of Pittsburgh Medical Center, Pittsburgh, Pa; Department of Interventional Cardiology, University of Pittsburgh, Pittsburgh, Pa
| | - Derek Serna-Gallegos
- Department of Cardiothoracic Surgery, University of Pittsburgh, Pittsburgh, Pa; UPMC Heart and Vascular Institute, University of Pittsburgh Medical Center, Pittsburgh, Pa
| | - Michel Pompeu Sá
- Department of Cardiothoracic Surgery, University of Pittsburgh, Pittsburgh, Pa; UPMC Heart and Vascular Institute, University of Pittsburgh Medical Center, Pittsburgh, Pa
| | - Ibrahim Sultan
- Department of Cardiothoracic Surgery, University of Pittsburgh, Pittsburgh, Pa; UPMC Heart and Vascular Institute, University of Pittsburgh Medical Center, Pittsburgh, Pa
| |
Collapse
|
3
|
Leha A, Huber C, Friede T, Bauer T, Beckmann A, Bekeredjian R, Bleiziffer S, Herrmann E, Möllmann H, Walther T, Beyersdorf F, Hamm C, Künzi A, Windecker S, Stortecky S, Kutschka I, Hasenfuß G, Ensminger S, Frerker C, Seidler T. Challenges in developing and validating machine learning models for TAVI mortality risk prediction: reply. EUROPEAN HEART JOURNAL. DIGITAL HEALTH 2024; 5:3-5. [PMID: 38264698 PMCID: PMC10802823 DOI: 10.1093/ehjdh/ztad065] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Download PDF] [Subscribe] [Scholar Register] [Received: 10/02/2023] [Accepted: 10/04/2023] [Indexed: 01/25/2024]
Affiliation(s)
- Andreas Leha
- Department of Medical Statistics, University Medical Center
Göttingen, Humboldtallee 32, 37073 Göttingen, Germany
- DZHK (German Center for Cardiovascular Research), Partner
Site Göttingen, Robert-Koch str. 40, 37075 Göttingen, Germany
| | - Cynthia Huber
- Department of Medical Statistics, University Medical Center
Göttingen, Humboldtallee 32, 37073 Göttingen, Germany
| | - Tim Friede
- Department of Medical Statistics, University Medical Center
Göttingen, Humboldtallee 32, 37073 Göttingen, Germany
- DZHK (German Center for Cardiovascular Research), Partner
Site Göttingen, Robert-Koch str. 40, 37075 Göttingen, Germany
| | - Timm Bauer
- Department of Cardiology, Sana Klinikum Offenbach,
Starkenburgring 66, 63069 Offenbach am Main, Germany
| | - Andreas Beckmann
- German Society for Thoracic and Cardiovascular Surgery,
Langenbeck-Virchow-Haus, Luisenstraße 58/59, 10117 Berlin, Germany
- Department for Cardiac and Pediatric Cardiac Surgery, Heart Center
Duisburg, EVKLN, Gerrickstr. 21, 47137 Duisburg,
Germany
| | - Raffi Bekeredjian
- Department of Cardiology, Robert-Bosch-Krankenhaus,
Auerbachstraße 110, 70376 Stuttgart, Germany
| | - Sabine Bleiziffer
- Clinic for Thoracic and Cardiovascular Surgery, Heart and Diabetes Center
Northrhine-Westphalia, Georgstr 11, 32545 Bad Oeynhausen, Germany
| | - Eva Herrmann
- Goethe University Frankfurt, Department of Medicine, Institute of
Biostatistics and Mathematical Modelling, Theodor-Stern-Kai 7, 60590
Frankfurt Main, Germany
- DZHK (German Centre for Cardiovascular Research), Partner
Site Rhine/Main, Theodor-Stern-Kai 7, 60590 Frankfurt Main, Germany
| | - Helge Möllmann
- Department of Cardiology, St.-Johannes-Hospital Dortmund,
Johannesstrasse 9-17, 44137 Dortmund, Germany
| | - Thomas Walther
- Department of Cardiothoracic Surgery, University Hospital
Frankfurt, Theodor-Stern-Kai 7, 60590 Frankfurt, Germany
| | - Friedhelm Beyersdorf
- Medical Faculty of the Albert-Ludwigs-University Freiburg, University
Hospital Freiburg, Hugstetterstr. 55, 79106 Freiburg, Germany
- Department of Cardiovascular Surgery, Heart Centre Freiburg
University, Freiburg, Germany
| | - Christian Hamm
- Department of Cardiology and Angiology, University Hospital
Gießen, Klinikstr. 33, 35392 Gießen, Germany
- Department of Cardiology, Kerckhoff Heart and Thorax Center,
Benekestraße 2-8, D-61231 Bad Nauheim, Germany
| | - Arnaud Künzi
- CTU Bern, University of Bern, Mittelstrasse 43, 3012 Bern,
Switzerland
| | - Stephan Windecker
- Department of Cardiology, Inselspital, Bern University Hospital, University
of Bern, 3010 Bern, Switzerland
| | - Stefan Stortecky
- Department of Cardiology, Inselspital, Bern University Hospital, University
of Bern, 3010 Bern, Switzerland
| | - Ingo Kutschka
- Clinic for Cardiothoracic and Vascular Surgery/Heart Center, University
Medical Center Göttingen, Robert-Koch Str. 40, 37075 Göttingen,
Germany
| | - Gerd Hasenfuß
- DZHK (German Center for Cardiovascular Research), Partner
Site Göttingen, Robert-Koch str. 40, 37075 Göttingen, Germany
- Clinic for Cardiology and Pulmonology, Heart Center, University Medical
Center Göttingen, Robert-Koch Str. 40, 37075 Göttingen, Germany
| | - Stephan Ensminger
- Department of Cardiac and Thoracic Vascular Surgery, University Heart
Center Lübeck, Ratzeburger Allee 160, 23538 Lübeck, Germany
- DZHK (German Centre for Cardiovascular Research),
partner site Hamburg/Kiel/Lübeck, Lübeck, Germany
| | - Christian Frerker
- DZHK (German Centre for Cardiovascular Research),
partner site Hamburg/Kiel/Lübeck, Lübeck, Germany
- Department of Cardiology, University Heart Center Lübeck,
Ratzeburger Allee 160, 23538 Lübeck, Germany
| | - Tim Seidler
- DZHK (German Center for Cardiovascular Research), Partner
Site Göttingen, Robert-Koch str. 40, 37075 Göttingen, Germany
- Clinic for Cardiology and Pulmonology, Heart Center, University Medical
Center Göttingen, Robert-Koch Str. 40, 37075 Göttingen, Germany
| |
Collapse
|
4
|
Kazemian S, Issaiy M, Hosseini K. Challenges in developing and validating machine learning models for transcatheter aortic valve implantation mortality risk prediction. EUROPEAN HEART JOURNAL. DIGITAL HEALTH 2024; 5:1-2. [PMID: 38264706 PMCID: PMC10802814 DOI: 10.1093/ehjdh/ztad059] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Download PDF] [Subscribe] [Scholar Register] [Indexed: 01/25/2024]
Affiliation(s)
- Sina Kazemian
- Cardiac Primary Prevention Research Center, Cardiovascular Diseases Research Institute, Tehran University of Medical Sciences, Tehran Heart Center, Kargar St. Jalal al-Ahmad Cross, 1411713138, Tehran, Iran
- Tehran Heart Center, Cardiovascular Diseases Research Institute, Tehran University of Medical Sciences, Imam Khomeini Hospital Complex, Tohid Square, 1419733141, Tehran, Iran
| | - Mahbod Issaiy
- Advanced Diagnostic and Interventional Radiology Research Center (ADHR), Tehran University of Medical Sciences, Tehran, Iran
| | - Kaveh Hosseini
- Cardiac Primary Prevention Research Center, Cardiovascular Diseases Research Institute, Tehran University of Medical Sciences, Tehran Heart Center, Kargar St. Jalal al-Ahmad Cross, 1411713138, Tehran, Iran
- Tehran Heart Center, Cardiovascular Diseases Research Institute, Tehran University of Medical Sciences, Imam Khomeini Hospital Complex, Tohid Square, 1419733141, Tehran, Iran
| |
Collapse
|