1
|
Christie S, Tam R, Laksman Z. Artificial Intelligence in Cardiology Research: How to Upskill. Can J Cardiol 2024; 40:1322-1325. [PMID: 38163479 DOI: 10.1016/j.cjca.2023.12.028] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/29/2023] [Revised: 11/27/2023] [Accepted: 12/12/2023] [Indexed: 01/03/2024] Open
Affiliation(s)
- Simon Christie
- Faculty of Medicine, Division of Cardiology, University of British Columbia, Vancouver, British Columbia, Canada.
| | - Roger Tam
- School of Biomedical Engineering, University of British Columbia, Vancouver, British Columbia, Canada; Department of Radiology, Faculty of Medicine, University of British Columbia, Vancouver, British Columbia, Canada
| | - Zachary Laksman
- Faculty of Medicine, Division of Cardiology, University of British Columbia, Vancouver, British Columbia, Canada; School of Biomedical Engineering, University of British Columbia, Vancouver, British Columbia, Canada; Centre for Heart Lung Innovation, University of British Columbia, St Paul's Hospital, Vancouver, British Columbia, Canada
| |
Collapse
|
2
|
Yagi R, Goto S, Himeno Y, Katsumata Y, Hashimoto M, MacRae CA, Deo RC. Artificial intelligence-enabled prediction of chemotherapy-induced cardiotoxicity from baseline electrocardiograms. Nat Commun 2024; 15:2536. [PMID: 38514629 PMCID: PMC10957877 DOI: 10.1038/s41467-024-45733-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/21/2023] [Accepted: 02/02/2024] [Indexed: 03/23/2024] Open
Abstract
Anthracyclines can cause cancer therapy-related cardiac dysfunction (CTRCD) that adversely affects prognosis. Despite guideline recommendations, only half of the patients undergo surveillance echocardiograms. An AI model detecting reduced left ventricular ejection fraction from 12-lead electrocardiograms (ECG) (AI-EF model) suggests ECG features reflect left ventricular pathophysiology. We hypothesized that AI could predict CTRCD from baseline ECG, leveraging the AI-EF model's insights, and developed the AI-CTRCD model using transfer learning on the AI-EF model. In 1011 anthracycline-treated patients, 8.7% experienced CTRCD. High AI-CTRCD scores indicated elevated CTRCD risk (hazard ratio (HR), 2.66; 95% CI 1.73-4.10; log-rank p < 0.001). This remained consistent after adjusting for risk factors (adjusted HR, 2.57; 95% CI 1.62-4.10; p < 0.001). AI-CTRCD score enhanced prediction beyond known factors (time-dependent AUC for 2 years: 0.78 with AI-CTRCD score vs. 0.74 without; p = 0.005). In conclusion, the AI model robustly stratified CTRCD risk from baseline ECG.
Collapse
Affiliation(s)
- Ryuichiro Yagi
- One Brave Idea and Division of Cardiovascular Medicine, Department of Medicine, Brigham and Women's Hospital, Boston, MA, USA
- Harvard Medical School, Boston, MA, USA
- Department of Preventive Medicine and Public Health, Keio University School of Medicine, Tokyo, Japan
| | - Shinichi Goto
- One Brave Idea and Division of Cardiovascular Medicine, Department of Medicine, Brigham and Women's Hospital, Boston, MA, USA
- Harvard Medical School, Boston, MA, USA
- Division of General Internal Medicine & Family Medicine, Department of General and Acute Medicine, Tokai University School of Medicine, Isehara, Kanagawa, Japan
| | - Yukihiro Himeno
- Department of Cardiology, Keio University School of Medicine, Tokyo, Japan
| | - Yoshinori Katsumata
- Institute for Integrated Sports Medicine, Keio University School of Medicine, Tokyo, Japan
| | - Masahiro Hashimoto
- Department of Radiology, Keio University School of Medicine, Tokyo, Japan
| | - Calum A MacRae
- One Brave Idea and Division of Cardiovascular Medicine, Department of Medicine, Brigham and Women's Hospital, Boston, MA, USA
- Harvard Medical School, Boston, MA, USA
| | - Rahul C Deo
- One Brave Idea and Division of Cardiovascular Medicine, Department of Medicine, Brigham and Women's Hospital, Boston, MA, USA.
- Harvard Medical School, Boston, MA, USA.
| |
Collapse
|
3
|
Makimoto H, Kohro T. Adopting artificial intelligence in cardiovascular medicine: a scoping review. Hypertens Res 2024; 47:685-699. [PMID: 37907600 DOI: 10.1038/s41440-023-01469-7] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/01/2023] [Revised: 09/03/2023] [Accepted: 09/26/2023] [Indexed: 11/02/2023]
Abstract
Recent years have witnessed significant transformations in cardiovascular medicine, driven by the rapid evolution of artificial intelligence (AI). This scoping review was conducted to capture the breadth of AI applications within cardiovascular science. Employing a structured approach, we sourced relevant articles from PubMed, with an emphasis on journals encompassing general cardiology and digital medicine. We applied filters to highlight cardiovascular articles published in journals focusing on general internal medicine, cardiology and digital medicine, thereby identifying the prevailing trends in the field. Following a comprehensive full-text screening, a total of 140 studies were identified. Over the preceding 5 years, cardiovascular medicine's interplay with AI has seen an over tenfold augmentation. This expansive growth encompasses multiple cardiovascular subspecialties, including but not limited to, general cardiology, ischemic heart disease, heart failure, and arrhythmia. Deep learning emerged as the predominant methodology. The majority of AI endeavors in this domain have been channeled toward enhancing diagnostic and prognostic capabilities, utilizing resources such as hospital datasets, electrocardiograms, and echocardiography. A significant uptrend was observed in AI's application for omics data analysis. However, a clear gap persists in AI's full-scale integration into the clinical decision-making framework. AI, particularly deep learning, has demonstrated robust applications across cardiovascular subspecialties, indicating its transformative potential in this field. As we continue on this trajectory, ensuring the alignment of technological progress with medical ethics becomes crucial. The abundant digital health data today further accentuates the need for meticulous systematic reviews, tailoring them to each cardiovascular subspecialty.
Collapse
Affiliation(s)
- Hisaki Makimoto
- Data Science Center/Cardiovascular Center, Jichi Medical University, Shimotsuke, Japan.
| | - Takahide Kohro
- Data Science Center/Cardiovascular Center, Jichi Medical University, Shimotsuke, Japan
| |
Collapse
|
4
|
König S, Hohenstein S, Nitsche A, Pellissier V, Leiner J, Stellmacher L, Hindricks G, Bollmann A. Artificial intelligence-based identification of left ventricular systolic dysfunction from 12-lead electrocardiograms: external validation and advanced application of an existing model. EUROPEAN HEART JOURNAL. DIGITAL HEALTH 2024; 5:144-151. [PMID: 38505486 PMCID: PMC10944686 DOI: 10.1093/ehjdh/ztad081] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 08/07/2023] [Revised: 12/06/2023] [Accepted: 12/14/2023] [Indexed: 03/21/2024]
Abstract
Aims The diagnostic application of artificial intelligence (AI)-based models to detect cardiovascular diseases from electrocardiograms (ECGs) evolves, and promising results were reported. However, external validation is not available for all published algorithms. The aim of this study was to validate an existing algorithm for the detection of left ventricular systolic dysfunction (LVSD) from 12-lead ECGs. Methods and results Patients with digitalized data pairs of 12-lead ECGs and echocardiography (at intervals of ≤7 days) were retrospectively selected from the Heart Center Leipzig ECG and electronic medical records databases. A previously developed AI-based model was applied to ECGs and calculated probabilities for LVSD. The area under the receiver operating characteristic curve (AUROC) was computed overall and in cohorts stratified for baseline and ECG characteristics. Repeated echocardiography studies recorded ≥3 months after index diagnostics were used for follow-up (FU) analysis. At baseline, 42 291 ECG-echocardiography pairs were analysed, and AUROC for LVSD detection was 0.88. Sensitivity and specificity were 82% and 77% for the optimal LVSD probability cut-off based on Youden's J. AUROCs were lower in ECG subgroups with tachycardia, atrial fibrillation, and wide QRS complexes. In patients without LVSD at baseline and available FU, model-generated high probability for LVSD was associated with a four-fold increased risk of developing LVSD during FU. Conclusion We provide the external validation of an existing AI-based ECG-analysing model for the detection of LVSD with robust performance metrics. The association of false positive LVSD screenings at baseline with a deterioration of ventricular function during FU deserves a further evaluation in prospective trials.
Collapse
Affiliation(s)
- Sebastian König
- Department of Electrophysiology, Heart Center Leipzig at University of Leipzig, Strümpellstr. 39, 04289 Leipzig, Germany
- Helios Health Institute, Real World Evidence & Health Technology Assessment, Schwanebecker Chaussee 50, 13125 Berlin, Germany
| | - Sven Hohenstein
- Helios Health Institute, Real World Evidence & Health Technology Assessment, Schwanebecker Chaussee 50, 13125 Berlin, Germany
| | - Anne Nitsche
- Helios Health Institute, Real World Evidence & Health Technology Assessment, Schwanebecker Chaussee 50, 13125 Berlin, Germany
| | - Vincent Pellissier
- Helios Health Institute, Real World Evidence & Health Technology Assessment, Schwanebecker Chaussee 50, 13125 Berlin, Germany
| | - Johannes Leiner
- Department of Electrophysiology, Heart Center Leipzig at University of Leipzig, Strümpellstr. 39, 04289 Leipzig, Germany
- Helios Health Institute, Real World Evidence & Health Technology Assessment, Schwanebecker Chaussee 50, 13125 Berlin, Germany
| | - Lars Stellmacher
- Department of Electrophysiology, Heart Center Leipzig at University of Leipzig, Strümpellstr. 39, 04289 Leipzig, Germany
- Helios Health Institute, Real World Evidence & Health Technology Assessment, Schwanebecker Chaussee 50, 13125 Berlin, Germany
| | - Gerhard Hindricks
- Department of Electrophysiology, Heart Center Leipzig at University of Leipzig, Strümpellstr. 39, 04289 Leipzig, Germany
| | - Andreas Bollmann
- Department of Electrophysiology, Heart Center Leipzig at University of Leipzig, Strümpellstr. 39, 04289 Leipzig, Germany
- Helios Health Institute, Real World Evidence & Health Technology Assessment, Schwanebecker Chaussee 50, 13125 Berlin, Germany
| |
Collapse
|
5
|
Di Costanzo A, Spaccarotella CAM, Esposito G, Indolfi C. An Artificial Intelligence Analysis of Electrocardiograms for the Clinical Diagnosis of Cardiovascular Diseases: A Narrative Review. J Clin Med 2024; 13:1033. [PMID: 38398346 PMCID: PMC10889404 DOI: 10.3390/jcm13041033] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/25/2023] [Revised: 02/04/2024] [Accepted: 02/08/2024] [Indexed: 02/25/2024] Open
Abstract
Artificial intelligence (AI) applied to cardiovascular disease (CVD) is enjoying great success in the field of scientific research. Electrocardiograms (ECGs) are the cornerstone form of examination in cardiology and are the most widely used diagnostic tool because they are widely available, inexpensive, and fast. Applications of AI to ECGs, especially deep learning (DL) methods using convolutional neural networks (CNNs), have been developed in many fields of cardiology in recent years. Deep learning methods provide valuable support for rapid ECG interpretation, demonstrating a diagnostic capability overlapping with specialists in the diagnosis of CVD by a classical analysis of macroscopic changes in the ECG trace. Through photoplethysmography, wearable devices can obtain single-derivative ECGs for the recognition of AI-diagnosed arrhythmias. In addition, CNNs have been developed that recognize no macroscopic electrocardiographic changes and can predict, from a 12-lead ECG, atrial fibrillation, even from sinus rhythm; left and right ventricular function; hypertrophic cardiomyopathy; acute coronary syndromes; or aortic stenosis. The fields of application are many, but numerous are the limitations, mainly associated with the reliability of the acquired data, an inability to verify black box processes, and medico-legal and ethical problems. The challenge of modern medicine is to recognize the limitations of AI and overcome them.
Collapse
Affiliation(s)
- Assunta Di Costanzo
- Division of Cardiology, Cardiovascular Research Center, University Magna Graecia Catanzaro, 88100 Catanzaro, Italy
| | - Carmen Anna Maria Spaccarotella
- Division of Cardiology, Department of Advanced Biomedical Sciences, University of Naples Federico II, 80126 Naples, Italy; (C.A.M.S.)
| | - Giovanni Esposito
- Division of Cardiology, Department of Advanced Biomedical Sciences, University of Naples Federico II, 80126 Naples, Italy; (C.A.M.S.)
| | - Ciro Indolfi
- Division of Cardiology, Cardiovascular Research Center, University Magna Graecia Catanzaro, 88100 Catanzaro, Italy
| |
Collapse
|
6
|
Naik N, Talyshinskii A, Shetty DK, Hameed BMZ, Zhankina R, Somani BK. Smart Diagnosis of Urinary Tract Infections: is Artificial Intelligence the Fast-Lane Solution? Curr Urol Rep 2024; 25:37-47. [PMID: 38112900 PMCID: PMC10787904 DOI: 10.1007/s11934-023-01192-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 12/01/2023] [Indexed: 12/21/2023]
Abstract
PURPOSE OF REVIEW Artificial intelligence (AI) can significantly improve physicians' workflow when examining patients with UTI. However, most contemporary reviews are focused on examining the usage of AI with a restricted quantity of data, analyzing only a subset of AI algorithms, or performing narrative work without analyzing all dedicated studies. Given the preceding, the goal of this work was to conduct a mini-review to determine the current state of AI-based systems as a support in UTI diagnosis. RECENT FINDINGS There are sufficient publications to comprehend the potential applications of artificial intelligence in the diagnosis of UTIs. Existing research in this field, in general, publishes performance metrics that are exemplary. However, upon closer inspection, many of the available publications are burdened with flaws associated with the improper use of artificial intelligence, such as the use of a small number of samples, their lack of heterogeneity, and the absence of external validation. AI-based models cannot be classified as full-fledged physician assistants in diagnosing UTIs due to the fact that these limitations and flaws represent only a portion of all potential obstacles. Instead, such studies should be evaluated as exploratory, with a focus on the importance of future work that complies with all rules governing the use of AI. AI algorithms have demonstrated their potential for UTI diagnosis. However, further studies utilizing large, heterogeneous, prospectively collected datasets, as well as external validations, are required to define the actual clinical workflow value of artificial intelligence.
Collapse
Affiliation(s)
- Nithesh Naik
- Department of Mechanical and Industrial Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, 576104, Karnataka, India.
| | - Ali Talyshinskii
- Department of Urology, Astana Medical University, Astana, 010000, Kazakhstan
| | - Dasharathraj K Shetty
- Department of Data Science and Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, 576104, Karnataka, India
| | - B M Zeeshan Hameed
- Department of Urology, Father Muller Medical College, Mangalore, 575002, Karnataka, India
- iTRUE-International Training and Research in Urology and Endourology, Manipal, 576104, Karnataka, India
| | - Rano Zhankina
- Department of Urology, Astana Medical University, Astana, 010000, Kazakhstan
| | - Bhaskar K Somani
- iTRUE-International Training and Research in Urology and Endourology, Manipal, 576104, Karnataka, India
- Department of Urology, University Hospital Southampton NHS Trust, Southampton, SO16 6YD, UK
| |
Collapse
|
7
|
Yamasawa D, Ozawa H, Goto S. The Importance of Interpretability and Validations of Machine-Learning Models. Circ J 2023; 88:157-158. [PMID: 38057101 DOI: 10.1253/circj.cj-23-0857] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/08/2023]
Affiliation(s)
| | - Hideki Ozawa
- Department of Medicine, Tokai University School of Medicine
| | - Shinichi Goto
- Department of Medicine, Tokai University School of Medicine
| |
Collapse
|
8
|
Elshoeibi AM, Badr A, Elsayed B, Metwally O, Elshoeibi R, Elhadary MR, Elshoeibi A, Attya MA, Khadadah F, Alshurafa A, Alhuraiji A, Yassin M. Integrating AI and ML in Myelodysplastic Syndrome Diagnosis: State-of-the-Art and Future Prospects. Cancers (Basel) 2023; 16:65. [PMID: 38201493 PMCID: PMC10778500 DOI: 10.3390/cancers16010065] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/14/2023] [Revised: 10/24/2023] [Accepted: 10/27/2023] [Indexed: 01/12/2024] Open
Abstract
Myelodysplastic syndrome (MDS) is composed of diverse hematological malignancies caused by dysfunctional stem cells, leading to abnormal hematopoiesis and cytopenia. Approximately 30% of MDS cases progress to acute myeloid leukemia (AML), a more aggressive disease. Early detection is crucial to intervene before MDS progresses to AML. The current diagnostic process for MDS involves analyzing peripheral blood smear (PBS), bone marrow sample (BMS), and flow cytometry (FC) data, along with clinical patient information, which is labor-intensive and time-consuming. Recent advancements in machine learning offer an opportunity for faster, automated, and accurate diagnosis of MDS. In this review, we aim to provide an overview of the current applications of AI in the diagnosis of MDS and highlight their advantages, disadvantages, and performance metrics.
Collapse
Affiliation(s)
| | - Ahmed Badr
- College of Medicine, QU Health, Qatar University, Doha 2713, Qatar
| | - Basel Elsayed
- College of Medicine, QU Health, Qatar University, Doha 2713, Qatar
| | - Omar Metwally
- College of Medicine, QU Health, Qatar University, Doha 2713, Qatar
| | | | | | | | | | - Fatima Khadadah
- Kuwait Cancer Centre, Sabah Medical Region, Shuwaikh 1031, Kuwait
| | - Awni Alshurafa
- Hematology Section, Medical Oncology, National Center for Cancer Care and Research (NCCCR), Hamad Medical Corporation, Doha 3050, Qatar
| | - Ahmad Alhuraiji
- Kuwait Cancer Centre, Sabah Medical Region, Shuwaikh 1031, Kuwait
| | - Mohamed Yassin
- College of Medicine, QU Health, Qatar University, Doha 2713, Qatar
- Hematology Section, Medical Oncology, National Center for Cancer Care and Research (NCCCR), Hamad Medical Corporation, Doha 3050, Qatar
| |
Collapse
|
9
|
Khurshid S. Clinical perspectives on the adoption of the artificial intelligence-enabled electrocardiogram. J Electrocardiol 2023; 81:142-145. [PMID: 37696174 PMCID: PMC11185998 DOI: 10.1016/j.jelectrocard.2023.08.014] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/01/2023] [Revised: 08/22/2023] [Accepted: 08/27/2023] [Indexed: 09/13/2023]
Abstract
The 12‑lead electrocardiogram (ECG) is a common and inexpensive diagnostic modality available at scale. The ECG reflects electrical activity throughout the cardiac cycle and is increasingly recognized to contain rich signal relevant across the spectrum of human conditions. Recent work has demonstrated that artificial intelligence (AI)-based algorithms may be able to extract latent information from within the 12‑lead ECG to classify the presence of disease and even predict the development of future disease. Despite recent development of many AI-based ECG algorithms, comparably few are used in routine clinical practice. Therefore, there is a critical unmet need to identify and mitigate potential barriers to the real-world clinical implementation of AI algorithms. We propose that the adoption of the AI-enabled ECG may be increased by future efforts focused on three key principles: a) maximizing credibility, b) optimizing practicality, and c) establishing clinical utility. In this mini-review, we discuss recent notable work focused on these principles and provide suggestions for future directions. AI-enabled ECG analysis possesses substantial potential to transform current methods to prevent, diagnose, and treat human disease, but a greater emphasis on their real-world application is required to bring that potential to reality.
Collapse
Affiliation(s)
- Shaan Khurshid
- Cardiovascular Research Center, Massachusetts General Hospital, Boston, MA, USA; Demoulas Center for Cardiac Arrhythmias, Cardiology Division, Massachusetts General Hospital, Boston, MA, USA; Cardiovascular Disease Initiative, The Broad Institute of MIT and Harvard, Cambridge, MA, USA.
| |
Collapse
|
10
|
Goto S, Ozawa H. The Importance of External Validation for Neural Network Models. JACC. ADVANCES 2023; 2:100610. [PMID: 38938365 PMCID: PMC11198197 DOI: 10.1016/j.jacadv.2023.100610] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 06/29/2024]
Affiliation(s)
- Shinichi Goto
- Division of General Internal Medicine & Family Medicine, Department of General and Acute Medicine, Tokai University School of Medicine, Isehara, Japan
- Division of Cardiovascular Medicine, Department of Medicine, Brigham and Women’s Hospital/Harvard Medical School, Boston, Massachusetts, USA
| | - Hideki Ozawa
- Division of General Internal Medicine & Family Medicine, Department of General and Acute Medicine, Tokai University School of Medicine, Isehara, Japan
| |
Collapse
|
11
|
Miura K, Yagi R, Miyama H, Kimura M, Kanazawa H, Hashimoto M, Kobayashi S, Nakahara S, Ishikawa T, Taguchi I, Sano M, Sato K, Fukuda K, Deo RC, MacRae CA, Itabashi Y, Katsumata Y, Goto S. Deep learning-based model detects atrial septal defects from electrocardiography: a cross-sectional multicenter hospital-based study. EClinicalMedicine 2023; 63:102141. [PMID: 37753448 PMCID: PMC10518511 DOI: 10.1016/j.eclinm.2023.102141] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/09/2023] [Revised: 07/20/2023] [Accepted: 07/24/2023] [Indexed: 09/28/2023] Open
Abstract
Background Atrial septal defect (ASD) increases the risk of adverse cardiovascular outcomes. Despite the potential for risk mitigation through minimally invasive percutaneous closure, ASD remains underdiagnosed due to subtle symptoms and examination findings. To bridge this diagnostic gap, we propose a novel screening strategy aimed at early detection and enhanced diagnosis through the implementation of a convolutional neural network (CNN) to identify ASD from 12-lead electrocardiography (ECG). Methods ECGs were collected from patients with at least one recorded echocardiogram at 3 hospitals from 2 continents (Keio University Hospital from July 2011 to December 2020, Brigham and Women's Hospital from January 2015 to December 2020, and Dokkyo Medical University Saitama Medical Center from January 2010 and December 2021). ECGs from patients with a diagnosis of ASD were labeled as positive cases while the remainder were labeled as negative. ECGs after the closure of ASD were excluded. After randomly splitting the ECGs into 3 datasets (50% derivation, 20% validation, and 30% test) with no patient overlap, a CNN-based model was trained using the derivation datasets from 2 hospitals and was tested on held-out datasets along with an external validation on the 3rd hospital. All eligible ECGs were used for derivation and validation whereas the earliest ECG for each patient was used for the test and external validation. The discrimination of ASD was assessed by the area under the receiver operating characteristic curve (AUROC). Multiple subgroups were examined to identify any heterogeneity. Findings A total of 671,201 ECGs from 80,947 patients were collected from the 3 institutions. The AUROC for detecting ASD was 0.85-0.90 across the 3 hospitals. The subgroup analysis showed excellent performance across various characteristics Screening simulation using the model greatly increased sensitivity from 80.6% to 93.7% at specificity 33.6% when compared to using overt ECG abnormalities. Interpretation A CNN-based model using 12-lead ECG successfully identified the presence of ASD with excellent generalizability across institutions from 2 separate continents. Funding This work was supported by research grants from JST (JPMJPF2101), JSR corporation, Taiju Life Social Welfare Foundation, Kondou Kinen Medical Foundation, Research fund of Mitsukoshi health and welfare foundation, Tokai University School of Medicine Project Research and Internal Medicine Project Research, Secom Science and Technology Foundation, and Grants from AMED (JP23hma922012 and JP23ym0126813). This work was partially supported by One Brave Idea, co-funded by the American Heart Association and Verily with significant support from AstraZeneca and pillar support from Quest Diagnostics.
Collapse
Affiliation(s)
- Kotaro Miura
- Department of Cardiology, Keio University School of Medicine, Tokyo, Japan
- Institute for Integrated Sports Medicine, Keio University School of Medicine, Tokyo, Japan
| | - Ryuichiro Yagi
- Division of Cardiovascular Medicine, Department of Medicine, Brigham and Women’s Hospital, Boston, USA
- Harvard Medical School, Boston, MA, USA
| | - Hiroshi Miyama
- Department of Cardiology, Keio University School of Medicine, Tokyo, Japan
| | - Mai Kimura
- Department of Cardiology, Keio University School of Medicine, Tokyo, Japan
| | - Hideaki Kanazawa
- Department of Cardiology, Keio University School of Medicine, Tokyo, Japan
| | - Masahiro Hashimoto
- Department of Radiology, Keio University School of Medicine, Tokyo, Japan
| | - Sayuki Kobayashi
- Department of Cardiology, Dokkyo Medical University Saitama Medical Center, Saitama, Japan
| | - Shiro Nakahara
- Department of Cardiology, Dokkyo Medical University Saitama Medical Center, Saitama, Japan
| | - Tetsuya Ishikawa
- Department of Cardiology, Dokkyo Medical University Saitama Medical Center, Saitama, Japan
| | - Isao Taguchi
- Department of Cardiology, Dokkyo Medical University Saitama Medical Center, Saitama, Japan
| | - Motoaki Sano
- Department of Cardiology, Keio University School of Medicine, Tokyo, Japan
| | - Kazuki Sato
- Institute for Integrated Sports Medicine, Keio University School of Medicine, Tokyo, Japan
| | - Keiichi Fukuda
- Department of Cardiology, Keio University School of Medicine, Tokyo, Japan
| | - Rahul C. Deo
- Division of Cardiovascular Medicine, Department of Medicine, Brigham and Women’s Hospital, Boston, USA
- Harvard Medical School, Boston, MA, USA
| | - Calum A. MacRae
- Division of Cardiovascular Medicine, Department of Medicine, Brigham and Women’s Hospital, Boston, USA
- Harvard Medical School, Boston, MA, USA
| | - Yuji Itabashi
- Department of Cardiology, Dokkyo Medical University Saitama Medical Center, Saitama, Japan
| | - Yoshinori Katsumata
- Department of Cardiology, Keio University School of Medicine, Tokyo, Japan
- Institute for Integrated Sports Medicine, Keio University School of Medicine, Tokyo, Japan
| | - Shinichi Goto
- Department of Cardiology, Keio University School of Medicine, Tokyo, Japan
- Division of Cardiovascular Medicine, Department of Medicine, Brigham and Women’s Hospital, Boston, USA
- Harvard Medical School, Boston, MA, USA
- Division of General Internal Medicine & Family Medicine, Department of General and Acute Medicine, Tokai University School of Medicine, Isehara, Japan
| |
Collapse
|
12
|
Gruwez H, Barthels M, Haemers P, Verbrugge FH, Dhont S, Meekers E, Wouters F, Nuyens D, Pison L, Vandervoort P, Pierlet N. Detecting Paroxysmal Atrial Fibrillation From an Electrocardiogram in Sinus Rhythm: External Validation of the AI Approach. JACC Clin Electrophysiol 2023; 9:1771-1782. [PMID: 37354171 DOI: 10.1016/j.jacep.2023.04.008] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/06/2023] [Revised: 03/29/2023] [Accepted: 04/10/2023] [Indexed: 06/26/2023]
Abstract
BACKGROUND Atrial fibrillation (AF) may occur asymptomatically and can be diagnosed only with electrocardiography (ECG) while the arrhythmia is present. OBJECTIVES The aim of this study was to independently validate the approach of using artificial intelligence (AI) to identify underlying paroxysmal AF from a 12-lead ECG in sinus rhythm (SR). METHODS An AI algorithm was trained to identify patients with underlying paroxysmal AF, using electrocardiographic data from all in- and outpatients from a single center with at least 1 ECG in SR. For patients without AF, all ECGs in SR were included. For patients with AF, all ECGs in SR starting 31 days before the first AF event were included. The patients were randomly allocated to training, internal validation, and testing datasets in a 7:1:2 ratio. In a secondary analysis, the AF prevalence of the testing group was modified. Additionally, the performance of the algorithm was validated at an external hospital. RESULTS The dataset consisted of 494,042 ECGs in SR from 142,310 patients. Testing the model on the first ECG of each patient (AF prevalence 9.0%) resulted in accuracy of 78.1% (95% CI: 77.6%-78.5%), area under the receiver-operating characteristic curve of 0.87 (95% CI: 0.86-0.87), and area under the precision recall curve (AUPRC) of 0.48 (95% CI: 0.46-0.50). In a low-risk group (AF prevalence 3%), the AUPRC decreased to 0.21 (95% CI: 0.18-0.24). In a high-risk group (AF prevalence 30%), the AUPRC increased to 0.76 (95% CI: 0.75-0.78). This performance was robust when validated in an external hospital. CONCLUSIONS The approach of using an AI-enabled electrocardiographic algorithm for the identification of patients with underlying paroxysmal AF from ECGs in SR was independently validated.
Collapse
Affiliation(s)
- Henri Gruwez
- Department of Cardiology, Hospital East-Limburg, Genk, Belgium; Department of Cardiovascular Sciences, University of Leuven, Leuven, Belgium; Doctoral School of Medicine and Life Science, Hasselt University, Hasselt, Belgium
| | - Myrte Barthels
- Data Science Department, Hospital East-Limburg, Genk, Belgium
| | - Peter Haemers
- Department of Cardiovascular Sciences, University of Leuven, Leuven, Belgium
| | - Frederik H Verbrugge
- Centre for Cardiovascular Diseases, University Hospital Brussels, Jette, Belgium; Faculty of Medicine and Pharmacy, Vrije Universiteit Brussel, Brussels, Belgium
| | - Sebastiaan Dhont
- Department of Cardiology, Hospital East-Limburg, Genk, Belgium; Doctoral School of Medicine and Life Science, Hasselt University, Hasselt, Belgium
| | - Evelyne Meekers
- Department of Cardiology, Hospital East-Limburg, Genk, Belgium; Department of Cardiovascular Sciences, University of Leuven, Leuven, Belgium; Doctoral School of Medicine and Life Science, Hasselt University, Hasselt, Belgium
| | - Femke Wouters
- LCRC, Mobile Health Unit, Hasselt University, Hasselt, Belgium; Future Health Department, Hospital East-Limburg, Genk, Belgium
| | - Dieter Nuyens
- Department of Cardiology, Hospital East-Limburg, Genk, Belgium
| | - Laurent Pison
- Department of Cardiology, Hospital East-Limburg, Genk, Belgium
| | | | - Noëlla Pierlet
- Doctoral School of Medicine and Life Science, Hasselt University, Hasselt, Belgium; Data Science Department, Hospital East-Limburg, Genk, Belgium.
| |
Collapse
|